A Hybrid Response Generation Model for an Empathetic Conversational Agent

Research on the use of conversational agents or chatbots to provide alternative and accessible mental health interventions has gained much interest in recent years. Designed to engage human users through natural and empathetic conversations, these chatbots have shown their potential applications in pre-emptive healthcare that emphasizes the importance of helping individuals maintain their optimal mental health and well-being. However, the use of rule-based or retrieval-based models limit the chatbots' abilities in processing user input and generating relevant and empathetic responses to dynamically adapt to the context of a conversation. Neural-based generative models, currently applied in open-domain dialogue and text generation systems, may be able to address the limitations of retrieval-based models. In this paper, we present VHope (Virtual Hope), a conversational agent that combines retrieval-based and generative models to perform its role as a therapist capable of generating empathetic responses to enrich the conversation. The best performing generative model, derived from training DialoGPT with the EmpatheticDialogues dataset and a local mental well-being dataset, yielded a perplexity score of 9.977. Results from experts' evaluation of the conversation logs showed that the responses generated by VHope were 67% relevant, 78% human-like, and 79% empathic. These results further support the idea of modelling complex conversations with ease by using a neural model and a task-specific dataset. Future improvements may include the use of larger, human-based empathetic dataset for enhanced retrieval model's conversation design and generative model's fine-tuning.