Harnessing Abstractive Summarization for Fact-Checked Claim Detection

TL;DR

This paper introduces a method that uses abstractive summarization to improve the detection of fact-checked claims on social media, significantly enhancing retrieval performance and aiding rapid misinformation identification.

Contribution

It presents a novel workflow combining abstractive summarization with claim retrieval, along with a new dataset of noisy claims and gold summaries for training and evaluation.

Findings

Retrieval performance doubled with out-of-the-box summarization models.

Fine-tuning models on the dataset triples retrieval effectiveness.

Achieved Recall@5 of 35% and MRR of 0.3, outperforming baselines.

Abstract

Social media platforms have become new battlegrounds for anti-social elements, with misinformation being the weapon of choice. Fact-checking organizations try to debunk as many claims as possible while staying true to their journalistic processes but cannot cope with its rapid dissemination. We believe that the solution lies in partial automation of the fact-checking life cycle, saving human time for tasks which require high cognition. We propose a new workflow for efficiently detecting previously fact-checked claims that uses abstractive summarization to generate crisp queries. These queries can then be executed on a general-purpose retrieval system associated with a collection of previously fact-checked claims. We curate an abstractive text summarization dataset comprising noisy claims from Twitter and their gold summaries. It is shown that retrieval performance improves 2x by using popular out-of-the-box summarization models and 3x by fine-tuning them on the accompanying dataset compared to verbatim querying. Our approach achieves Recall@5 and MRR of 35% and 0.3, compared to baseline values of 10% and 0.1, respectively. Our dataset, code, and models are available publicly: https://github.com/varadhbhatnagar/FC-Claim-Det/