Towards Humanizing Online Discourse - Exploring Linguistic and Emotional Tones in Online Learning
Year: 2019
Type: dissertation
Abstract: Online learning has seen tremendous growth over the last few years, but there is limited research in understanding the role of tones in an online learning environment. The goal of this thesis is to explore the presence of both emotional and linguistic tones in threaded discourse to understand their role in online conversations. This study presents evidence of the presence of emotions in online discussions using a sequential mixed-methods design by analyzing text using machine learning techniques based on the theory of psycholinguistics to predict both linguistic and emotional tones in discourse. It further explores participants’ experiences and insights using semi-structured interviews with learners and instructors. The analysis uncovered significant differences in tone across different courses, users and notes. This research is a first step to acknowledge, identify and understand tones in text written by the user; thereby humanizing text discourse online.
Source: TSpace (University of Toronto)
Author: Raman, Preeti
Institution: University of Toronto
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
SDG: Quality education
Open Access status: green
OpenAlex ID: W7025042353