# GraphNLI: A Graph-based Natural Language Inference Model for Polarity Prediction in Online Debates

arXiv: https://arxiv.org/abs/2202.08175 · HTML: https://mlsanity.com/paper/2202.08175/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 48 references that are in the map.
- First posted on arXiv 16 Feb 2022.

## Builds on (most cited first, 12 of 12)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [A Retrospective Analysis of the Fake News Challenge Stance Detection Task](https://mlsanity.com/paper/1806.05180/) (2018)
- [Asking Too Much? The Rhetorical Role of Questions in Political Discourse](https://mlsanity.com/paper/1708.02254/) (2017)
- [A Dataset Independent Set of Baselines for Relation Prediction in Argument Mining](https://mlsanity.com/paper/2003.04970/) (2020)
- [Identifying Partisan Slant in News Articles and Twitter during Political Crises](https://mlsanity.com/paper/1703.05819/) (2017)
- [Illuminating an Ecosystem of Partisan Websites](https://mlsanity.com/paper/1803.03576/) (2018)
- [Stop Tracking Me Bro! Differential Tracking Of User Demographics On Hyper-partisan Websites](https://mlsanity.com/paper/2002.00934/) (2020)
- [Online Hate: Behavioural Dynamics and Relationship with Misinformation](https://mlsanity.com/paper/2105.14005/) (2021)
- [Notes on Abstract Argumentation Theory](https://mlsanity.com/paper/1806.07709/) (2018)
- [Under the Spotlight: Web Tracking in Indian Partisan News Websites](https://mlsanity.com/paper/2102.03656/) (2021)

## Built on by (most cited first, 14 of 14)

- [SAMGPT: Text-free Graph Foundation Model for Multi-domain Pre-training and Cross-domain Adaptation](https://mlsanity.com/paper/2502.05424/) (2025)
- [MultiGPrompt for Multi-Task Pre-Training and Prompting on Graphs](https://mlsanity.com/paper/2312.03731/) (2023)
- [Reinforcement Learning-based Counter-Misinformation Response Generation: A Case Study of COVID-19 Vaccine Misinformation](https://mlsanity.com/paper/2303.06433/) (2023)
- [Large Language Models in Argument Mining: A Survey](https://mlsanity.com/paper/2506.16383/) (2025)
- [AnnoBERT: Effectively Representing Multiple Annotators' Label Choices to Improve Hate Speech Detection](https://mlsanity.com/paper/2212.10405/) (2022)
- [CoSyn: Detecting Implicit Hate Speech in Online Conversations Using a Context Synergized Hyperbolic Network](https://mlsanity.com/paper/2303.03387/) (2023)
- [AI in the Gray: Exploring Moderation Policies in Dialogic Large Language Models vs. Human Answers in Controversial Topics](https://mlsanity.com/paper/2308.14608/) (2023)
- [Node-Time Conditional Prompt Learning In Dynamic Graphs](https://mlsanity.com/paper/2405.13937/) (2024)
- [A semantic embedding space based on large language models for modelling human beliefs](https://mlsanity.com/paper/2408.07237/) (2024)
- [A Graph-Based Context-Aware Model to Understand Online Conversations](https://mlsanity.com/paper/2211.09207/) (2022)
- [Putting Context in Context: the Impact of Discussion Structure on Text Classification](https://mlsanity.com/paper/2402.02975/) (2024)
- [Strategic Planning and Rationalizing on Trees Make LLMs Better Debaters](https://mlsanity.com/paper/2505.14886/) (2025)
- [When Prompting Meets Spiking: Graph Sparse Prompting via Spiking Graph Prompt Learning](https://mlsanity.com/paper/2601.02662/) (2026)
- [GASCOM: Graph-based Attentive Semantic Context Modeling for Online Conversation Understanding](https://mlsanity.com/paper/2310.14028/) (2023)

## Abstract (arXiv)

Online forums that allow participatory engagement between users have been transformative for public discussion of important issues. However, debates on such forums can sometimes escalate into full blown exchanges of hate or misinformation. An important tool in understanding and tackling such problems is to be able to infer the argumentative relation of whether a reply is supporting or attacking the post it is replying to. This so called polarity prediction task is difficult because replies may be based on external context beyond a post and the reply whose polarity is being predicted. We propose GraphNLI, a novel graph-based deep learning architecture that uses graph walk techniques to capture the wider context of a discussion thread in a principled fashion. Specifically, we propose methods to perform root-seeking graph walks that start from a post and captures its surrounding context to generate additional embeddings for the post. We then use these embeddings to predict the polarity relation between a reply and the post it is replying to. We evaluate the performance of our models on a curated debate dataset from Kialo, an online debating platform. Our model outperforms relevant baselines, including S-BERT, with an overall accuracy of 83%.