Topic Modelling on Consumer Financial Protection Bureau Data: An Approach Using BERT Based Embeddings
Abstract
Customers' reviews and comments are important for businesses to understand users' sentiment about the products and services. However, this data needs to be analyzed to assess the sentiment associated with topics/aspects to provide efficient customer assistance. LDA and LSA fail to capture the semantic relationship and are not specific to any domain. In this study, we evaluate BERTopic, a novel method that generates topics using sentence embeddings on Consumer Financial Protection Bureau (CFPB) data. Our work shows that BERTopic is flexible and yet provides meaningful and diverse topics compared to LDA and LSA. Furthermore, domain-specific pre-trained embeddings (FinBERT) yield even better topics. We evaluated the topics on coherence score (c_v) and UMass.
Keywords
Cite
@article{arxiv.2205.07259,
title = {Topic Modelling on Consumer Financial Protection Bureau Data: An Approach Using BERT Based Embeddings},
author = {Vasudeva Raju Sangaraju and Bharath Kumar Bolla and Deepak Kumar Nayak and Jyothsna Kh},
journal= {arXiv preprint arXiv:2205.07259},
year = {2022}
}
Comments
Accepted at International Conference for Convergence in Technology, 2022