Upgrade to Pro — share decks privately, control downloads, hide ads and more …

Word Cloud for Meeting: A Visualization System for DHH People in Online Meetings - ASSETS 2021 Poster

Word Cloud for Meeting: A Visualization System for DHH People in Online Meetings - ASSETS 2021 Poster

This presentation was created for the poster session at the ASSETS 2021.

Ryo Iijima, Akihisa Shitara, Sayan Sarcar, and Yoichi Ochiai. 2021. Word Cloud for Meeting: A Visualization System for DHH People in Online Meetings. In The 23rd International ACM SIGACCESS Conference on Computers and Accessibility (ASSETS ’21), October 18–22, 2021, Virtual Event, USA. ACM, New York, NY, USA, 4 pages. https://doi.org/10.1145/3441852.3476547

【Project page】

【Project movie】

Ryo Iijima (飯嶋 稜)
College of Media Arts, Science and Technology
School of Informatics
University of Tsukuba, Japan
Digital Nature Group (Yoichi Ochiai)

Deaf and hard of hearing (DHH) people have limited access to auditory input, so they mainly receive visual information during online meetings. In recent years, the usability of a system that visualizes the ongoing topic in a conference has been confirmed, but it has not been verified in a remote conference that includes DHH people. One possible reason is that visual dispersion occurs when there are multiple sources of visual information. In this study, we introduce “Word Cloud for Meeting,” a system that generates a separate word cloud for each participant and displays it in the background of each participant’s video to visualize who is saying what. We conducted an experiment with seven DHH participants and obtained positive qualitative feedback on the ease of recognizing topic changes. However, when the topic changed in a sequence, it was found to be distracting. Additionally, we discuss the design implications for visualizing topics for DHH people in online meetings.

Digital Nature Group

October 19, 2021

More Decks by Digital Nature Group

Other Decks in Technology


  1. Introduction visualization of topic transitions Senthil Chandrasegaran, Chris Bryan, Hidekazu

    Shidara, Tung-Yen Chuang, and Kwan-Liu Ma. 2019. TalkTraces: Real-Time Capture and Visualization of Verbal Content in Meetings. In Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems (CHI '19). Additional visual sources of information can be beneficial. 3
  2. Introduction maintaining a small visual dispersion Adding one more display

    for word cloud would cause the visual dispersion. Displaying word cloud in the background of each participant's video. Word Cloud for Meeting 4
  3. Pilot Study three requirements Users can understand the ongoing topics

    at a glance. Users can understand who is saying what. Users can be aware of changes in information. 1. 2. 3. 5
  4. Pilot Study modifications made to the system To illustrate a

    change in topic, new words are presented in a darker color, and the words fade over time. Old words are removed to avoid displaying too many words. 1. 2. 7
  5. Experiment customizability (theme 1/3) P3 suggested the ability to mute

    words that were not important to him. P1, 6 wanted to see only nouns and verbs. P3 wanted only nouns. P1, 3, 6 wanted to change the color of the words. P2, 6 wanted the switch the system on and o f according to their needs. 12
  6. Experiment situation where the system is useful (theme 2/3) P1,

    3, 7 would like to use the system in casual conversations. P2, 6 said the system helps them to passively listen to conversations. P1, 3, 5 worry that the system may make errors in conversations with many technical terms. 13
  7. Experiment optimal placement (theme 3/3) Four participants were concerned about

    the word hidden behind a person, making it partially invisible. P5, 7 suggested that the person be placed on the left side of the video and the word cloud on the right. P3, 5 suggested that the words be placed around the person. Four participants asked that the freshness of the word be expressed by its layout, not by its color. 14
  8. Discussion frequent topic shifts make the system distracting halloween...? Our

    system is useful for observing shifts in topics. Frequent switching of topics may cause confusion. 1. 2. 15