Unique Presentation Identifier:

P17

Program Type

Graduate

Faculty Advisor

Robin Ghosh

Document Type

Poster

Location

Face-to-face

Start Date

29-4-2025 9:30 AM

Abstract

The growing prevalence of mental health concerns worldwide underscores the urgent need for accessible, scalable, and supportive solutions. Artificial Intelligence (AI) has emerged as a promising tool in this domain, capable of delivering immediate and empathetic interactions to complement traditional methods of mental health care. This project introduces a conversational AI system to assist individuals experiencing mental health challenges. The proposed system is built on a LLaMA model fine-tuned with a dataset of 10,000 mental health-related dialogues; the system leverages advanced natural language processing and machine learning techniques for meaningful engagement. The core functionality of this tool lies in its ability to understand user inputs, retain context across conversations, and offer tailored responses. By utilizing LangChain’s Conversation BufferMemory, the system ensures seamless and personalized conversation flow. Inferencing is managed efficiently through deployment on Ollama, while ethical principles such as user privacy, inclusivity, and sensitivity remain central to its design. This study evaluates the chatbot’s effectiveness in recognizing nuanced user expressions, providing constructive suggestions, and bridging gaps in AI-based mental health support systems. The findings demonstrate the potential integration of mental health care practice while identifying opportunities for further research and refinement to enhance its reliability and impact in real-world applications.

Keywords: Chatbot, LLM, mental health support system

Share

COinS
 
Apr 29th, 9:30 AM

Empowering Mental Support Health through AI Chatbot

Face-to-face

The growing prevalence of mental health concerns worldwide underscores the urgent need for accessible, scalable, and supportive solutions. Artificial Intelligence (AI) has emerged as a promising tool in this domain, capable of delivering immediate and empathetic interactions to complement traditional methods of mental health care. This project introduces a conversational AI system to assist individuals experiencing mental health challenges. The proposed system is built on a LLaMA model fine-tuned with a dataset of 10,000 mental health-related dialogues; the system leverages advanced natural language processing and machine learning techniques for meaningful engagement. The core functionality of this tool lies in its ability to understand user inputs, retain context across conversations, and offer tailored responses. By utilizing LangChain’s Conversation BufferMemory, the system ensures seamless and personalized conversation flow. Inferencing is managed efficiently through deployment on Ollama, while ethical principles such as user privacy, inclusivity, and sensitivity remain central to its design. This study evaluates the chatbot’s effectiveness in recognizing nuanced user expressions, providing constructive suggestions, and bridging gaps in AI-based mental health support systems. The findings demonstrate the potential integration of mental health care practice while identifying opportunities for further research and refinement to enhance its reliability and impact in real-world applications.

Keywords: Chatbot, LLM, mental health support system