Analysing Longitudinal Social Science Questionnaires: Topic modelling with BERT-based Embeddings
Authors:
- 17 December 2022
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 5558-5567
Abstract
Unsupervised topic modelling is a useful unbiased mechanism for topic labelling of complex longitudinal questionnaires covering multiple domains such as social science and medicine. Manual tagging of such complex datasets increases the propensity of incorrect or inconsistent labels and is a barrier to scaling the processing of longitudinal questionnaires for provision of question banks for data collection agencies. Towards this effort, we propose a tailored BERTopic framework that takes advantage of its novel sentence embedding for creating interpretable topics, and extend it with an enhanced visualisation for comparing the topic model labels with the tags manually assigned to the question literals. The resulting topic clusters uncover instances of mislabelled question tags, while also enabling showcasing the semantic shifts and evolution of the topics across the time span of the longitudinal questionnaires. The tailored BERTopic framework outperforms existing topic modelling baselines for the quantitative evaluation metrics of topic coherence and diversity, while also being 18 times faster than the next best-performing baseline.Keywords
Funding Information
- Science and Technology Facilities Council
This publication has 14 references indexed in Scilit:
- OCTIS: Comparing and Optimizing Topic models is Simple!2021
- DeCLUTR: Deep Contrastive Learning for Unsupervised Textual Representations2021
- Predictive Biases in Natural Language Processing Models: A Conceptual Framework and Overview2020
- Search for K: Assessing Five Topic-Modeling Approaches to 120,000 Canadian Articles2019
- Identifying and Understanding Business Trends using Topic Models with Word Embedding2019
- Deep Contextualized Word Representations2018
- Real World City Event Extraction from Twitter Data StreamsProcedia Computer Science, 2016
- LDAvis: A method for visualizing and interpreting topics2014
- Glove: Global Vectors for Word Representation2014
- Empirical study of topic modeling in Twitter2010