Teaching Feedback in the Digital Age: Satisfaction Analysis Based on Student Evaluation Website Data (Poster 4)

• In Event: AERA Poster Session Wednesday 10:50 a.m.
  In Poster Session: Technology-Mediated Learning and Social Interactions

Abstract

This study examines key aspects and satisfaction levels from student evaluations of teaching to enhance instructional methods and teaching quality. Analyzing 3,231 evaluations of 240 teachers from the top 30 US high schools (US NEWS 2023), key themes were identified using Latent Dirichlet Allocation (LDA). Advanced machine learning techniques, including Support Vector Machine (SVM), predicted student evaluations, addressing data imbalance with binary classification and SMOTE. The refined SVM algorithm achieved 76% accuracy. Theme modeling revealed concerns about classroom experiences, teaching styles, atmospheres, and support. The research highlights student concerns and rating preferences, offering insights for improving teacher evaluations and teaching styles.

Authors

• Guo Chen, China University of Mining and Technology

• Qian Zhou, The George Washington University