Analysis of students’ perspectives of teaching quality through topic modeling: an empirical approach
Charalampos Dervenis et al.
What the paper says
Purpose The purpose of this study is to explore student perceptions regarding the competencies of their teachers by analyzing a data set of 2,870 open-ended comments from course evaluations and comparing these insights with established competency frameworks to enhance teaching quality. Design/methodology/approach In this study, the authors used topic modeling techniques to analyze 2,870 comments from student course evaluations, allowing to extract key competencies perceived as essential for effective teaching. This qualitative approach enabled a deeper understanding of student perspectives, beyond the limitations of closed-ended survey formats. The competencies identified through this analysis were then compared with those outlined in earlier research, providing a unique opportunity to validate and expand the understanding of teaching effectiveness in higher education. Findings This analysis revealed a strong alignment between student-perceived competencies and those identified in previous literature-based research. Key competencies such as communication, empathy, creativity and others, emerged as essential for effective teaching, with students emphasizing the importance of their engagement in the learning process. However, some competencies were less prominently highlighted in student feedback. Research limitations/implications This study’s reliance on open-ended student feedback presents a limitation, as certain competencies may not be easily expressed or recognized by students. Originality/value While previous studies have applied text mining or topic modeling to student feedback, this study makes a distinct contribution by systematically comparing the competencies emerging from open-ended comments with an established framework derived from the literature.
Evidence weight
Balanced mode · F 0.40 / M 0.15 / V 0.05 / R 0.40
| F · citation impact | 0.50 × 0.4 = 0.20 |
| M · momentum | 0.50 × 0.15 = 0.07 |
| V · venue signal | 0.50 × 0.05 = 0.03 |
| R · text relevance † | 0.50 × 0.4 = 0.20 |
† Text relevance is estimated at 0.50 on the detail page — for your query’s actual relevance score, open this paper from a search result.