# Improving Document-Level Sentiment Analysis with User and Product Context

arXiv: https://arxiv.org/abs/2011.09210 · HTML: https://mlsanity.com/paper/2011.09210/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Nov 2020.

## Built on by (most cited first, 7 of 7)

- [The Sentiment Problem: A Critical Survey towards Deconstructing Sentiment Analysis](https://mlsanity.com/paper/2310.12318/) (2023)
- [Dynamic Multi-Scale Context Aggregation for Conversational Aspect-Based Sentiment Quadruple Analysis](https://mlsanity.com/paper/2309.15476/) (2023)
- [Fine-grainedly Synthesize Streaming Data Based On Large Language Models With Graph Structure Understanding For Data Sparsity](https://mlsanity.com/paper/2403.06139/) (2024)
- [Exploiting Rich Textual User-Product Context for Improving Sentiment Analysis](https://mlsanity.com/paper/2212.08888/) (2022)
- [Entity-Aspect-Opinion-Sentiment Quadruple Extraction for Fine-grained Sentiment Analysis](https://mlsanity.com/paper/2311.16678/) (2023)
- [SynGraph: A Dynamic Graph-LLM Synthesis Framework for Sparse Streaming User Sentiment Modeling](https://mlsanity.com/paper/2503.04619/) (2025)
- [Multi-Attribute Multi-Grained Adaptation of Pre-Trained Language Models for Text Understanding from Bayesian Perspective](https://mlsanity.com/paper/2503.06085/) (2025)

## Abstract (arXiv)

Past work that improves document-level sentiment analysis by encoding user and product information has been limited to considering only the text of the current review. We investigate incorporating additional review text available at the time of sentiment prediction that may prove meaningful for guiding prediction. Firstly, we incorporate all available historical review text belonging to the author of the review in question. Secondly, we investigate the inclusion of historical reviews associated with the current product (written by other users). We achieve this by explicitly storing representations of reviews written by the same user and about the same product and force the model to memorize all reviews for one particular user and product. Additionally, we drop the hierarchical architecture used in previous work to enable words in the text to directly attend to each other. Experiment results on IMDB, Yelp 2013 and Yelp 2014 datasets show improvement to state-of-the-art of more than 2 percentage points in the best case.