# TopicImpact: Improving Customer Feedback Analysis with Opinion Units for Topic Modeling and Star-Rating Prediction

arXiv: https://arxiv.org/abs/2507.13392 · HTML: https://mlsanity.com/paper/2507.13392/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 5 of its 39 references that are in the map.
- First posted on arXiv 16 Jul 2025.

## Builds on (most cited first, 5 of 5)

- [BERTopic: Neural topic modeling with a class-based TF-IDF procedure](https://mlsanity.com/paper/2203.05794/) (2022)
- [Knowing What, How and Why: A Near Complete Solution for Aspect-based Sentiment Analysis](https://mlsanity.com/paper/1911.01616/) (2019)
- [Sentiment-Aware Word and Sentence Level Pre-training for Sentiment Analysis](https://mlsanity.com/paper/2210.09803/) (2022)
- [SentiCSE: A Sentiment-aware Contrastive Sentence Embedding Framework with Sentiment-guided Textual Similarity](https://mlsanity.com/paper/2404.01104/) (2024)
- [Exploring the Power of Topic Modeling Techniques in Analyzing Customer Reviews: A Comparative Analysis](https://mlsanity.com/paper/2308.11520/) (2023)

## Abstract (arXiv)

We improve the extraction of insights from customer reviews by restructuring the topic modelling pipeline to operate on opinion units - distinct statements that include relevant text excerpts and associated sentiment scores. Prior work has demonstrated that such units can be reliably extracted using large language models. The result is a heightened performance of the subsequent topic modeling, leading to coherent and interpretable topics while also capturing the sentiment associated with each topic. By correlating the topics and sentiments with business metrics, such as star ratings, we can gain insights on how specific customer concerns impact business outcomes. We present our system's implementation, use cases, and advantages over other topic modeling and classification solutions. We also evaluate its effectiveness in creating coherent topics and assess methods for integrating topic and sentiment modalities for accurate star-rating prediction.