# OpinionDigest: A Simple Framework for Opinion Summarization

arXiv: https://arxiv.org/abs/2005.01901 · HTML: https://mlsanity.com/paper/2005.01901/

## Key facts

- Cited by 37 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 May 2020.

## Built on by (most cited first, 30 of 37)

- [Fine-tuning language models to find agreement among humans with diverse preferences](https://mlsanity.com/paper/2211.15006/) (2022)
- [Learning Opinion Summarizers by Selecting Informative Reviews](https://mlsanity.com/paper/2109.04325/) (2021)
- [Convex Aggregation for Opinion Summarization](https://mlsanity.com/paper/2104.01371/) (2021)
- [Every Bite Is an Experience: Key Point Analysis of Business Reviews](https://mlsanity.com/paper/2106.06758/) (2021)
- [Comparative Opinion Summarization via Collaborative Decoding](https://mlsanity.com/paper/2110.07520/) (2021)
- [Controllable Text Summarization: Unraveling Challenges, Approaches, and Prospects -- A Survey](https://mlsanity.com/paper/2311.09212/) (2023)
- [Unsupervised Extractive Opinion Summarization Using Sparse Coding](https://mlsanity.com/paper/2203.07921/) (2022)
- [Efficient Few-Shot Fine-Tuning for Opinion Summarization](https://mlsanity.com/paper/2205.02170/) (2022)
- [Scientific Opinion Summarization: Paper Meta-review Generation Dataset, Methods, and Evaluation](https://mlsanity.com/paper/2305.14647/) (2023)
- [OpinSummEval: Revisiting Automated Evaluation for Opinion Summarization](https://mlsanity.com/paper/2310.18122/) (2023)
- [DYPLOC: Dynamic Planning of Content Using Mixed Language Models for Text Generation](https://mlsanity.com/paper/2106.00791/) (2021)
- [Product Question Answering in E-Commerce: A Survey](https://mlsanity.com/paper/2302.08092/) (2023)
- [Beyond Opinion Mining: Summarizing Opinions of Customer Reviews](https://mlsanity.com/paper/2206.01543/) (2022)
- [An Empirical Analysis of Diversity in Argument Summarization](https://mlsanity.com/paper/2402.01535/) (2024)
- [GLIMPSE: Pragmatically Informative Multi-Document Summarization for Scholarly Reviews](https://mlsanity.com/paper/2406.07359/) (2024)
- [Aligning Large Language Models with Diverse Political Viewpoints](https://mlsanity.com/paper/2406.14155/) (2024)
- [Prompted Aspect Key Point Analysis for Quantitative Review Summarization](https://mlsanity.com/paper/2407.14049/) (2024)
- [Why Do You Feel This Way? Summarizing Triggers of Emotions in Social Media Posts](https://mlsanity.com/paper/2210.12531/) (2022)
- [Self-Agreement: A Framework for Fine-tuning Language Models to Find Agreement among Diverse Opinions](https://mlsanity.com/paper/2305.11460/) (2023)
- [OpinioRAG: Towards Generating User-Centric Opinion Highlights from Large-scale Online Reviews](https://mlsanity.com/paper/2509.00285/) (2025)
- [Noisy Pairing and Partial Supervision for Stylized Opinion Summarization](https://mlsanity.com/paper/2211.08723/) (2022)
- [Rationale-based Opinion Summarization](https://mlsanity.com/paper/2404.00217/) (2024)
- [Summarization of Opinionated Political Documents with Varied Perspectives](https://mlsanity.com/paper/2411.04093/) (2024)
- [Polarity Calibration for Opinion Summarization](https://mlsanity.com/paper/2404.01706/) (2024)
- [Fine-Grained Opinion Summarization with Minimal Supervision](https://mlsanity.com/paper/2110.08845/) (2021)
- [Automatically Evaluating Opinion Prevalence in Opinion Summarization](https://mlsanity.com/paper/2307.14305/) (2023)
- [LFOSum: Summarizing Long-form Opinions with Large Language Models](https://mlsanity.com/paper/2410.13037/) (2024)
- [The Variance Paradox: How AI Reduces Diversity but Increases Novelty](https://mlsanity.com/paper/2508.19264/) (2025)
- [Faithful Summarisation under Disagreement via Belief-Level Aggregation](https://mlsanity.com/paper/2601.04889/) (2026)
- [Abstractive Opinion Tagging](https://mlsanity.com/paper/2101.06880/) (2021)

## Abstract (arXiv)

We present OpinionDigest, an abstractive opinion summarization framework, which does not rely on gold-standard summaries for training. The framework uses an Aspect-based Sentiment Analysis model to extract opinion phrases from reviews, and trains a Transformer model to reconstruct the original reviews from these extractions. At summarization time, we merge extractions from multiple reviews and select the most popular ones. The selected opinions are used as input to the trained Transformer model, which verbalizes them into an opinion summary. OpinionDigest can also generate customized summaries, tailored to specific user needs, by filtering the selected opinions according to their aspect and/or sentiment. Automatic evaluation on Yelp data shows that our framework outperforms competitive baselines. Human studies on two corpora verify that OpinionDigest produces informative summaries and shows promising customization capabilities.