WhatsApp Tiplines and Multilingual Claims in the 2021 Indian Assembly Elections

2025-07-22

AI Summary

This study investigates the handling of election- and COVID-19-related misinformation via multilingual WhatsApp tiplines during India’s 2021 state elections, examining disparities and commonalities across high- and low-resource languages (e.g., Hindi, Tamil, Bengali). Method: A mixed-methods approach integrates高频 word analysis, neural sentence embedding clustering, user behavior tracking, and response-time modeling. Contribution/Results: We find that cross-lingual tip submissions exhibit high semantic similarity; approximately 12% of users submit duplicate reports in multiple languages to the same fact-checking organization; median verification latency is 48 hours; no cross-organization reporting is observed. These findings empirically refute the “linguistic silo” hypothesis, demonstrating structural homogeneity in multilingual misinformation diffusion. The study provides actionable evidence for designing scalable, interoperable, multilingual fact-checking infrastructures globally.

Technology Category

• Natural Language Processing: Fact-Checking / Misinformation Detection (NLP Focus)
• Application Domains: Misinformation & Fake News
• Humans and AI: Voting

Application Category

• Web Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data
• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search
• Responsible Web: Mitigating misinformation and disinformation

Abstract

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 (tips) from 451 users, covering both high-resource languages (English, Hindi) and a low-resource language (Telugu) during the 2021 Indian assembly elections using a mixed-method approach. We categorize the claims into three categories, election, COVID-19, and others, and observe variations across languages. We compare content similarity through frequent word analysis and clustering of neural sentence embeddings. We also investigate user overlap across languages and fact-checking organizations. We measure the average time required to debunk claims and inform tipline users. Results reveal similarities in claims across languages, with some users submitting tips in multiple languages to the same fact-checkers. Fact-checkers generally require a couple of days to debunk a new claim and share the results with users. Notably, no user submits claims to multiple fact-checking organizations, indicating that each organization maintains a unique audience. We provide practical recommendations for using tiplines during elections with ethical consideration of users' information.

Problem

• Analyzing multilingual misinformation claims during Indian elections
• Comparing content similarity across high and low-resource languages
• Measuring fact-checking response times and user engagement patterns

Innovation

• WhatsApp tiplines combat misinformation via user interaction
• Mixed-method analysis of multilingual claims during elections
• Neural embeddings compare content similarity across languages