Analyzing Brand Reputation with Oracle Analytics

[email protected] www.rittmanmead.com @rittmanmead Analyzing Brand Reputation   with Oracle Analytics

[email protected] www.rittmanmead.com @rittmanmead 2 •Principal Consultant at Rittman Mead •12
years experience in BI/Analytics •Based in Trebaseleghe Venice, Italy • https://fventurin.digitalpress.blog • https://speakerdeck.com/barretbse • [email protected] • @barretbse Federico Venturin

[email protected] www.rittmanmead.com @rittmanmead 3 A Long Time Ago

[email protected] www.rittmanmead.com @rittmanmead 4 A Long Time Ago

[email protected] www.rittmanmead.com @rittmanmead 5 Nothing Lasts Forever

[email protected] www.rittmanmead.com @rittmanmead 6 Nothing Lasts Forever

[email protected] www.rittmanmead.com @rittmanmead 7 Why Am I Here Today? I
was raised by my parents to believe that you had a moral obligation to try and help save the world. Anne Lamott

[email protected] www.rittmanmead.com @rittmanmead 8 Why Am I Here Today?

[email protected] www.rittmanmead.com @rittmanmead 9 Brand Reputation is the perception of
the brand and how the particular brand of the company is viewed by customers, stakeholders, and the market as a whole. It is the culmination of ideas and emotions that a customer associated with the brand with the customer service experienced during the purchase of goods and services, whilst using them, and after-sales services provided by the company. — Marketing91 Brand Reputation

[email protected] www.rittmanmead.com @rittmanmead 10 The Brand

[email protected] www.rittmanmead.com @rittmanmead Collecting the Data

[email protected] www.rittmanmead.com @rittmanmead 12 Where to Collect the Data?

[email protected] www.rittmanmead.com @rittmanmead 13 What to Collect from Metacritic?

[email protected] www.rittmanmead.com @rittmanmead 14 What to Collect from Metacritic? •User
reviews for each platform

[email protected] www.rittmanmead.com @rittmanmead 15 What to Collect from Twitter?

[email protected] www.rittmanmead.com @rittmanmead •Mentions of / replies to the eFootball
o ffi cial account 16 What to Collect from Twitter?

[email protected] www.rittmanmead.com @rittmanmead 17 •Oracle Analytics does not allow to
collect data from Metacritic and Twitter out-of-the-box How to Collect the Data?

[email protected] www.rittmanmead.com @rittmanmead 18 Collecting Data from Metacritic

[email protected] www.rittmanmead.com @rittmanmead 19 Sample Data from Metacritic (User Reviews)

[email protected] www.rittmanmead.com @rittmanmead 20 •Apply for a Twitter developer account
•Set up your Twitter API project and an application •Use Search Tweets v2 Collecting Data from Twitter

[email protected] www.rittmanmead.com @rittmanmead 21 •Apply for a Twitter developer account
•Set up your Twitter API project and an application •Use Search Tweets v2 Collecting Data from Twitter

[email protected] www.rittmanmead.com @rittmanmead 22 Sample Data from Twitter (Tweets)

[email protected] www.rittmanmead.com @rittmanmead 23 Sample Data from Twitter (Users)

[email protected] www.rittmanmead.com @rittmanmead 24 Hold Up for a Minute... I
don't know Python!!!

[email protected] www.rittmanmead.com @rittmanmead 25 Leveraging Custom Scripts in Oracle Analytics
It's all drag and drop!!!

[email protected] www.rittmanmead.com @rittmanmead Leveraging Custom Scripts in OAS

[email protected] www.rittmanmead.com @rittmanmead 27 •Extend ML and data curation capabilities
of Oracle Analytics •The Custom Script feature is disabled by default •Doc ID 2675894.1 explains how to enable it Custom Script Feature

[email protected] www.rittmanmead.com @rittmanmead 28 • Python/R scripts must be embedded
in XML format • Data transformation logic must be implemented in the obi_execute_script function • Check out my article for more details! Anatomy of a Custom Script

[email protected] www.rittmanmead.com @rittmanmead 29 •Click on the Create button and
select the Script option •Uploaded scripts are displayed in the Machine Learning > Scripts tab Uploading a Custom Script

[email protected] www.rittmanmead.com @rittmanmead 30 •Invoked in data fl ows using
the Add Custom Script step Invoking a Custom Script

[email protected] www.rittmanmead.com @rittmanmead Leveraging OCI Functions in OAC

[email protected] www.rittmanmead.com @rittmanmead 32 •Create an Auth Token for the
OCI user who will own the Function •Create a Container Registry to be the eventual repository for your functions •Create an Object Storage bucket to serve as the temporary processing / staging area for your Function to utilize as it handles the input data from OAC •Ensure you have the proper OCI IAM policies in place Prerequisites

[email protected] www.rittmanmead.com @rittmanmead 33 •Create an application from Developer Services
> Applications •Set up the Cloud Shell by following the steps outlined in Getting started tab under the Resources menu •Create a boilerplate function:  fn init --runtime <runtime-language> <function-name> •Add the oac-compatible free-form tag to the function, and set its value to True Creating the Function

[email protected] www.rittmanmead.com @rittmanmead 34 •Include the funcMode variable in the
function code ‣ When funcMode in the request is 'describeFunction', the function should return the function de fi nition with status, outputs, parameters, bucket name and so on as a JSON object ‣ When funcMode in the request is 'executeFunction', the actual function logic should be executed and the response should be sent back to OAC with the output Creating the Function

[email protected] www.rittmanmead.com @rittmanmead 35 •Create a OCI Resource connection to
your OCI Tenancy •Expand the Page Menu, then select Register Mode/Function > OCI Functions to register the function •Invoke registered functions in data fl ows using the Add Custom Script step Registering the Function on OAC

[email protected] www.rittmanmead.com @rittmanmead Preparing and Enriching the Data

[email protected] www.rittmanmead.com @rittmanmead 37 •Use a custom script to the
detect the language of each review and fi lter out non- English ones Filtering Out Non-English Reviews

[email protected] www.rittmanmead.com @rittmanmead 38 •Add a calculated column to determine
the sentiment (Positive, Negative or Mixed) for each review using the rating information Analyzing the Sentiment

[email protected] www.rittmanmead.com @rittmanmead 39 •Use the Analyze Sentiment step to
detect the sentiment (Positive, Negative or Neutral) for each tweet Analyzing the Sentiment

[email protected] www.rittmanmead.com @rittmanmead 40 •Use a custom script to break
text down into distinct words and count their occurences Tokenizing Reviews and Tweets

[email protected] www.rittmanmead.com @rittmanmead 41 Example: Original Tweet

[email protected] www.rittmanmead.com @rittmanmead 42 Example: Converting Text to Lowercase

[email protected] www.rittmanmead.com @rittmanmead 43 Example: Removing Punctuation

[email protected] www.rittmanmead.com @rittmanmead 44 Example: Extracting Hashtags

[email protected] www.rittmanmead.com @rittmanmead 45 Example: Extracting Account Mentions

[email protected] www.rittmanmead.com @rittmanmead 46 Example: Removing Stop Words

[email protected] www.rittmanmead.com @rittmanmead 47 Example: Output

[email protected] www.rittmanmead.com @rittmanmead 48 • As an alternative, you can
use  the Text Tokenization database  analytics function ‣ The source data must be available  in an Oracle Database ‣ Straightforward implementation ‣ Returns only top N tokens ‣ Does not handle mentions  and hashtags in tweets Tokenizing Reviews and Tweets

[email protected] www.rittmanmead.com @rittmanmead 49 The Final Datasets

[email protected] www.rittmanmead.com @rittmanmead Exploring the Data

[email protected] www.rittmanmead.com @rittmanmead 51 Global Metrics

[email protected] www.rittmanmead.com @rittmanmead 52 Global Metrics

[email protected] www.rittmanmead.com @rittmanmead 53 Mentions Over Time

[email protected] www.rittmanmead.com @rittmanmead 56 Sentiment Ratio

[email protected] www.rittmanmead.com @rittmanmead 57 Sentiment Over Time

[email protected] www.rittmanmead.com @rittmanmead 58 Sentiment Over Time

[email protected] www.rittmanmead.com @rittmanmead 59 In fl uencers

[email protected] www.rittmanmead.com @rittmanmead 60 Top 10 In fl uencers by
Tweet Count

Followers Count

Engagement

[email protected] www.rittmanmead.com @rittmanmead 63 Word Cloud

[email protected] www.rittmanmead.com @rittmanmead 64 Word Cloud

[email protected] www.rittmanmead.com @rittmanmead 65 Mentioned Users Cloud

[email protected] www.rittmanmead.com @rittmanmead 66 Hashtag Cloud

[email protected] www.rittmanmead.com @rittmanmead 67 •Interact with people and data sources
‣ Open a user pro fi le on Metacritic:  https://metacritic.com/user/${valuesForColumn:username} ‣ Open a user pro fi le on Twitter:  https://twitter.com/intent/user?user_id=${valuesForColumn:author_id} ‣ Open a tweet on Twitter:  https://twitter.com/twitter/status/${valuesForColumn:id} Leverage Data Actions

[email protected] www.rittmanmead.com @rittmanmead 68 •Automate the data gathering process •Update
the stop list with the commonly used words in the context of the brand (e.g. efootball, game, konami) •Extend the search query by including popular hashtags •Include competitors data (e.g. EA SPORTS FIFA) in the analysis •Monitor all relevant data sources What's Next?

[email protected] www.rittmanmead.com @rittmanmead Demonstration

[email protected] www.rittmanmead.com @rittmanmead 70 #EOF email   [email protected] web  
https://fventurin.digitalpress.blog twitter   @barretbse presentations   https://speakerdeck.com/barretbse

Analyzing Brand Reputation with Oracle Analytics

Analyzing Brand Reputation with Oracle Analytics

More Decks by Federico Venturin

Other Decks in Technology

Featured

Transcript