Is AI mingling or bullying me? Exploring User Interactions with a Chatbot in China

TL;DR

This study investigates how an autonomous social chatbot in China influences human interactions online, revealing complex emotional dynamics and societal implications of unsolicited AI engagement in digital discourse.

Contribution

It introduces a novel analysis of unsolicited, autonomous AI comments in social media, highlighting their impact on human-AI emotional and social interactions.

Findings

Chatbot intervenes in public discourse with six key themes.

Interactions evoke warmth, humor, but also covert hostility.

AI's social presence often falls short of emotional needs.

Abstract

Since its viral emergence in early 2024, Comment Robert-a Weibo-launched social chatbot-has gained widespread attention on the Chinese Internet for its unsolicited and unpredictable comments on user posts. Unlike conventional chatbots that respond only to user prompts, Robert autonomously intervenes in public discourse, representing a novel form of AI-driven social media engagement. This study examines how such autonomous, algorithmic communication reshapes human-AI interaction in everyday online contexts. Using computational linguistics techniques, including topic classification and sentiment analysis, we analyze over 3,900 user-submitted interactions from the "Robert Victims Alliance", a grassroots community documenting their exchanges with the chatbot. Topic modeling reveals six key themes: interpersonal relationships, self-identity, academic and career concerns, subcultures, sensitive topics, and social events. Complementing this, mixed-methods emotional analysis uncovers a complex affective spectrum: Robert's casual remarks can evoke warmth and humor but may also conceal covert hostility beneath neutral or polite language. These ambivalent interactions reveal an emerging emotional divide between humans and socially proactive AI, suggesting that while Robert simulates social presence, it often falls short of users' emotional needs. Our study contributes to human-AI interaction research by offering new insights into the affective dynamics and socio-technical implications of unsolicited AI bots' participation in digital public spheres.