Slide 1

Slide 1 text

Email-based Intelligent Virtual Assistant for Scheduling Presented by Anand Chowdhary Supervised by Dr. Job Zwiers Creative Technology BSc University of Twente Enschede, the Netherlands

Slide 2

Slide 2 text

No content

Slide 3

Slide 3 text

Email-based Intelligent Virtual Assistant for Scheduling Presented by Anand Chowdhary Supervised by Dr. Job Zwiers Creative Technology BSc University of Twente Enschede, the Netherlands

Slide 4

Slide 4 text

Email-based Intelligent Virtual Assistant for Scheduling Presented by Anand Chowdhary Supervised by Dr. Job Zwiers Creative Technology BSc University of Twente Enschede, the Netherlands

Slide 5

Slide 5 text

Email-based Intelligent Virtual Assistant for Scheduling Presented by Anand Chowdhary Supervised by Dr. Job Zwiers Creative Technology BSc University of Twente Enschede, the Netherlands

Slide 6

Slide 6 text

is a creative technologist and entrepreneur. Apart from studying CreaTe, he also co-founded Oswald Labs, an accessibility technology startup, for which he was featured in Forbes and Het Financieele Dagblad lists. He also studied at Santa Clara University as part of the Global Engineering Exchange program, and Bachelor Honors in Science at the UT. Email-based Intelligent Virtual Assistant for Scheduling Presented by Anand Chowdhary Supervised by Dr. Job Zwiers Creative Technology BSc University of Twente Enschede, the Netherlands

Slide 7

Slide 7 text

Email-based Intelligent Virtual Assistant for Scheduling Presented by Anand Chowdhary Supervised by Dr. Job Zwiers Creative Technology BSc University of Twente Enschede, the Netherlands

Slide 8

Slide 8 text

Email-based Intelligent Virtual Assistant for Scheduling Presented by Anand Chowdhary Supervised by Dr. Job Zwiers Creative Technology BSc University of Twente Enschede, the Netherlands

Slide 9

Slide 9 text

Email-based Intelligent Virtual Assistant for Scheduling Presented by Anand Chowdhary Supervised by Dr. Job Zwiers Creative Technology BSc University of Twente Enschede, the Netherlands EIVA

Slide 10

Slide 10 text

Abstract Manually setting up appointments by email wastes tens of hours every month for professionals, because several email exchanges are required before receiving confirmation. Since not everyone can afford to hire full-time assistants, Email-based Intelligent Virtual Assistants (EIVA) can help by automating this task. In this paper, a functional EIVA is developed based on research and industry best-practices with the support of Speakup. Users can simply add their assistant’s address as ‘CC’ in an email, and EIVA will share the recommended location and time slots with guests, based on the user’s availability (using their calendar) and scheduling preferences. A companion web application is also developed to manage meetings and settings. The code is open source and written in TypeScript with Node.js and Vue.js and deployed on Amazon Web Services architecture in Europe. The product is built with focus on data privacy and user personalization. A user experience evaluation of both the EIVA and its app with 30 participants was conducted that found positive reception, with the average rating of the overall assistant and app experience of 4.4 and 4.5 out of 5 respectively. Users’ behavior was also understood with heatmaps and visualizations using pageview and mouse clicks tracking. All but one participants said that the EIVA met their expectations, and 25 out of 30 would use it in the future if it launches as a service. Most would also be willing to pay for it, with an average amount up to €6.16 per month. Participants also shared their frustrations and recommendations for future work. In the future, NLP classification should be improved and user recommendations should be implemented before launching the EIVA service for consumers.

Slide 11

Slide 11 text

Abstract Manually setting up appointments by email wastes tens of hours every month for professionals, because several email exchanges are required before receiving confirmation. Since not everyone can afford to hire full-time assistants, Email-based Intelligent Virtual Assistants (EIVA) can help by automating this task. In this paper, a functional EIVA is developed based on research and industry best-practices with the support of Speakup. Users can simply add their assistant’s address as ‘CC’ in an email, and EIVA will share the recommended location and time slots with guests, based on the user’s availability (using their calendar) and scheduling preferences. A companion web application is also developed to manage meetings and settings. The code is open source and written in TypeScript with Node.js and Vue.js and

Slide 12

Slide 12 text

Abstract Manually setting up appointments by email wastes tens of hours every month for professionals, because several email exchanges are required before receiving confirmation. Since not everyone can afford to hire full-time assistants, Email-based Intelligent Virtual Assistants (EIVA) can help by automating this task. In this paper, a functional EIVA is developed based on research and industry best-practices with the support of Speakup. Users can simply add their assistant’s address as ‘CC’ in an email, and EIVA will share the recommended location and time slots with guests, based on the user’s availability (using their calendar) and scheduling preferences. A companion web application is also developed to manage meetings and settings. The code is open source and written in TypeScript with Node.js and Vue.js and

Slide 13

Slide 13 text

Abstract Manually setting up appointments by email wastes tens of hours every month for professionals, because several email exchanges are required before receiving confirmation. Since not everyone can afford to hire full-time assistants, Email-based Intelligent Virtual Assistants (EIVA) can help by automating this task. In this paper, a functional EIVA is developed based on research and industry best-practices with the support of Speakup. Users can simply add their assistant’s address as ‘CC’ in an email, and EIVA will share the recommended location and time slots with guests, based on the user’s availability (using their calendar) and scheduling preferences. A companion web application is also developed to manage meetings and settings. The code is open source and written in TypeScript with Node.js and Vue.js and 8 out of 10 USE EMAIL FOR SCHEDULING

Slide 14

Slide 14 text

Abstract Manually setting up appointments by email wastes tens of hours every month for professionals, because several email exchanges are required before receiving confirmation. Since not everyone can afford to hire full-time assistants, Email-based Intelligent Virtual Assistants (EIVA) can help by automating this task. In this paper, a functional EIVA is developed based on research and industry best-practices with the support of Speakup. Users can simply add their assistant’s address as ‘CC’ in an email, and EIVA will share the recommended location and time slots with guests, based on the user’s availability (using their calendar) and scheduling preferences. A companion web application is also developed to manage meetings and settings. The code is open source and written in TypeScript with Node.js and Vue.js and 8 out of 10 USE EMAIL FOR SCHEDULING 6 out of 10 MEETINGS ARE RESCHEDULED

Slide 15

Slide 15 text

Abstract Manually setting up appointments by email wastes tens of hours every month for professionals, because several email exchanges are required before receiving confirmation. Since not everyone can afford to hire full-time assistants, Email-based Intelligent Virtual Assistants (EIVA) can help by automating this task. In this paper, a functional EIVA is developed based on research and industry best-practices with the support of Speakup. Users can simply add their assistant’s address as ‘CC’ in an email, and EIVA will share the recommended location and time slots with guests, based on the user’s availability (using their calendar) and scheduling preferences. A companion web application is also developed to manage meetings and settings. The code is open source and written in TypeScript with Node.js and Vue.js and 8 out of 10 USE EMAIL FOR SCHEDULING 6 out of 10 MEETINGS ARE RESCHEDULED €150 per month IN LOST TIME WHILE SCHEDULING

Slide 16

Slide 16 text

Abstract Manually setting up appointments by email wastes tens of hours every month for professionals, because several email exchanges are required before receiving confirmation. Since not everyone can afford to hire full-time assistants, Email-based Intelligent Virtual Assistants (EIVA) can help by automating this task. In this paper, a functional EIVA is developed based on research and industry best-practices with the support of Speakup. Users can simply add their assistant’s address as ‘CC’ in an email, and EIVA will share the recommended location and time slots with guests, based on the user’s availability (using their calendar) and scheduling preferences. A companion web application is also developed to manage meetings and settings. The code is open source and written in TypeScript with Node.js and Vue.js and

Slide 17

Slide 17 text

Abstract Manually setting up appointments by email wastes tens of hours every month for professionals, because several email exchanges are required before receiving confirmation. Since not everyone can afford to hire full-time assistants, Email-based Intelligent Virtual Assistants (EIVA) can help by automating this task. In this paper, a functional EIVA is developed based on research and industry best-practices with the support of Speakup. Users can simply add their assistant’s address as ‘CC’ in an email, and EIVA will share the recommended location and time slots with guests, based on the user’s availability (using their calendar) and scheduling preferences. A companion web application is also developed to manage meetings and settings. The code is open source and written in TypeScript with Node.js and Vue.js and deployed on Amazon Web Services architecture in Europe. The product is built with focus on data privacy and user personalization. A user experience evaluation of both the EIVA and its app with

Slide 18

Slide 18 text

Abstract Manually setting up appointments by email wastes tens of hours every month for professionals, because several email exchanges are required before receiving confirmation. Since not everyone can afford to hire full-time assistants, Email-based Intelligent Virtual Assistants (EIVA) can help by automating this task. In this paper, a functional EIVA is developed based on research and industry best-practices with the support of Speakup. Users can simply add their assistant’s address as ‘CC’ in an email, and EIVA will share the recommended location and time slots with guests, based on the user’s availability (using their calendar) and scheduling preferences. A companion web application is also developed to manage meetings and settings. The code is open source and written in TypeScript with Node.js and Vue.js and deployed on Amazon Web Services architecture in Europe. The product is built with focus on data privacy and user personalization. A user experience evaluation of both the EIVA and its app with

Slide 19

Slide 19 text

Abstract Manually setting up appointments by email wastes tens of hours every month for professionals, because several email exchanges are required before receiving confirmation. Since not everyone can afford to hire full-time assistants, Email-based Intelligent Virtual Assistants (EIVA) can help by automating this task. In this paper, a functional EIVA is developed based on research and industry best-practices with the support of Speakup. Users can simply add their assistant’s address as ‘CC’ in an email, and EIVA will share the recommended location and time slots with guests, based on the user’s availability (using their calendar) and scheduling preferences. A companion web application is also developed to manage meetings and settings. The code is open source and written in TypeScript with Node.js and Vue.js and deployed on Amazon Web Services architecture in Europe. The product is built with focus on data privacy and user personalization. A user experience evaluation of both the EIVA and its app with 9 out of 10 ASK ASSISTANT TO SCHEDULE

Slide 20

Slide 20 text

Abstract Manually setting up appointments by email wastes tens of hours every month for professionals, because several email exchanges are required before receiving confirmation. Since not everyone can afford to hire full-time assistants, Email-based Intelligent Virtual Assistants (EIVA) can help by automating this task. In this paper, a functional EIVA is developed based on research and industry best-practices with the support of Speakup. Users can simply add their assistant’s address as ‘CC’ in an email, and EIVA will share the recommended location and time slots with guests, based on the user’s availability (using their calendar) and scheduling preferences. A companion web application is also developed to manage meetings and settings. The code is open source and written in TypeScript with Node.js and Vue.js and deployed on Amazon Web Services architecture in Europe. The product is built with focus on data privacy and user personalization. A user experience evaluation of both the EIVA and its app with 9 out of 10 ASK ASSISTANT TO SCHEDULE 8 out of 10 AI ASSISTANT FOR SCHEDULING

Slide 21

Slide 21 text

Abstract Manually setting up appointments by email wastes tens of hours every month for professionals, because several email exchanges are required before receiving confirmation. Since not everyone can afford to hire full-time assistants, Email-based Intelligent Virtual Assistants (EIVA) can help by automating this task. In this paper, a functional EIVA is developed based on research and industry best-practices with the support of Speakup. Users can simply add their assistant’s address as ‘CC’ in an email, and EIVA will share the recommended location and time slots with guests, based on the user’s availability (using their calendar) and scheduling preferences. A companion web application is also developed to manage meetings and settings. The code is open source and written in TypeScript with Node.js and Vue.js and deployed on Amazon Web Services architecture in Europe. The product is built with focus on data privacy and user personalization. A user experience evaluation of both the EIVA and its app with 9 out of 10 ASK ASSISTANT TO SCHEDULE 8 out of 10 AI ASSISTANT FOR SCHEDULING THE SOLUTION?

Slide 22

Slide 22 text

Abstract Manually setting up appointments by email wastes tens of hours every month for professionals, because several email exchanges are required before receiving confirmation. Since not everyone can afford to hire full-time assistants, Email-based Intelligent Virtual Assistants (EIVA) can help by automating this task. In this paper, a functional EIVA is developed based on research and industry best-practices with the support of Speakup. Users can simply add their assistant’s address as ‘CC’ in an email, and EIVA will share the recommended location and time slots with guests, based on the user’s availability (using their calendar) and scheduling preferences. A companion web application is also developed to manage meetings and settings. The code is open source and written in TypeScript with Node.js and Vue.js and deployed on Amazon Web Services architecture in Europe. The product is built with focus on data privacy and user personalization. A user experience evaluation of both the EIVA and its app with

Slide 23

Slide 23 text

every month for professionals, because several email exchanges are required before receiving confirmation. Since not everyone can afford to hire full-time assistants, Email-based Intelligent Virtual Assistants (EIVA) can help by automating this task. In this paper, a functional EIVA is developed based on research and industry best-practices with the support of Speakup. Users can simply add their assistant’s address as ‘CC’ in an email, and EIVA will share the recommended location and time slots with guests, based on the user’s availability (using their calendar) and scheduling preferences. A companion web application is also developed to manage meetings and settings. The code is open source and written in TypeScript with Node.js and Vue.js and deployed on Amazon Web Services architecture in Europe. The product is built with focus on data privacy and user personalization. A user experience evaluation of both the EIVA and its app with 30 participants was conducted that found positive reception, with the average rating of the overall assistant and app experience of 4.4 and 4.5 out of 5 respectively. Users’ behavior was also understood

Slide 24

Slide 24 text

every month for professionals, because several email exchanges are required before receiving confirmation. Since not everyone can afford to hire full-time assistants, Email-based Intelligent Virtual Assistants (EIVA) can help by automating this task. In this paper, a functional EIVA is developed based on research and industry best-practices with the support of Speakup. Users can simply add their assistant’s address as ‘CC’ in an email, and EIVA will share the recommended location and time slots with guests, based on the user’s availability (using their calendar) and scheduling preferences. A companion web application is also developed to manage meetings and settings. The code is open source and written in TypeScript with Node.js and Vue.js and deployed on Amazon Web Services architecture in Europe. The product is built with focus on data privacy and user personalization. A user experience evaluation of both the EIVA and its app with 30 participants was conducted that found positive reception, with the average rating of the overall assistant and app experience of 4.4 and 4.5 out of 5 respectively. Users’ behavior was also understood

Slide 25

Slide 25 text

every month for professionals, because several email exchanges are required before receiving confirmation. Since not everyone can afford to hire full-time assistants, Email-based Intelligent Virtual Assistants (EIVA) can help by automating this task. In this paper, a functional EIVA is developed based on research and industry best-practices with the support of Speakup. Users can simply add their assistant’s address as ‘CC’ in an email, and EIVA will share the recommended location and time slots with guests, based on the user’s availability (using their calendar) and scheduling preferences. A companion web application is also developed to manage meetings and settings. The code is open source and written in TypeScript with Node.js and Vue.js and deployed on Amazon Web Services architecture in Europe. The product is built with focus on data privacy and user personalization. A user experience evaluation of both the EIVA and its app with 30 participants was conducted that found positive reception, with the average rating of the overall assistant and app experience of 4.4 and 4.5 out of 5 respectively. Users’ behavior was also understood Florian Overkamp Founder of Speakup B.V.

Slide 26

Slide 26 text

every month for professionals, because several email exchanges are required before receiving confirmation. Since not everyone can afford to hire full-time assistants, Email-based Intelligent Virtual Assistants (EIVA) can help by automating this task. In this paper, a functional EIVA is developed based on research and industry best-practices with the support of Speakup. Users can simply add their assistant’s address as ‘CC’ in an email, and EIVA will share the recommended location and time slots with guests, based on the user’s availability (using their calendar) and scheduling preferences. A companion web application is also developed to manage meetings and settings. The code is open source and written in TypeScript with Node.js and Vue.js and deployed on Amazon Web Services architecture in Europe. The product is built with focus on data privacy and user personalization. A user experience evaluation of both the EIVA and its app with 30 participants was conducted that found positive reception, with the average rating of the overall assistant and app experience of 4.4 and 4.5 out of 5 respectively. Users’ behavior was also understood Idea Research Development External testing Analysis

Slide 27

Slide 27 text

every month for professionals, because several email exchanges are required before receiving confirmation. Since not everyone can afford to hire full-time assistants, Email-based Intelligent Virtual Assistants (EIVA) can help by automating this task. In this paper, a functional EIVA is developed based on research and industry best-practices with the support of Speakup. Users can simply add their assistant’s address as ‘CC’ in an email, and EIVA will share the recommended location and time slots with guests, based on the user’s availability (using their calendar) and scheduling preferences. A companion web application is also developed to manage meetings and settings. The code is open source and written in TypeScript with Node.js and Vue.js and deployed on Amazon Web Services architecture in Europe. The product is built with focus on data privacy and user personalization. A user experience evaluation of both the EIVA and its app with 30 participants was conducted that found positive reception, with the average rating of the overall assistant and app experience of 4.4 and 4.5 out of 5 respectively. Users’ behavior was also understood

Slide 28

Slide 28 text

every month for professionals, because several email exchanges are required before receiving confirmation. Since not everyone can afford to hire full-time assistants, Email-based Intelligent Virtual Assistants (EIVA) can help by automating this task. In this paper, a functional EIVA is developed based on research and industry best-practices with the support of Speakup. Users can simply add their assistant’s address as ‘CC’ in an email, and EIVA will share the recommended location and time slots with guests, based on the user’s availability (using their calendar) and scheduling preferences. A companion web application is also developed to manage meetings and settings. The code is open source and written in TypeScript with Node.js and Vue.js and deployed on Amazon Web Services architecture in Europe. The product is built with focus on data privacy and user personalization. A user experience evaluation of both the EIVA and its app with 30 participants was conducted that found positive reception, with the average rating of the overall assistant and app experience of 4.4 and 4.5 out of 5 respectively. Users’ behavior was also understood

Slide 29

Slide 29 text

every month for professionals, because several email exchanges are required before receiving confirmation. Since not everyone can afford to hire full-time assistants, Email-based Intelligent Virtual Assistants (EIVA) can help by automating this task. In this paper, a functional EIVA is developed based on research and industry best-practices with the support of Speakup. Users can simply add their assistant’s address as ‘CC’ in an email, and EIVA will share the recommended location and time slots with guests, based on the user’s availability (using their calendar) and scheduling preferences. A companion web application is also developed to manage meetings and settings. The code is open source and written in TypeScript with Node.js and Vue.js and deployed on Amazon Web Services architecture in Europe. The product is built with focus on data privacy and user personalization. A user experience evaluation of both the EIVA and its app with 30 participants was conducted that found positive reception, with the average rating of the overall assistant and app experience of 4.4 and 4.5 out of 5 respectively. Users’ behavior was also understood

Slide 30

Slide 30 text

every month for professionals, because several email exchanges are required before receiving confirmation. Since not everyone can afford to hire full-time assistants, Email-based Intelligent Virtual Assistants (EIVA) can help by automating this task. In this paper, a functional EIVA is developed based on research and industry best-practices with the support of Speakup. Users can simply add their assistant’s address as ‘CC’ in an email, and EIVA will share the recommended location and time slots with guests, based on the user’s availability (using their calendar) and scheduling preferences. A companion web application is also developed to manage meetings and settings. The code is open source and written in TypeScript with Node.js and Vue.js and deployed on Amazon Web Services architecture in Europe. The product is built with focus on data privacy and user personalization. A user experience evaluation of both the EIVA and its app with 30 participants was conducted that found positive reception, with the average rating of the overall assistant and app experience of 4.4 and 4.5 out of 5 respectively. Users’ behavior was also understood

Slide 31

Slide 31 text

every month for professionals, because several email exchanges are required before receiving confirmation. Since not everyone can afford to hire full-time assistants, Email-based Intelligent Virtual Assistants (EIVA) can help by automating this task. In this paper, a functional EIVA is developed based on research and industry best-practices with the support of Speakup. Users can simply add their assistant’s address as ‘CC’ in an email, and EIVA will share the recommended location and time slots with guests, based on the user’s availability (using their calendar) and scheduling preferences. A companion web application is also developed to manage meetings and settings. The code is open source and written in TypeScript with Node.js and Vue.js and deployed on Amazon Web Services architecture in Europe. The product is built with focus on data privacy and user personalization. A user experience evaluation of both the EIVA and its app with 30 participants was conducted that found positive reception, with the average rating of the overall assistant and app experience of 4.4 and 4.5 out of 5 respectively. Users’ behavior was also understood

Slide 32

Slide 32 text

every month for professionals, because several email exchanges are required before receiving confirmation. Since not everyone can afford to hire full-time assistants, Email-based Intelligent Virtual Assistants (EIVA) can help by automating this task. In this paper, a functional EIVA is developed based on research and industry best-practices with the support of Speakup. Users can simply add their assistant’s address as ‘CC’ in an email, and EIVA will share the recommended location and time slots with guests, based on the user’s availability (using their calendar) and scheduling preferences. A companion web application is also developed to manage meetings and settings. The code is open source and written in TypeScript with Node.js and Vue.js and deployed on Amazon Web Services architecture in Europe. The product is built with focus on data privacy and user personalization. A user experience evaluation of both the EIVA and its app with 30 participants was conducted that found positive reception, with the average rating of the overall assistant and app experience of 4.4 and 4.5 out of 5 respectively. Users’ behavior was also understood

Slide 33

Slide 33 text

every month for professionals, because several email exchanges are required before receiving confirmation. Since not everyone can afford to hire full-time assistants, Email-based Intelligent Virtual Assistants (EIVA) can help by automating this task. In this paper, a functional EIVA is developed based on research and industry best-practices with the support of Speakup. Users can simply add their assistant’s address as ‘CC’ in an email, and EIVA will share the recommended location and time slots with guests, based on the user’s availability (using their calendar) and scheduling preferences. A companion web application is also developed to manage meetings and settings. The code is open source and written in TypeScript with Node.js and Vue.js and deployed on Amazon Web Services architecture in Europe. The product is built with focus on data privacy and user personalization. A user experience evaluation of both the EIVA and its app with 30 participants was conducted that found positive reception, with the average rating of the overall assistant and app experience of 4.4 and 4.5 out of 5 respectively. Users’ behavior was also understood

Slide 34

Slide 34 text

every month for professionals, because several email exchanges are required before receiving confirmation. Since not everyone can afford to hire full-time assistants, Email-based Intelligent Virtual Assistants (EIVA) can help by automating this task. In this paper, a functional EIVA is developed based on research and industry best-practices with the support of Speakup. Users can simply add their assistant’s address as ‘CC’ in an email, and EIVA will share the recommended location and time slots with guests, based on the user’s availability (using their calendar) and scheduling preferences. A companion web application is also developed to manage meetings and settings. The code is open source and written in TypeScript with Node.js and Vue.js and deployed on Amazon Web Services architecture in Europe. The product is built with focus on data privacy and user personalization. A user experience evaluation of both the EIVA and its app with 30 participants was conducted that found positive reception, with the average rating of the overall assistant and app experience of 4.4 and 4.5 out of 5 respectively. Users’ behavior was also understood

Slide 35

Slide 35 text

every month for professionals, because several email exchanges are required before receiving confirmation. Since not everyone can afford to hire full-time assistants, Email-based Intelligent Virtual Assistants (EIVA) can help by automating this task. In this paper, a functional EIVA is developed based on research and industry best-practices with the support of Speakup. Users can simply add their assistant’s address as ‘CC’ in an email, and EIVA will share the recommended location and time slots with guests, based on the user’s availability (using their calendar) and scheduling preferences. A companion web application is also developed to manage meetings and settings. The code is open source and written in TypeScript with Node.js and Vue.js and deployed on Amazon Web Services architecture in Europe. The product is built with focus on data privacy and user personalization. A user experience evaluation of both the EIVA and its app with 30 participants was conducted that found positive reception, with the average rating of the overall assistant and app experience of 4.4 and 4.5 out of 5 respectively. Users’ behavior was also understood

Slide 36

Slide 36 text

every month for professionals, because several email exchanges are required before receiving confirmation. Since not everyone can afford to hire full-time assistants, Email-based Intelligent Virtual Assistants (EIVA) can help by automating this task. In this paper, a functional EIVA is developed based on research and industry best-practices with the support of Speakup. Users can simply add their assistant’s address as ‘CC’ in an email, and EIVA will share the recommended location and time slots with guests, based on the user’s availability (using their calendar) and scheduling preferences. A companion web application is also developed to manage meetings and settings. The code is open source and written in TypeScript with Node.js and Vue.js and deployed on Amazon Web Services architecture in Europe. The product is built with focus on data privacy and user personalization. A user experience evaluation of both the EIVA and its app with 30 participants was conducted that found positive reception, with the average rating of the overall assistant and app experience of 4.4 and 4.5 out of 5 respectively. Users’ behavior was also understood SCREEN SHARING

Slide 37

Slide 37 text

and industry best-practices with the support of Speakup. Users can simply add their assistant’s address as ‘CC’ in an email, and EIVA will share the recommended location and time slots with guests, based on the user’s availability (using their calendar) and scheduling preferences. A companion web application is also developed to manage meetings and settings. The code is open source and written in TypeScript with Node.js and Vue.js and deployed on Amazon Web Services architecture in Europe. The product is built with focus on data privacy and user personalization. A user experience evaluation of both the EIVA and its app with 30 participants was conducted that found positive reception, with the average rating of the overall assistant and app experience of 4.4 and 4.5 out of 5 respectively. Users’ behavior was also understood with heatmaps and visualizations using pageview and mouse clicks tracking. All but one participants said that the EIVA met their expectations, and 25 out of 30 would use it in the future if it launches as a service. Most would also be willing to pay for it, with an average amount up to €6.16 per month. Participants also shared

Slide 38

Slide 38 text

and industry best-practices with the support of Speakup. Users can simply add their assistant’s address as ‘CC’ in an email, and EIVA will share the recommended location and time slots with guests, based on the user’s availability (using their calendar) and scheduling preferences. A companion web application is also developed to manage meetings and settings. The code is open source and written in TypeScript with Node.js and Vue.js and deployed on Amazon Web Services architecture in Europe. The product is built with focus on data privacy and user personalization. A user experience evaluation of both the EIVA and its app with 30 participants was conducted that found positive reception, with the average rating of the overall assistant and app experience of 4.4 and 4.5 out of 5 respectively. Users’ behavior was also understood with heatmaps and visualizations using pageview and mouse clicks tracking. All but one participants said that the EIVA met their expectations, and 25 out of 30 would use it in the future if it launches as a service. Most would also be willing to pay for it, with an average amount up to €6.16 per month. Participants also shared

Slide 39

Slide 39 text

and industry best-practices with the support of Speakup. Users can simply add their assistant’s address as ‘CC’ in an email, and EIVA will share the recommended location and time slots with guests, based on the user’s availability (using their calendar) and scheduling preferences. A companion web application is also developed to manage meetings and settings. The code is open source and written in TypeScript with Node.js and Vue.js and deployed on Amazon Web Services architecture in Europe. The product is built with focus on data privacy and user personalization. A user experience evaluation of both the EIVA and its app with 30 participants was conducted that found positive reception, with the average rating of the overall assistant and app experience of 4.4 and 4.5 out of 5 respectively. Users’ behavior was also understood with heatmaps and visualizations using pageview and mouse clicks tracking. All but one participants said that the EIVA met their expectations, and 25 out of 30 would use it in the future if it launches as a service. Most would also be willing to pay for it, with an average amount up to €6.16 per month. Participants also shared Natural Language Processing

Slide 40

Slide 40 text

and industry best-practices with the support of Speakup. Users can simply add their assistant’s address as ‘CC’ in an email, and EIVA will share the recommended location and time slots with guests, based on the user’s availability (using their calendar) and scheduling preferences. A companion web application is also developed to manage meetings and settings. The code is open source and written in TypeScript with Node.js and Vue.js and deployed on Amazon Web Services architecture in Europe. The product is built with focus on data privacy and user personalization. A user experience evaluation of both the EIVA and its app with 30 participants was conducted that found positive reception, with the average rating of the overall assistant and app experience of 4.4 and 4.5 out of 5 respectively. Users’ behavior was also understood with heatmaps and visualizations using pageview and mouse clicks tracking. All but one participants said that the EIVA met their expectations, and 25 out of 30 would use it in the future if it launches as a service. Most would also be willing to pay for it, with an average amount up to €6.16 per month. Participants also shared Natural Language Processing Language Detection & Variable Extraction

Slide 41

Slide 41 text

and industry best-practices with the support of Speakup. Users can simply add their assistant’s address as ‘CC’ in an email, and EIVA will share the recommended location and time slots with guests, based on the user’s availability (using their calendar) and scheduling preferences. A companion web application is also developed to manage meetings and settings. The code is open source and written in TypeScript with Node.js and Vue.js and deployed on Amazon Web Services architecture in Europe. The product is built with focus on data privacy and user personalization. A user experience evaluation of both the EIVA and its app with 30 participants was conducted that found positive reception, with the average rating of the overall assistant and app experience of 4.4 and 4.5 out of 5 respectively. Users’ behavior was also understood with heatmaps and visualizations using pageview and mouse clicks tracking. All but one participants said that the EIVA met their expectations, and 25 out of 30 would use it in the future if it launches as a service. Most would also be willing to pay for it, with an average amount up to €6.16 per month. Participants also shared Natural Language Processing Language Detection & Variable Extraction Intent Classification

Slide 42

Slide 42 text

and industry best-practices with the support of Speakup. Users can simply add their assistant’s address as ‘CC’ in an email, and EIVA will share the recommended location and time slots with guests, based on the user’s availability (using their calendar) and scheduling preferences. A companion web application is also developed to manage meetings and settings. The code is open source and written in TypeScript with Node.js and Vue.js and deployed on Amazon Web Services architecture in Europe. The product is built with focus on data privacy and user personalization. A user experience evaluation of both the EIVA and its app with 30 participants was conducted that found positive reception, with the average rating of the overall assistant and app experience of 4.4 and 4.5 out of 5 respectively. Users’ behavior was also understood with heatmaps and visualizations using pageview and mouse clicks tracking. All but one participants said that the EIVA met their expectations, and 25 out of 30 would use it in the future if it launches as a service. Most would also be willing to pay for it, with an average amount up to €6.16 per month. Participants also shared Natural Language Processing Language Detection & Variable Extraction Intent Classification Date Parsing

Slide 43

Slide 43 text

and industry best-practices with the support of Speakup. Users can simply add their assistant’s address as ‘CC’ in an email, and EIVA will share the recommended location and time slots with guests, based on the user’s availability (using their calendar) and scheduling preferences. A companion web application is also developed to manage meetings and settings. The code is open source and written in TypeScript with Node.js and Vue.js and deployed on Amazon Web Services architecture in Europe. The product is built with focus on data privacy and user personalization. A user experience evaluation of both the EIVA and its app with 30 participants was conducted that found positive reception, with the average rating of the overall assistant and app experience of 4.4 and 4.5 out of 5 respectively. Users’ behavior was also understood with heatmaps and visualizations using pageview and mouse clicks tracking. All but one participants said that the EIVA met their expectations, and 25 out of 30 would use it in the future if it launches as a service. Most would also be willing to pay for it, with an average amount up to €6.16 per month. Participants also shared Natural Language Processing Language Detection & Variable Extraction Intent Classification Date Parsing Google Cloud Natural Language API

Slide 44

Slide 44 text

and industry best-practices with the support of Speakup. Users can simply add their assistant’s address as ‘CC’ in an email, and EIVA will share the recommended location and time slots with guests, based on the user’s availability (using their calendar) and scheduling preferences. A companion web application is also developed to manage meetings and settings. The code is open source and written in TypeScript with Node.js and Vue.js and deployed on Amazon Web Services architecture in Europe. The product is built with focus on data privacy and user personalization. A user experience evaluation of both the EIVA and its app with 30 participants was conducted that found positive reception, with the average rating of the overall assistant and app experience of 4.4 and 4.5 out of 5 respectively. Users’ behavior was also understood with heatmaps and visualizations using pageview and mouse clicks tracking. All but one participants said that the EIVA met their expectations, and 25 out of 30 would use it in the future if it launches as a service. Most would also be willing to pay for it, with an average amount up to €6.16 per month. Participants also shared Natural Language Processing Language Detection & Variable Extraction Intent Classification Date Parsing Google Cloud Natural Language API

Slide 45

Slide 45 text

and industry best-practices with the support of Speakup. Users can simply add their assistant’s address as ‘CC’ in an email, and EIVA will share the recommended location and time slots with guests, based on the user’s availability (using their calendar) and scheduling preferences. A companion web application is also developed to manage meetings and settings. The code is open source and written in TypeScript with Node.js and Vue.js and deployed on Amazon Web Services architecture in Europe. The product is built with focus on data privacy and user personalization. A user experience evaluation of both the EIVA and its app with 30 participants was conducted that found positive reception, with the average rating of the overall assistant and app experience of 4.4 and 4.5 out of 5 respectively. Users’ behavior was also understood with heatmaps and visualizations using pageview and mouse clicks tracking. All but one participants said that the EIVA met their expectations, and 25 out of 30 would use it in the future if it launches as a service. Most would also be willing to pay for it, with an average amount up to €6.16 per month. Participants also shared Natural Language Processing Language Detection & Variable Extraction Intent Classification Date Parsing Google Cloud Natural Language API Node Natural with Naive Bayes Classifier natural

Slide 46

Slide 46 text

and industry best-practices with the support of Speakup. Users can simply add their assistant’s address as ‘CC’ in an email, and EIVA will share the recommended location and time slots with guests, based on the user’s availability (using their calendar) and scheduling preferences. A companion web application is also developed to manage meetings and settings. The code is open source and written in TypeScript with Node.js and Vue.js and deployed on Amazon Web Services architecture in Europe. The product is built with focus on data privacy and user personalization. A user experience evaluation of both the EIVA and its app with 30 participants was conducted that found positive reception, with the average rating of the overall assistant and app experience of 4.4 and 4.5 out of 5 respectively. Users’ behavior was also understood with heatmaps and visualizations using pageview and mouse clicks tracking. All but one participants said that the EIVA met their expectations, and 25 out of 30 would use it in the future if it launches as a service. Most would also be willing to pay for it, with an average amount up to €6.16 per month. Participants also shared Natural Language Processing Language Detection & Variable Extraction Intent Classification Date Parsing Google Cloud Natural Language API Node Natural with Naive Bayes Classifier natural Chrono Node with custom filters Chrono

Slide 47

Slide 47 text

and industry best-practices with the support of Speakup. Users can simply add their assistant’s address as ‘CC’ in an email, and EIVA will share the recommended location and time slots with guests, based on the user’s availability (using their calendar) and scheduling preferences. A companion web application is also developed to manage meetings and settings. The code is open source and written in TypeScript with Node.js and Vue.js and deployed on Amazon Web Services architecture in Europe. The product is built with focus on data privacy and user personalization. A user experience evaluation of both the EIVA and its app with 30 participants was conducted that found positive reception, with the average rating of the overall assistant and app experience of 4.4 and 4.5 out of 5 respectively. Users’ behavior was also understood with heatmaps and visualizations using pageview and mouse clicks tracking. All but one participants said that the EIVA met their expectations, and 25 out of 30 would use it in the future if it launches as a service. Most would also be willing to pay for it, with an average amount up to €6.16 per month. Participants also shared Natural Language Processing Intent Classification Node Natural with Naive Bayes Classifier natural

Slide 48

Slide 48 text

and industry best-practices with the support of Speakup. Users can simply add their assistant’s address as ‘CC’ in an email, and EIVA will share the recommended location and time slots with guests, based on the user’s availability (using their calendar) and scheduling preferences. A companion web application is also developed to manage meetings and settings. The code is open source and written in TypeScript with Node.js and Vue.js and deployed on Amazon Web Services architecture in Europe. The product is built with focus on data privacy and user personalization. A user experience evaluation of both the EIVA and its app with 30 participants was conducted that found positive reception, with the average rating of the overall assistant and app experience of 4.4 and 4.5 out of 5 respectively. Users’ behavior was also understood with heatmaps and visualizations using pageview and mouse clicks tracking. All but one participants said that the EIVA met their expectations, and 25 out of 30 would use it in the future if it launches as a service. Most would also be willing to pay for it, with an average amount up to €6.16 per month. Participants also shared Intent Classification import { BayesClassifier } from "natural"; const classifier = new BayesClassifier(); classifier.addDocument( [ "set up an appointment", "schedule a call", "meet me for dinner", ], "setupNewAppointment" ); classifier.addDocument( [ "i can’t make it", "reschedule this call", "find another time", ], "rescheduleAppointment" ); classifier.train();

Slide 49

Slide 49 text

and industry best-practices with the support of Speakup. Users can simply add their assistant’s address as ‘CC’ in an email, and EIVA will share the recommended location and time slots with guests, based on the user’s availability (using their calendar) and scheduling preferences. A companion web application is also developed to manage meetings and settings. The code is open source and written in TypeScript with Node.js and Vue.js and deployed on Amazon Web Services architecture in Europe. The product is built with focus on data privacy and user personalization. A user experience evaluation of both the EIVA and its app with 30 participants was conducted that found positive reception, with the average rating of the overall assistant and app experience of 4.4 and 4.5 out of 5 respectively. Users’ behavior was also understood with heatmaps and visualizations using pageview and mouse clicks tracking. All but one participants said that the EIVA met their expectations, and 25 out of 30 would use it in the future if it launches as a service. Most would also be willing to pay for it, with an average amount up to €6.16 per month. Participants also shared Intent Classification classifier.getClassifications( "i don’t think I’ll be able to make it to this time" ); // Classifications: // // setupNewAppointment: 0.1666 // rescheduleAppointment: 0.3333 // This never-before-seen sentence is correctly classified as ‘Reschedule Appointment’ This is an example with a tiny training dataset

Slide 50

Slide 50 text

and industry best-practices with the support of Speakup. Users can simply add their assistant’s address as ‘CC’ in an email, and EIVA will share the recommended location and time slots with guests, based on the user’s availability (using their calendar) and scheduling preferences. A companion web application is also developed to manage meetings and settings. The code is open source and written in TypeScript with Node.js and Vue.js and deployed on Amazon Web Services architecture in Europe. The product is built with focus on data privacy and user personalization. A user experience evaluation of both the EIVA and its app with 30 participants was conducted that found positive reception, with the average rating of the overall assistant and app experience of 4.4 and 4.5 out of 5 respectively. Users’ behavior was also understood with heatmaps and visualizations using pageview and mouse clicks tracking. All but one participants said that the EIVA met their expectations, and 25 out of 30 would use it in the future if it launches as a service. Most would also be willing to pay for it, with an average amount up to €6.16 per month. Participants also shared

Slide 51

Slide 51 text

and industry best-practices with the support of Speakup. Users can simply add their assistant’s address as ‘CC’ in an email, and EIVA will share the recommended location and time slots with guests, based on the user’s availability (using their calendar) and scheduling preferences. A companion web application is also developed to manage meetings and settings. The code is open source and written in TypeScript with Node.js and Vue.js and deployed on Amazon Web Services architecture in Europe. The product is built with focus on data privacy and user personalization. A user experience evaluation of both the EIVA and its app with 30 participants was conducted that found positive reception, with the average rating of the overall assistant and app experience of 4.4 and 4.5 out of 5 respectively. Users’ behavior was also understood with heatmaps and visualizations using pageview and mouse clicks tracking. All but one participants said that the EIVA met their expectations, and 25 out of 30 would use it in the future if it launches as a service. Most would also be willing to pay for it, with an average amount up to €6.16 per month. Participants also shared Configuration Management Transactional Emails Authentication Rate Limits MariaDB Redis ElasticSearch Simple Storage Service Public RESTful API Scheduled Jobs Third-party APIs Vue.js Nuxt.js Authorization in Fetching Unit Tests Continuous Integration Initialization Tests Uptime & Error Monitoring Sentry Resource Monitoring Caprover GitHub Actions Netlify Deployments

Slide 52

Slide 52 text

and industry best-practices with the support of Speakup. Users can simply add their assistant’s address as ‘CC’ in an email, and EIVA will share the recommended location and time slots with guests, based on the user’s availability (using their calendar) and scheduling preferences. A companion web application is also developed to manage meetings and settings. The code is open source and written in TypeScript with Node.js and Vue.js and deployed on Amazon Web Services architecture in Europe. The product is built with focus on data privacy and user personalization. A user experience evaluation of both the EIVA and its app with 30 participants was conducted that found positive reception, with the average rating of the overall assistant and app experience of 4.4 and 4.5 out of 5 respectively. Users’ behavior was also understood with heatmaps and visualizations using pageview and mouse clicks tracking. All but one participants said that the EIVA met their expectations, and 25 out of 30 would use it in the future if it launches as a service. Most would also be willing to pay for it, with an average amount up to €6.16 per month. Participants also shared

Slide 53

Slide 53 text

scheduling preferences. A companion web application is also developed to manage meetings and settings. The code is open source and written in TypeScript with Node.js and Vue.js and deployed on Amazon Web Services architecture in Europe. The product is built with focus on data privacy and user personalization. A user experience evaluation of both the EIVA and its app with 30 participants was conducted that found positive reception, with the average rating of the overall assistant and app experience of 4.4 and 4.5 out of 5 respectively. Users’ behavior was also understood with heatmaps and visualizations using pageview and mouse clicks tracking. All but one participants said that the EIVA met their expectations, and 25 out of 30 would use it in the future if it launches as a service. Most would also be willing to pay for it, with an average amount up to €6.16 per month. Participants also shared their frustrations and recommendations for future work. In the future, NLP classification should be improved and user recommendations should be implemented before launching the EIVA service for consumers.

Slide 54

Slide 54 text

preferences. A companion web application is also developed to manage meetings and settings. The code is open source and written in TypeScript with Node.js and Vue.js and deployed on Amazon Web Services architecture in Europe. The product is built with focus on data privacy and user personalization. A user experience evaluation of both the EIVA and its app with 30 participants was conducted that found positive reception, with the average rating of the overall assistant and app experience of 4.4 and 4.5 out of 5 respectively. Users’ behavior was also understood with heatmaps and visualizations using pageview and mouse clicks tracking. All but one participants said that the EIVA met their expectations, and 25 out of 30 would use it in the future if it launches as a service. Most would also be willing to pay for it, with an average amount up to €6.16 per month. Participants also shared their frustrations and recommendations for future work. In the future, NLP classification should be improved and user recommendations should be implemented before launching the EIVA service for consumers.

Slide 55

Slide 55 text

preferences. A companion web application is also developed to manage meetings and settings. The code is open source and written in TypeScript with Node.js and Vue.js and deployed on Amazon Web Services architecture in Europe. The product is built with focus on data privacy and user personalization. A user experience evaluation of both the EIVA and its app with 30 participants was conducted that found positive reception, with the average rating of the overall assistant and app experience of 4.4 and 4.5 out of 5 respectively. Users’ behavior was also understood with heatmaps and visualizations using pageview and mouse clicks tracking. All but one participants said that the EIVA met their expectations, and 25 out of 30 would use it in the future if it launches as a service. Most would also be willing to pay for it, with an average amount up to €6.16 per month. Participants also shared their frustrations and recommendations for future work. In the future, NLP classification should be improved and user recommendations should be implemented before launching the EIVA service for consumers. PROFESSIONALS OF PARTICIPANTS 18 employees at companies or organizations 9 students at schools or universities 3 self-employed professionals or freelancers

Slide 56

Slide 56 text

preferences. A companion web application is also developed to manage meetings and settings. The code is open source and written in TypeScript with Node.js and Vue.js and deployed on Amazon Web Services architecture in Europe. The product is built with focus on data privacy and user personalization. A user experience evaluation of both the EIVA and its app with 30 participants was conducted that found positive reception, with the average rating of the overall assistant and app experience of 4.4 and 4.5 out of 5 respectively. Users’ behavior was also understood with heatmaps and visualizations using pageview and mouse clicks tracking. All but one participants said that the EIVA met their expectations, and 25 out of 30 would use it in the future if it launches as a service. Most would also be willing to pay for it, with an average amount up to €6.16 per month. Participants also shared their frustrations and recommendations for future work. In the future, NLP classification should be improved and user recommendations should be implemented before launching the EIVA service for consumers. 19,177 API requests 98 Emails processed 2,244 Pageviews

Slide 57

Slide 57 text

Germany Finland France Russia 12 Countries India Nederland Poland Kenya United States United Kingdom Iran Indonesia

Slide 58

Slide 58 text

7 Provinces Flevoland Overijssel Gelderland Utrecht S. Holland N. Holland Friesland

Slide 59

Slide 59 text

preferences. A companion web application is also developed to manage meetings and settings. The code is open source and written in TypeScript with Node.js and Vue.js and deployed on Amazon Web Services architecture in Europe. The product is built with focus on data privacy and user personalization. A user experience evaluation of both the EIVA and its app with 30 participants was conducted that found positive reception, with the average rating of the overall assistant and app experience of 4.4 and 4.5 out of 5 respectively. Users’ behavior was also understood with heatmaps and visualizations using pageview and mouse clicks tracking. All but one participants said that the EIVA met their expectations, and 25 out of 30 would use it in the future if it launches as a service. Most would also be willing to pay for it, with an average amount up to €6.16 per month. Participants also shared their frustrations and recommendations for future work. In the future, NLP classification should be improved and user recommendations should be implemented before launching the EIVA service for consumers. Firefox Chrome Safari Safari Mobile Edge Chrome-related macOS Linux Windows Android iOS Ubuntu 992 529 377 217 83 44 772 729 637 59 3 34

Slide 60

Slide 60 text

preferences. A companion web application is also developed to manage meetings and settings. The code is open source and written in TypeScript with Node.js and Vue.js and deployed on Amazon Web Services architecture in Europe. The product is built with focus on data privacy and user personalization. A user experience evaluation of both the EIVA and its app with 30 participants was conducted that found positive reception, with the average rating of the overall assistant and app experience of 4.4 and 4.5 out of 5 respectively. Users’ behavior was also understood with heatmaps and visualizations using pageview and mouse clicks tracking. All but one participants said that the EIVA met their expectations, and 25 out of 30 would use it in the future if it launches as a service. Most would also be willing to pay for it, with an average amount up to €6.16 per month. Participants also shared their frustrations and recommendations for future work. In the future, NLP classification should be improved and user recommendations should be implemented before launching the EIVA service for consumers. WEB APP EXPERIENCE 4.4 5.0 5.0 MEDIAN MODE MEAN WEB APP DESIGN 4.6 5.0 5.0 MEDIAN MODE MEAN

Slide 61

Slide 61 text

preferences. A companion web application is also developed to manage meetings and settings. The code is open source and written in TypeScript with Node.js and Vue.js and deployed on Amazon Web Services architecture in Europe. The product is built with focus on data privacy and user personalization. A user experience evaluation of both the EIVA and its app with 30 participants was conducted that found positive reception, with the average rating of the overall assistant and app experience of 4.4 and 4.5 out of 5 respectively. Users’ behavior was also understood with heatmaps and visualizations using pageview and mouse clicks tracking. All but one participants said that the EIVA met their expectations, and 25 out of 30 would use it in the future if it launches as a service. Most would also be willing to pay for it, with an average amount up to €6.16 per month. Participants also shared their frustrations and recommendations for future work. In the future, NLP classification should be improved and user recommendations should be implemented before launching the EIVA service for consumers. WEB APP EXPERIENCE 4.4 5.0 5.0 MEDIAN MODE MEAN 4.6 5.0 5.0 MEDIAN MODE MEAN PRIVACY FEATURES 4.7 5.0 5.0 MEDIAN MODE MEAN WEB APP DESIGN

Slide 62

Slide 62 text

preferences. A companion web application is also developed to manage meetings and settings. The code is open source and written in TypeScript with Node.js and Vue.js and deployed on Amazon Web Services architecture in Europe. The product is built with focus on data privacy and user personalization. A user experience evaluation of both the EIVA and its app with 30 participants was conducted that found positive reception, with the average rating of the overall assistant and app experience of 4.4 and 4.5 out of 5 respectively. Users’ behavior was also understood with heatmaps and visualizations using pageview and mouse clicks tracking. All but one participants said that the EIVA met their expectations, and 25 out of 30 would use it in the future if it launches as a service. Most would also be willing to pay for it, with an average amount up to €6.16 per month. Participants also shared their frustrations and recommendations for future work. In the future, NLP classification should be improved and user recommendations should be implemented before launching the EIVA service for consumers. ASSISTANT EXPERIENCE 4.5 5.0 5.0 MEDIAN MODE MEAN UNDERSTANDING 4.4 5.0 5.0 MEDIAN MODE MEAN

Slide 63

Slide 63 text

preferences. A companion web application is also developed to manage meetings and settings. The code is open source and written in TypeScript with Node.js and Vue.js and deployed on Amazon Web Services architecture in Europe. The product is built with focus on data privacy and user personalization. A user experience evaluation of both the EIVA and its app with 30 participants was conducted that found positive reception, with the average rating of the overall assistant and app experience of 4.4 and 4.5 out of 5 respectively. Users’ behavior was also understood with heatmaps and visualizations using pageview and mouse clicks tracking. All but one participants said that the EIVA met their expectations, and 25 out of 30 would use it in the future if it launches as a service. Most would also be willing to pay for it, with an average amount up to €6.16 per month. Participants also shared their frustrations and recommendations for future work. In the future, NLP classification should be improved and user recommendations should be implemented before launching the EIVA service for consumers. TIME RECOMMENDATIONS 3.9 4.0 4.0 MEDIAN MODE MEAN TRUST 3.6 4.0 4.0 MEDIAN MODE MEAN

Slide 64

Slide 64 text

preferences. A companion web application is also developed to manage meetings and settings. The code is open source and written in TypeScript with Node.js and Vue.js and deployed on Amazon Web Services architecture in Europe. The product is built with focus on data privacy and user personalization. A user experience evaluation of both the EIVA and its app with 30 participants was conducted that found positive reception, with the average rating of the overall assistant and app experience of 4.4 and 4.5 out of 5 respectively. Users’ behavior was also understood with heatmaps and visualizations using pageview and mouse clicks tracking. All but one participants said that the EIVA met their expectations, and 25 out of 30 would use it in the future if it launches as a service. Most would also be willing to pay for it, with an average amount up to €6.16 per month. Participants also shared their frustrations and recommendations for future work. In the future, NLP classification should be improved and user recommendations should be implemented before launching the EIVA service for consumers.

Slide 65

Slide 65 text

preferences. A companion web application is also developed to manage meetings and settings. The code is open source and written in TypeScript with Node.js and Vue.js and deployed on Amazon Web Services architecture in Europe. The product is built with focus on data privacy and user personalization. A user experience evaluation of both the EIVA and its app with 30 participants was conducted that found positive reception, with the average rating of the overall assistant and app experience of 4.4 and 4.5 out of 5 respectively. Users’ behavior was also understood with heatmaps and visualizations using pageview and mouse clicks tracking. All but one participants said that the EIVA met their expectations, and 25 out of 30 would use it in the future if it launches as a service. Most would also be willing to pay for it, with an average amount up to €6.16 per month. Participants also shared their frustrations and recommendations for future work. In the future, NLP classification should be improved and user recommendations should be implemented before launching the EIVA service for consumers.

Slide 66

Slide 66 text

preferences. A companion web application is also developed to manage meetings and settings. The code is open source and written in TypeScript with Node.js and Vue.js and deployed on Amazon Web Services architecture in Europe. The product is built with focus on data privacy and user personalization. A user experience evaluation of both the EIVA and its app with 30 participants was conducted that found positive reception, with the average rating of the overall assistant and app experience of 4.4 and 4.5 out of 5 respectively. Users’ behavior was also understood with heatmaps and visualizations using pageview and mouse clicks tracking. All but one participants said that the EIVA met their expectations, and 25 out of 30 would use it in the future if it launches as a service. Most would also be willing to pay for it, with an average amount up to €6.16 per month. Participants also shared their frustrations and recommendations for future work. In the future, NLP classification should be improved and user recommendations should be implemented before launching the EIVA service for consumers.

Slide 67

Slide 67 text

the average rating of the overall assistant and app experience of 4.4 and 4.5 out of 5 respectively. Users’ behavior was also understood with heatmaps and visualizations using pageview and mouse clicks tracking. All but one participants said that the EIVA met their expectations, and 25 out of 30 would use it in the future if it launches as a service. Most would also be willing to pay for it, with an average amount up to €6.16 per month. Participants also shared their frustrations and recommendations for future work. In the future, NLP classification should be improved and user recommendations should be implemented before launching the EIVA service for consumers.

Slide 68

Slide 68 text

the average rating of the overall assistant and app experience of 4.4 and 4.5 out of 5 respectively. Users’ behavior was also understood with heatmaps and visualizations using pageview and mouse clicks tracking. All but one participants said that the EIVA met their expectations, and 25 out of 30 would use it in the future if it launches as a service. Most would also be willing to pay for it, with an average amount up to €6.16 per month. Participants also shared their frustrations and recommendations for future work. In the future, NLP classification should be improved and user recommendations should be implemented before launching the EIVA service for consumers. 29 out of 30 EIVA MET EXPECTATIONS

Slide 69

Slide 69 text

the average rating of the overall assistant and app experience of 4.4 and 4.5 out of 5 respectively. Users’ behavior was also understood with heatmaps and visualizations using pageview and mouse clicks tracking. All but one participants said that the EIVA met their expectations, and 25 out of 30 would use it in the future if it launches as a service. Most would also be willing to pay for it, with an average amount up to €6.16 per month. Participants also shared their frustrations and recommendations for future work. In the future, NLP classification should be improved and user recommendations should be implemented before launching the EIVA service for consumers. 29 out of 30 EIVA MET EXPECTATIONS 25 out of 30 WOULD USE EIVA SERVICE

Slide 70

Slide 70 text

the average rating of the overall assistant and app experience of 4.4 and 4.5 out of 5 respectively. Users’ behavior was also understood with heatmaps and visualizations using pageview and mouse clicks tracking. All but one participants said that the EIVA met their expectations, and 25 out of 30 would use it in the future if it launches as a service. Most would also be willing to pay for it, with an average amount up to €6.16 per month. Participants also shared their frustrations and recommendations for future work. In the future, NLP classification should be improved and user recommendations should be implemented before launching the EIVA service for consumers. 29 out of 30 EIVA MET EXPECTATIONS 25 out of 30 WOULD USE EIVA SERVICE 24 out of 30 WOULD PAY AT LEAST UP TO €5

Slide 71

Slide 71 text

the average rating of the overall assistant and app experience of 4.4 and 4.5 out of 5 respectively. Users’ behavior was also understood with heatmaps and visualizations using pageview and mouse clicks tracking. All but one participants said that the EIVA met their expectations, and 25 out of 30 would use it in the future if it launches as a service. Most would also be willing to pay for it, with an average amount up to €6.16 per month. Participants also shared their frustrations and recommendations for future work. In the future, NLP classification should be improved and user recommendations should be implemented before launching the EIVA service for consumers.

Slide 72

Slide 72 text

tracking. All but one participants said that the EIVA met their expectations, and 25 out of 30 would use it in the future if it launches as a service. Most would also be willing to pay for it, with an average amount up to €6.16 per month. Participants also shared their frustrations and recommendations for future work. In the future, NLP classification should be improved and user recommendations should be implemented before launching the EIVA service for consumers.

Slide 73

Slide 73 text

tracking. All but one participants said that the EIVA met their expectations, and 25 out of 30 would use it in the future if it launches as a service. Most would also be willing to pay for it, with an average amount up to €6.16 per month. Participants also shared their frustrations and recommendations for future work. In the future, NLP classification should be improved and user recommendations should be implemented before launching the EIVA service for consumers.

Slide 74

Slide 74 text

tracking. All but one participants said that the EIVA met their expectations, and 25 out of 30 would use it in the future if it launches as a service. Most would also be willing to pay for it, with an average amount up to €6.16 per month. Participants also shared their frustrations and recommendations for future work. In the future, NLP classification should be improved and user recommendations should be implemented before launching the EIVA service for consumers. WHAT DO YOU LIKE THE MOST? 5 × Ease of use 3 × Fast response time 1 × Overall concept 1 × Security features 1 × Conversational interface 1 × Web app user interface

Slide 75

Slide 75 text

tracking. All but one participants said that the EIVA met their expectations, and 25 out of 30 would use it in the future if it launches as a service. Most would also be willing to pay for it, with an average amount up to €6.16 per month. Participants also shared their frustrations and recommendations for future work. In the future, NLP classification should be improved and user recommendations should be implemented before launching the EIVA service for consumers. WHAT DO YOU LIKE THE MOST? 5 × Ease of use 3 × Fast response time 1 × Overall concept 1 × Security features 1 × Conversational interface 1 × Web app user interface WHAT DO YOU LIKE THE LEAST? 1 × Pretending to be human 1 × Lengthy app onboarding 1 × Mobile user interface

Slide 76

Slide 76 text

tracking. All but one participants said that the EIVA met their expectations, and 25 out of 30 would use it in the future if it launches as a service. Most would also be willing to pay for it, with an average amount up to €6.16 per month. Participants also shared their frustrations and recommendations for future work. In the future, NLP classification should be improved and user recommendations should be implemented before launching the EIVA service for consumers. WHAT DO YOU LIKE THE MOST? 5 × Ease of use 3 × Fast response time 1 × Overall concept 1 × Security features 1 × Conversational interface 1 × Web app user interface WHAT DO YOU LIKE THE LEAST? 1 × Pretending to be human 1 × Lengthy app onboarding 1 × Mobile user interface FEATURE RECOMMENDATIONS Meeting without emails SMS and WhatsApp support Multiple guests in a meeting Manual time slot selection Cancel or reschedule UI

Slide 77

Slide 77 text

tracking. All but one participants said that the EIVA met their expectations, and 25 out of 30 would use it in the future if it launches as a service. Most would also be willing to pay for it, with an average amount up to €6.16 per month. Participants also shared their frustrations and recommendations for future work. In the future, NLP classification should be improved and user recommendations should be implemented before launching the EIVA service for consumers.

Slide 78

Slide 78 text

tracking. All but one participants said that the EIVA met their expectations, and 25 out of 30 would use it in the future if it launches as a service. Most would also be willing to pay for it, with an average amount up to €6.16 per month. Participants also shared their frustrations and recommendations for future work. In the future, NLP classification should be improved and user recommendations should be implemented before launching the EIVA service for consumers.

Slide 79

Slide 79 text

and 4.5 out of 5 respectively. Users’ behavior was also understood with heatmaps and visualizations using pageview and mouse clicks tracking. All but one participants said that the EIVA met their expectations, and 25 out of 30 would use it in the future if it launches as a service. Most would also be willing to pay for it, with an average amount up to €6.16 per month. Participants also shared their frustrations and recommendations for future work. In the future, NLP classification should be improved and user recommendations should be implemented before launching the EIVA service for consumers.

Slide 80

Slide 80 text

A user experience evaluation of both the EIVA and its app with 30 participants was conducted that found positive reception, with the average rating of the overall assistant and app experience of 4.4 and 4.5 out of 5 respectively. Users’ behavior was also understood with heatmaps and visualizations using pageview and mouse clicks tracking. All but one participants said that the EIVA met their expectations, and 25 out of 30 would use it in the future if it launches as a service. Most would also be willing to pay for it, with an average amount up to €6.16 per month. Participants also shared their frustrations and recommendations for future work. In the future, NLP classification should be improved and user recommendations should be implemented before launching the EIVA service for consumers.

Slide 81

Slide 81 text

Abstract Manually setting up appointments by email wastes tens of hours every month for professionals, because several email exchanges are required before receiving confirmation. Since not everyone can afford to hire full-time assistants, Email-based Intelligent Virtual Assistants (EIVA) can help by automating this task. In this paper, a functional EIVA is developed based on research and industry best-practices with the support of Speakup. Users can simply add their assistant’s address as ‘CC’ in an email, and EIVA will share the recommended location and time slots with guests, based on the user’s availability (using their calendar) and scheduling preferences. A companion web application is also developed to manage meetings and settings. The code is open source and written in TypeScript with Node.js and Vue.js and deployed on Amazon Web Services architecture in Europe. The product is built with focus on data privacy and user personalization. A user experience evaluation of both the EIVA and its app with 30 participants was conducted that found positive reception, with the average rating of the overall assistant and app experience of 4.4 and 4.5 out of 5 respectively. Users’ behavior was also understood with heatmaps and visualizations using pageview and mouse clicks tracking. All but one participants said that the EIVA met their expectations, and 25 out of 30 would use it in the future if it launches as a service. Most would also be willing to pay for it, with an average amount up to €6.16 per month. Participants also shared their frustrations and recommendations for future work. In the future, NLP classification should be improved and user recommendations should be implemented before launching the EIVA service for consumers.

Slide 82

Slide 82 text

Email-based Intelligent Virtual Assistant for Scheduling Presented by Anand Chowdhary Supervised by Dr. Job Zwiers Creative Technology BSc University of Twente Enschede, the Netherlands

Slide 83

Slide 83 text

Email-based Intelligent Virtual Assistant for Scheduling Presented by Anand Chowdhary Supervised by Dr. Job Zwiers Creative Technology BSc University of Twente Enschede, the Netherlands NOMINEE CREATIVE TECHNOLOGY BACHELOR AWARD UNIVERSITY OF TWENTE.

Slide 84

Slide 84 text

How does the Naive Bayes Classifier actually work? What’s the author’s previous work, Ara? How did you collect data? How did you design the questions? How did you analyze the collected data? How did you capture stakeholders’ requirements? What questions did you explore using personas? How do you deal with gender bias in assistants? Do email recipients know EIVA is not human? How do you parse dates in emails? What authentications standards does the app use? Do you implement rate limits for security? How do you use scheduled jobs? How do you send client-side fetch requests? How do you manage state in the frontend app? Does EIVA work in both English and Dutch? How do you test the source code? How does the CI/CD pipeline work? How does you test external services? How much was the infrastructure cost? Do you monitor the service’s uptime? Do you monitor server resource usage? How do you know if an error occurs? Do people actually check their email or send emails? What calendaring services do people use? How many API requests or emails were logged? What were people’s first-impressions? How did people like the web app? How did people like the assistant over email? How much would people be willing to pay for this? What were common user frustrations? What were common feature recommendations? How would you improve this in the future? What about AI-driven job loss? What’s the business case for this service? How are the database tables structured? Where can I find the code for this?

Slide 85

Slide 85 text

How does the Naive Bayes Classifier actually work? ← Back

Slide 86

Slide 86 text

How does the Naive Bayes Classifier actually work? ← Back

Slide 87

Slide 87 text

How does the Naive Bayes Classifier actually work? ← Back

Slide 88

Slide 88 text

What’s the author’s previous work, Ara? ← Back

Slide 89

Slide 89 text

How did you collect data? ← Back

Slide 90

Slide 90 text

How did you design the questions? ← Back

Slide 91

Slide 91 text

How did you analyze the collected data? ← Back

Slide 92

Slide 92 text

How did you capture stakeholders’ requirements? ← Back

Slide 93

Slide 93 text

What questions did you explore using personas? ← Back

Slide 94

Slide 94 text

How do you deal with gender bias in assistants? ← Back

Slide 95

Slide 95 text

Do email recipients know EIVA is not human? ← Back

Slide 96

Slide 96 text

How do you parse dates in emails? ← Back

Slide 97

Slide 97 text

What authentications standards does the app use? ← Back

Slide 98

Slide 98 text

Do you implement rate limits for security? ← Back

Slide 99

Slide 99 text

How do you use scheduled jobs? ← Back

Slide 100

Slide 100 text

How do you send client-side fetch requests? ← Back

Slide 101

Slide 101 text

How do you manage state in the frontend app? ← Back

Slide 102

Slide 102 text

Does EIVA work in both English and Dutch? ← Back

Slide 103

Slide 103 text

How do you test the source code? ← Back

Slide 104

Slide 104 text

How does the CI/CD pipeline work? ← Back

Slide 105

Slide 105 text

How does you test external services? ← Back

Slide 106

Slide 106 text

How much was the infrastructure cost? ← Back

Slide 107

Slide 107 text

Do you monitor the service’s uptime? ← Back

Slide 108

Slide 108 text

Do you monitor server resource usage? ← Back

Slide 109

Slide 109 text

How do you know if an error occurs? ← Back

Slide 110

Slide 110 text

Do people actually check their email or send emails? ← Back

Slide 111

Slide 111 text

What calendaring services do people use? ← Back

Slide 112

Slide 112 text

How many API requests or emails were logged? ← Back

Slide 113

Slide 113 text

What were people’s first-impressions? ← Back

Slide 114

Slide 114 text

How did people like the web app? ← Back

Slide 115

Slide 115 text

How did people like the assistant over email? ← Back

Slide 116

Slide 116 text

How much would people be willing to pay for this? ← Back

Slide 117

Slide 117 text

What were common user frustrations? ← Back

Slide 118

Slide 118 text

What were common feature recommendations? ← Back

Slide 119

Slide 119 text

How would you improve this in the future? ← Back

Slide 120

Slide 120 text

What about AI-driven job loss? ← Back

Slide 121

Slide 121 text

What’s the business case for this service? ← Back

Slide 122

Slide 122 text

How are the database tables structured? ← Back

Slide 123

Slide 123 text

Where can I find the code for this? ← Back

Slide 124

Slide 124 text

Email-based Intelligent Virtual Assistant for Scheduling Presented by Anand Chowdhary Supervised by Dr. Job Zwiers Creative Technology BSc University of Twente Enschede, the Netherlands