TY - GEN
T1 - Document Retrieval and Claim Verification to Mitigate COVID-19 Misinformation
AU - Sundriyal, Megha
AU - Malhotra, Ganeshan
AU - Akhtar, Md Shad
AU - Sengupta, Shubhashis
AU - Fano, Andrew
AU - Chakraborty, Tanmoy
N1 - Funding Information:
T. Chakraborty would like to acknowledge the support of the Ramanujan Fellowship, and ihubAnubhuti-iiitd Foundation set up under the NMICPS scheme of the Department of Science and Technology, India. M. S. Akhtar and T. Chakraborty thank Infosys Centre for AI at IIIT-Delhi for the valuable support.
Funding Information:
T. Chakraborty would like to acknowledge the support of the Ramanujan Fellowship, and ihub-Anubhuti-iiitd Foundation set up under the NM-ICPS scheme of the Department of Science and Technology, India. M. S. Akhtar and T. Chakraborty thank Infosys Centre for AI at IIIT-Delhi for the valuable support.
Publisher Copyright:
© 2022 Association for Computational Linguistics.
PY - 2022
Y1 - 2022
N2 - During the COVID-19 pandemic, the spread of misinformation on online social media has grown exponentially. Unverified bogus claims on these platforms regularly mislead people, leading them to believe in half-baked truths. The current vogue is to employ manual fact-checkers to verify claims to combat this avalanche of misinformation. However, establishing such claims’ veracity is becoming increasingly challenging, partly due to the plethora of information available, which is difficult to process manually. Thus, it becomes imperative to verify claims automatically without human interventions. To cope up with this issue, we propose an automated claim verification solution encompassing two steps – document retrieval and veracity prediction. For the retrieval module, we employ a hybrid search-based system with BM25 as a base retriever and experiment with recent state-of-the-art transformer-based models for re-ranking. Furthermore, we use a BART-based textual entailment architecture to authenticate the retrieved documents in the later step. We report experimental findings, demonstrating that our retrieval module outperforms the best baseline system by 10.32 NDCG@100 points. We escort a demonstration to assess the efficacy and impact of our suggested solution. As a byproduct of this study, we present an open-source, easily deployable, and user-friendly Python API that the community can adopt.
AB - During the COVID-19 pandemic, the spread of misinformation on online social media has grown exponentially. Unverified bogus claims on these platforms regularly mislead people, leading them to believe in half-baked truths. The current vogue is to employ manual fact-checkers to verify claims to combat this avalanche of misinformation. However, establishing such claims’ veracity is becoming increasingly challenging, partly due to the plethora of information available, which is difficult to process manually. Thus, it becomes imperative to verify claims automatically without human interventions. To cope up with this issue, we propose an automated claim verification solution encompassing two steps – document retrieval and veracity prediction. For the retrieval module, we employ a hybrid search-based system with BM25 as a base retriever and experiment with recent state-of-the-art transformer-based models for re-ranking. Furthermore, we use a BART-based textual entailment architecture to authenticate the retrieved documents in the later step. We report experimental findings, demonstrating that our retrieval module outperforms the best baseline system by 10.32 NDCG@100 points. We escort a demonstration to assess the efficacy and impact of our suggested solution. As a byproduct of this study, we present an open-source, easily deployable, and user-friendly Python API that the community can adopt.
UR - http://www.scopus.com/inward/record.url?scp=85137453904&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85137453904&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85137453904
T3 - CONSTRAINT 2022 - 2nd Workshop on Combating Online Hostile Posts in Regional Languages during Emergency Situation, Proceedings of the Workshop
SP - 66
EP - 74
BT - CONSTRAINT 2022 - 2nd Workshop on Combating Online Hostile Posts in Regional Languages during Emergency Situation, Proceedings of the Workshop
A2 - Chakraborty, Tanmoy
A2 - Akhtar, Md. Shad
A2 - Shu, Kai
A2 - Bernard, H. Russell
A2 - Liakata, Maria
A2 - Nakov, Preslav
PB - Association for Computational Linguistics (ACL)
T2 - 2nd Workshop on Combating Online Hostile Posts in Regional Languages during Emergency Situation, CONSTRAINT 2022
Y2 - 27 May 2022
ER -