activity
20242026
collaborators

11 papers

cs.IR2026

Automating Categorization of Scientific Texts with In-Context Learning and Prompt-Chaining in Large Language Models

Gautam Kishore Shahi, Oliver Hummel

The relentless expansion of scientific literature presents significant challenges for navigation and knowledge discovery. Within Research Information Retrieval, established tasks s…

cs.SI2026

When Transparency Falls Short: Auditing Platform Moderation During a High-Stakes Election

Benedetta Tessa, Gautam Kishore Shahi, Amaury Trujillo +1

During major political events, social media platforms encounter increased systemic risks. However, it is still unclear if and how they adjust their moderation practices in response…

cs.CL2025

Defining, Understanding, and Detecting Online Toxicity: Challenges and Machine Learning Approaches

Gautam Kishore Shahi, Tim A. Majchrzak

Online toxic content has grown into a pervasive phenomenon, intensifying during times of crisis, elections, and social unrest. A significant amount of research has been focused on…

cs.CL2025

SemCAFE: When Named Entities make the Difference Assessing Web Source Reliability through Entity-level Analytics

Gautam Kishore Shahi, Oshani Seneviratne, Marc Spaniol

With the shift from traditional to digital media, the online landscape now hosts not only reliable news articles but also a significant amount of unreliable content. Digital media…

cs.SI2025

WhatsApp Tiplines and Multilingual Claims in the 2021 Indian Assembly Elections

Gautam Kishore Shahi, Scot A. Hale

WhatsApp tiplines, first launched in 2019 to combat misinformation, enable users to interact with fact-checkers to verify misleading content. This study analyzes 580 unique claims…

cs.LG2025

Multimodal Misinformation Detection Using Early Fusion of Linguistic, Visual, and Social Features

Gautam Kishore Shahi

Amid a tidal wave of misinformation flooding social media during elections and crises, extensive research has been conducted on misinformation detection, primarily focusing on text…