The IRMA Community
Newsletters
Research IRM
Click a keyword to search titles using our InfoSci-OnDemand powered search:
|
Automated Evaluation of Students’ Performance by Analyzing Online Messages
Abstract
Students participate in a virtual classroom and interact with the instructor and other students largely by composing text messages and replying to others. We propose measurements derived from natural language processing techniques to evaluate these text messages. Students’ performance is evaluated from three perspectives: knowledge they learn from, effort they devote to, and their participation activeness in the class; three measures - keyword density, message length, and message count, are derived for each evaluation aspect respectively. An overall performance indicator is computed from the three measures. The experiment shows that there is a high correlation between the performance indicator scores and the actual grades. The rank order of students by the performance indicator score and that by the actual grades are highly correlated as well.
|
|