University of Twente Student Theses

Login

Text Mining to Improve Education : An Evaluation of Text Mining in the Student Feedback Process

Claessen, C.T. (2022) Text Mining to Improve Education : An Evaluation of Text Mining in the Student Feedback Process.

[img] PDF
862kB
Abstract:When it comes to evaluating education, student feedback surveys are common practice. Students are then typically asked to answer both open and Likert-type questions. While there is a consensus on the richness of qualitative data, its analysis is costly. One solution that would allow universities to take full advantage of their data, is text mining. In this research, sentiment analysis and text summarization were applied and evaluated. Moreover, the usage of other methodologies was mapped in a literature review. Overall, it was found that sentiment analysis may be a useful tool for replacing numerical measurements of student feedback. Text summarization on individual comments did not yield promising results, which may be due to the shortness of comments. Moreover, current literature mainly focuses on sentiment analysis, clustering, and categorization. Consequently, future efforts may expand this research by using larger samples and applying different methods.
Item Type:Essay (Bachelor)
Faculty:BMS: Behavioural, Management and Social Sciences
Subject:54 computer science, 77 psychology, 81 education, teaching
Programme:Psychology BSc (56604)
Link to this item:https://purl.utwente.nl/essays/91280
Export this item as:BibTeX
EndNote
HTML Citation
Reference Manager

 

Repository Staff Only: item control page