# Unsupervised Opinion Summarization with Content Planning

arXiv: https://arxiv.org/abs/2012.07808 · HTML: https://mlsanity.com/paper/2012.07808/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Dec 2020.

## Built on by (most cited first, 27 of 27)

- [Aspect-Controllable Opinion Summarization](https://mlsanity.com/paper/2109.03171/) (2021)
- [Prompted Opinion Summarization with GPT-3.5](https://mlsanity.com/paper/2211.15914/) (2022)
- [Convex Aggregation for Opinion Summarization](https://mlsanity.com/paper/2104.01371/) (2021)
- [Comparative Opinion Summarization via Collaborative Decoding](https://mlsanity.com/paper/2110.07520/) (2021)
- [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)
- [One Prompt To Rule Them All: LLMs for Opinion Summary Evaluation](https://mlsanity.com/paper/2402.11683/) (2024)
- [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)
- [Do Multi-Document Summarization Models Synthesize?](https://mlsanity.com/paper/2301.13844/) (2023)
- [What Is That Talk About? A Video-to-Text Summarization Dataset for Scientific Presentations](https://mlsanity.com/paper/2502.08279/) (2025)
- [Large-Scale and Multi-Perspective Opinion Summarization with Diverse Review Subsets](https://mlsanity.com/paper/2310.13340/) (2023)
- [A Sentiment Consolidation Framework for Meta-Review Generation](https://mlsanity.com/paper/2402.18005/) (2024)
- [Beyond Opinion Mining: Summarizing Opinions of Customer Reviews](https://mlsanity.com/paper/2206.01543/) (2022)
- [Hierarchical Indexing for Retrieval-Augmented Opinion Summarization](https://mlsanity.com/paper/2403.00435/) (2024)
- [Attributable and Scalable Opinion Summarization](https://mlsanity.com/paper/2305.11603/) (2023)
- [Product Description and QA Assisted Self-Supervised Opinion Summarization](https://mlsanity.com/paper/2404.05243/) (2024)
- [GLIMPSE: Pragmatically Informative Multi-Document Summarization for Scholarly Reviews](https://mlsanity.com/paper/2406.07359/) (2024)
- [Unsupervised Opinion Summarization Using Approximate Geodesics](https://mlsanity.com/paper/2209.07496/) (2022)
- [Integrating AI Planning with Natural Language Processing: A Combination of Explicit and Tacit Knowledge](https://mlsanity.com/paper/2202.07138/) (2022)
- [Decomposed Opinion Summarization with Verified Aspect-Aware Modules](https://mlsanity.com/paper/2501.17191/) (2025)
- [Simple Yet Effective Synthetic Dataset Construction for Unsupervised Opinion Summarization](https://mlsanity.com/paper/2303.11660/) (2023)
- [A Hierarchical Encoding-Decoding Scheme for Abstractive Multi-document Summarization](https://mlsanity.com/paper/2305.08503/) (2023)
- [Warmup Generations: A Task-Agnostic Approach for Guiding Sequence-to-Sequence Learning with Unsupervised Initial State Generation](https://mlsanity.com/paper/2502.12304/) (2025)
- [Distilling Opinions at Scale: Incremental Opinion Summarization using XL-OPSUMM](https://mlsanity.com/paper/2406.10886/) (2024)
- [Answering Subjective Induction Questions on Products by Summarizing Multi-sources Multi-viewpoints Knowledge](https://mlsanity.com/paper/2309.05938/) (2023)
- [Multilingual Sentiment Aware Text Summarization A Reinforcement Learning Approach for Consistency Maintenance](https://mlsanity.com/paper/2606.08940/) (2026)

## Abstract (arXiv)

The recent success of deep learning techniques for abstractive summarization is predicated on the availability of large-scale datasets. When summarizing reviews (e.g., for products or movies), such training data is neither available nor can be easily sourced, motivating the development of methods which rely on synthetic datasets for supervised training. We show that explicitly incorporating content planning in a summarization model not only yields output of higher quality, but also allows the creation of synthetic datasets which are more natural, resembling real world document-summary pairs. Our content plans take the form of aspect and sentiment distributions which we induce from data without access to expensive annotations. Synthetic datasets are created by sampling pseudo-reviews from a Dirichlet distribution parametrized by our content planner, while our model generates summaries based on input reviews and induced content plans. Experimental results on three domains show that our approach outperforms competitive models in generating informative, coherent, and fluent summaries that capture opinion consensus.