emotionVis: Designing an Emotion Text Inference Tool for Visual Analytics

Publication: Research - peer-reviewArticle in proceedings


With increasingly high volumes of conversations across social media, the rapid detection of emotions is of significant strategic value to industry prac‐ titioners. Summarizing large volumes of text with computational linguistics and visual analytics allows for several new possibilities from general trend detection to specific applications in marketing practice, such as monitoring product launches, campaigns and public relations milestones. After collecting 1.6 million user-tagged feelings from 12 million online posts that mention emotions, we utilized machine learning techniques towards building an automatic ‘feelings meter’; a tool for both researchers and practitioners to automatically detect emotional dimensions from text. Following several iterations, the test version has now taken shape as emotionVis, a dashboard prototype for inferring emotions from text while presenting the results for visual analysis.

Publication information

Original languageEnglish
Title of host publicationTackling Society’s Grand Challenges with Design Science : Proceedings of the 11th International Conference, DESRIST 2016
EditorsJeffrey Parsons, Tuure Tuunanen, John Venable, Brian Donnellan, Markus Helfert, Jim Kenneally
Place of PublicationChams
PublisherSpringer Science+Business Media B.V.
Publication date2016
ISBN (print)9783319392936
ISBN (electronic)9783319392943
StatePublished - 2016
Event - St. John’s, NL, Canada


ConferenceThe 11th International Conference on Design Science Research in Information Systems and Technology. DESRIST 2016
BySt. John’s, NL
SeriesLecture Notes in Computer Science

ID: 44743678