BERTopic for Topic Modeling of Hindi Short Texts: A Comparative Study

TL;DR

This study evaluates BERTopic's effectiveness in modeling Hindi short texts, demonstrating its superior performance over traditional models through coherence score assessments across multiple embedding techniques.

Contribution

It provides a comprehensive comparison of BERTopic with eight established models specifically for Hindi short texts, highlighting its advantages in semantic coherence.

Findings

BERTopic outperforms traditional models in coherence scores

Contextual embeddings enhance topic modeling for Hindi texts

Multiple embedding models were evaluated to confirm robustness

Abstract

As short text data in native languages like Hindi increasingly appear in modern media, robust methods for topic modeling on such data have gained importance. This study investigates the performance of BERTopic in modeling Hindi short texts, an area that has been under-explored in existing research. Using contextual embeddings, BERTopic can capture semantic relationships in data, making it potentially more effective than traditional models, especially for short and diverse texts. We evaluate BERTopic using 6 different document embedding models and compare its performance against 8 established topic modeling techniques, such as Latent Dirichlet Allocation (LDA), Non-negative Matrix Factorization (NMF), Latent Semantic Indexing (LSI), Additive Regularization of Topic Models (ARTM), Probabilistic Latent Semantic Analysis (PLSA), Embedded Topic Model (ETM), Combined Topic Model (CTM), and Top2Vec. The models are assessed using coherence scores across a range of topic counts. Our results reveal that BERTopic consistently outperforms other models in capturing coherent topics from short Hindi texts.