# OpinionConv: Conversational Product Search with Grounded Opinions

arXiv: https://arxiv.org/abs/2308.04226 · HTML: https://mlsanity.com/paper/2308.04226/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 43 references that are in the map.
- First posted on arXiv 8 Aug 2023.

## Builds on (most cited first, 13 of 13)

- [Persuasion for Good: Towards a Personalized Persuasive Dialogue System for Social Good](https://mlsanity.com/paper/1906.06725/) (2019)
- [Decoupling Strategy and Generation in Negotiation Dialogues](https://mlsanity.com/paper/1808.09637/) (2018)
- [AmazonQA: A Review-Based Question Answering Task](https://mlsanity.com/paper/1908.04364/) (2019)
- [Conversational Question Answering: A Survey](https://mlsanity.com/paper/2106.00874/) (2021)
- [Addressing Complex and Subjective Product-Related Queries with Customer Reviews](https://mlsanity.com/paper/1512.06863/) (2015)
- [A Dynamic Strategy Coach for Effective Negotiation](https://mlsanity.com/paper/1909.13426/) (2019)
- [SubjQA: A Dataset for Subjectivity and Review Comprehension](https://mlsanity.com/paper/2004.14283/) (2020)
- [Modeling Ambiguity, Subjectivity, and Diverging Viewpoints in Opinion Question Answering Systems](https://mlsanity.com/paper/1610.08095/) (2016)
- [Improving BERT Performance for Aspect-Based Sentiment Analysis](https://mlsanity.com/paper/2010.11731/) (2020)
- [Conversational Product Search Based on Negative Feedback](https://mlsanity.com/paper/1909.02071/) (2019)
- [Answering Product-Questions by Utilizing Questions from Other Contextually Similar Products](https://mlsanity.com/paper/2105.08956/) (2021)
- [End-to-End Conversational Search for Online Shopping with Utterance Transfer](https://mlsanity.com/paper/2109.05460/) (2021)
- [Review Conversational Reading Comprehension](https://mlsanity.com/paper/1902.00821/) (2019)

## Abstract (arXiv)

When searching for products, the opinions of others play an important role in making informed decisions. Subjective experiences about a product can be a valuable source of information. This is also true in sales conversations, where a customer and a sales assistant exchange facts and opinions about products. However, training an AI for such conversations is complicated by the fact that language models do not possess authentic opinions for their lack of real-world experience. We address this problem by leveraging product reviews as a rich source of product opinions to ground conversational AI in true subjective narratives. With OpinionConv, we develop the first conversational AI for simulating sales conversations. To validate the generated conversations, we conduct several user studies showing that the generated opinions are perceived as realistic. Our assessors also confirm the importance of opinions as an informative basis for decision-making.