Year: 2018
Type: conference-paper
Abstract: We implemented a social networking platform called Course Networking (CN) in IUPUI's introductory calculus based mechanics course and recorded three semesters of online discussions.We used the Syuzhet package in R to evaluate sentiment in the recorded discussions, and to quantify the incidence of eight basic emotions: anger, anticipation, disgust, fear, joy, sadness, surprise, and trust.We applied this text mining method to over nine thousand posts and replies to identify and analyze student sentiment during three semesters.We also investigated the variation of these emotions throughout the semester, the role played by the most vocal students as compared to the least frequent posters, and gender differences.With an abundance of students' online discussions, text mining offers an expedient and automated means of analysis, providing a new window into students thinking and emotional state during semester-long physics courses.
Authors: Patrick Kelley, Andrew Gavrin, Rebecca S. Lindell
Institution: Indiana University – Purdue University Indianapolis
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
SDG: Quality education
Open Access status: hybrid
OpenAlex ID: W2790990282