PERC 2016 Abstract Detail Page
Previous Page | New Search | Browse All
| Abstract Title: | Text Mining Social Media in an Introductory Physics Course |
|---|---|
| Abstract: | A social networking website called Course Networking (CN) was used in IUPUI's introductory calculus-based mechanics course, and recorded two semesters of online discussions. We applied text mining to over six thousand posts and replies to identify and analyze student sentiment as it evolves during the semester. Using the Syuzhet package in R, sentiment can be evaluated from one of three sentiment dictionaries, which assign numerical value to words, making it possible to gain emotional valence and to group comments into eight basic emotion types: anger, anticipation, disgust, fear, joy, sadness, surprise, and trust.* Text mining offers an expedient, automated analysis of students' online discussions, providing a new window into students thinking and emotional state during a semester-long physics course. * Jockers, Matthew. "Extracts Sentiment and Sentiment-Derived Plot Arcs from Text". CRAN. April 24, 2016. |
| Abstract Type: | Contributed Poster Presentation |
Author/Organizer Information | |
| Primary Contact: |
Patrick Kelley Department of Physics, Indiana University-Purdue University Indianapolis (IUPUI), Indianapolis, Indiana, 46202 |
| Co-Author(s) and Co-Presenter(s) |
A. Gavrin Department of Physics, Indiana University-Purdue University Indianapolis (IUPUI), Indianapolis, Indiana, 46202 Rebecca Lindell Department of Physics and Astronomy, Purdue University, West Lafayette, Indiana, 47907 |
