Katalog Plus
Bibliothek der Frankfurt UAS
Bald neuer Katalog: sichern Sie sich schon vorab Ihre persönlichen Merklisten im Nutzerkonto: Anleitung.
Dieses Ergebnis aus BASE kann Gästen nicht angezeigt werden.  Login für vollen Zugriff.

Clustering students’ text form feedback data: comparison of eight vector space models

Title: Clustering students’ text form feedback data: comparison of eight vector space models
Authors: Hämäläinen, Wilhelmiina; Rybicki, Jan-Mikael; Malmi, Lauri; Jung, Alex; Pollari-Malmi, Kerttu
Contributors: Department of Computer Science; Computer Science Lecturers; Computer Science - Computational Life Sciences (CSLife) - Research area; Computer Science - Artificial Intelligence and Machine Learning (AIML) - Research area; Lecturer Hämäläinen Wilhelmiina group; Computer Science Professors; Computer Science - Human-Computer Interaction and Design (HCID) - Research area; Computer Science - Computing education research and educational technology (CER) - Research area; Professorship Malmi L.; Computer Science - Large-scale Computing and Data Analysis (LSCA) - Research area; Helsinki Institute for Information Technology (HIIT); Professorship Jung Alexander; Lecturer Pollari-Malmi Kerttu group; Aalto-yliopisto; Aalto University
Publication Year: 2025
Collection: Aalto University Publication Archive (Aaltodoc) / Aalto-yliopiston julkaisuarkistoa
Subject Terms: clustering; vector space models; student feedback
Description: Text-form student feedback is an indispensable source of information for all university lecturers. Since manual analysis of such feedback is laborious, it has been suggested that text clustering methods could be used to automate the process. However, the success of text clustering depends heavily on the vector space presentation of documents. In this paper, a comprehensive evaluation of eight vector space models (VSMs) is presented in combination with different linguistic preprocessing techniques in English and Finnish student feedback data. The results show that the choice of VSM has a strong effect on the clustering performance. The models based on short and long character n-grams work best, while word2vec models perform worst. In general, stop word removal has a positive effect, while stemming and lemmatization may be detrimental with many VSMs. The main themes of the data could be well identified from cluster centroids. An alternative approach of describing clusters by frequent word n-grams worked also well for sufficiently large, distinct classes with clear keywords. ; Peer reviewed
Document Type: conference object
File Description: application/pdf
Language: English
Relation: International Conference on Big Data and Education; ICBDE '24: Proceedings of the 2024 7th International Conference on Big Data and Education; pp. 57-64; https://aaltodoc.aalto.fi/handle/123456789/133843
DOI: 10.1145/3704289.3704294
Availability: https://aaltodoc.aalto.fi/handle/123456789/133843; https://doi.org/10.1145/3704289.3704294
Rights: openAccess ; CC BY ; https://creativecommons.org/licenses/by/4.0/
Accession Number: edsbas.DCCC40B6
Database: BASE