Countering Misinformation in Private Messaging Groups: Insights From a Fact-checking Chatbot

摘要

Misinformation on private messaging platforms like WhatsApp and LINE is a global concern. However, research has primarily focused on combating misinformation on public social media. Misinformation in private messaging platforms is difficult to challenge due to social norms, interpersonal relationships, and technological affordances. This study investigates Auntie Meiyu, a fact-checking chatbot integrated into LINE, a popular private messaging service in Taiwan. We interviewed 27 users who adopted Auntie Meiyu in their messaging groups to understand their motivations and perceptions of the chatbot, and to assess its influence on interpersonal interactions. Participants indicated that they primarily adopted the chatbot to protect close family members from misleading news. Nevertheless, they experienced mixed feelings due to the chatbot's robotic style and errors in detecting misinformation. We conclude that conversational agents present a promising approach for tackling misinformation, particularly when conversational participants disagree, and offer design recommendations for leveraging AI-enabled conversational agents in countering misinformation.