ComPeer: A Generative Conversational Agent for Proactive Peer Support

TL;DR

ComPeer is a generative conversational agent designed for proactive peer support, leveraging large language models to detect key events and strategically engage users, thereby enhancing long-term engagement and support effectiveness.

Contribution

This paper introduces ComPeer, a novel proactive peer support chatbot that uses large language models to adaptively initiate support, unlike prior rule-based or user-initiated systems.

Findings

ComPeer increased user engagement over a one-week period.

It effectively detected significant dialogue events for timely support.

Users reported higher satisfaction with ComPeer's proactive approach.

Abstract

Conversational Agents (CAs) acting as peer supporters have been widely studied and demonstrated beneficial for people's mental health. However, previous peer support CAs either are user-initiated or follow predefined rules to initiate the conversations, which may discourage users to engage and build relationships with the CAs for long-term benefits. In this paper, we develop ComPeer, a generative CA that can proactively offer adaptive peer support to users. ComPeer leverages large language models to detect and reflect significant events in the dialogue, enabling it to strategically plan the timing and content of proactive care. In addition, ComPeer incorporates peer support strategies, conversation history, and its persona into the generative messages. Our one-week between-subjects study (N=24) demonstrates ComPeer's strength in providing peer support over time and boosting users' engagement compared to a baseline user-initiated CA.