Trust Me, I'm Funny: Humor, Personalization, and Trust in Conversational Agents

A Systematic Literature Review on User Engagement, Educational Adoption, and Responsible Use

Brîncoveanu · INFORMATIK 2025, Potsdam, Germany ·

TL;DR: A review of 88 studies on chatbot design, revealing the delicate balance between using humor for engagement and maintaining user trust. As conversational agents become more integrated into sensitive fields like education, their design becomes critically important. Features like humor and personalization can make interactions more engaging, but how do these choices affect user trust and the responsible use of AI?

To investigate this, we conducted a systematic literature review, synthesizing the findings from 88 studies on conversational design. We analyzed how dimensions like humor, proactivity, and personalization impact user engagement, adoption, and perceived credibility.

Our analysis confirms that tailored humor and personalization can significantly enhance user engagement. However, the findings also highlight a crucial challenge: these features are highly context-sensitive and must be carefully managed to respect ethical boundaries and maintain user trust.

The study provides practical recommendations for designing more adaptive and trustworthy conversational agents. It underscores the need to balance engaging features with responsible application, offering a path forward for creating AI that can be effectively and ethically deployed in educational contexts and beyond.

Read the Full Paper