Overview of the CLAIMSCAN-2023: Uncovering Truth in Social Media through Claim Detection and Identification of Claim Spans

Megha Sundriyal, Md. Shad Akhtar, Tanmoy Chakraborty

Abstract: The rapid development of online social media platforms has enabled a significant increase in content creation and information exchange, which has been extremely beneficial. These platforms, however, have also become a haven for those who spread false information, propaganda, and fake news. Claims are important in shaping our perceptions of the world, but they are often used to deceive people by those who spread false information. To address this issue, social media behemoths hire content moderators to filter out fake news from the real world. However, the sheer volume of information makes it difficult to identify fake news effectively. As a result, it is critical to automatically identify social media posts that make such claims, verify their veracity, and distinguish between credible and false claims. In response, CLAIMSCAN was presented at the 2023 Forum for Information Retrieval Evaluation (FIRE’2023). The primary goals focused on two critical tasks: Task A, determining whether a social media post is a claim, and Task B, precisely identifying the words or phrases within the post that form the claim. Task A received 40 registrations, indicating a high level of interest and participation in this timely challenge. Meanwhile, Task B drew participation from 28 teams, emphasizing its importance in the digital age of misinformation.