Have you tried Neural Topic Models? Comparative Analysis of Neural and Non-Neural Topic Models with Application to COVID-19 Twitter Data
This work provides insights for researchers analyzing social media data, though it is incremental as it builds on existing topic modeling techniques.
The authors compared neural and non-neural topic models on COVID-19 Twitter data, finding that neural models outperform classical ones on metrics and produce more coherent topics, with a novel regularization term addressing mode collapse effectively.
Topic models are widely used in studying social phenomena. We conduct a comparative study examining state-of-the-art neural versus non-neural topic models, performing a rigorous quantitative and qualitative assessment on a dataset of tweets about the COVID-19 pandemic. Our results show that not only do neural topic models outperform their classical counterparts on standard evaluation metrics, but they also produce more coherent topics, which are of great benefit when studying complex social problems. We also propose a novel regularization term for neural topic models, which is designed to address the well-documented problem of mode collapse, and demonstrate its effectiveness.