Operationalizing Emotions Based on Click Stream Data on Digital Media Platforms
Abstract
As the intelligent systems are evolving, the digital media platforms are becoming more affective. This research attempts to capture emotions of users without seeking explicit feedback from the digital media users using mouse clicks and mouse movement. Consequently, the goal of this study is to check if the emotions (happiness and sadness) of users influence the clickstream data while using digital media websites. It was found that there is a significant difference in number of mouse clicks and mouse movements when the person is sad and when the person is happy. The resulting clickstream data was related to the emotional induction. The models from the study can have a good impact on not only how the posts and feeds are presented while a person is using digital media platform, but also in providing relevant advertisements.
Degree
M.S.
Advisors
Vorvoreanu, Purdue University.
Subject Area
Behavioral psychology|Artificial intelligence|Computer science
Off-Campus Purdue Users:
To access this dissertation, please log in to our
proxy server.