Aug 2026· Advances in Engineering Innovation· Vol 17, pp. None-None· 0 citations
TL;DR
A generative AI-based system for personalized emotion support, which integrates psychological condition assessment, therapeutic audio recommendation, and intervention outcome evaluation within a prompt-guided and RAG-augmented multi-stage conversation framework, is proposed.
Abstract
Recent advances in generative AI have enabled the development of personalized and interactive user-centered systems. However, its application in the field of mental health intervention remains relatively underexplored. Therefore, this study proposes a generative AI-based system for personalized emotion support, which integrates psychological condition assessment, therapeutic audio recommendation, and intervention outcome evaluation within a prompt-guided and RAG-augmented multi-stage conversation framework. With the assistance of Cursor, an AI programming assistant, the researcher completed the construction of the system. 30 participants were invited to experience and evaluate the system for five days. The evaluation results showed that the system had a relatively high accuracy in identifying users' psychological condition and effectiveness in emotion regulation. However, the system shows limitations in handling subtle emotions. Future work will focus on improving model sensitivity and enhancing system adaptability.
Kizuna is an intelligent affective virtual agent designed to support the practice of resilience-related skills in children through interactive socio-emotional activities. The system combines speech-based interaction, large language model-driven dialogue generation, contextual memory, and virtual companion characters to...
Mariam Janai Martínez-Castro, Arturo Morales-Tellez, J. Martínez-Miranda· Proceedings of the 26th ACM...· 0 citations
This study investigates how Large Language Model (LLM)-based conversational AI and human teacher intervention affect the development of Second Language (L2) Interactional Competence (IC). Employing a two-phase qualitative research design, the study first analyzes interaction texts and reflective journals from five coll...
Ji-Jing Xing· Lecture Notes in Education P...· 0 citations
Mental health interventions use therapeutic techniques to support emotional well-being, often leveraging emerging technologies to improve accessibility and effectiveness. In recent years, tools such as VR and AI have been increasingly used to create immersive and adaptive therapeutic experiences. This paper presents...
Attilio Della Greca, Ilaria Amaro, Paola Barra et al.· Virtual Reality· 0 citations
A growing number of individuals experiencing anxiety and other mental health difficulties require accessible approaches to mental health support. This paper presents a hybrid AI-assisted framework designed as a potential complementary support tool for future therapist-supervised mental health care rather than as a repl...
Artificial Intelligence (AI) and digital media have shown potential in enhancing natural language processing (NLP) and conversational agents capable of simulating empathetic interaction. Cross Reality (CR) refers to applications that interconnect users across different stages of the Reality-Virtuality Continuum, integr...
Hazidi Nur Aqila Natasha, Ismail Ajune Wanis, Ahmad Muhammad Anwar et al.· EPJ Web of Conferences· 0 citations
AffAdapt is presented, a seamless interaction design framework for AI-personas, which coordinates streaming speech recognition, proactive turn-management, persona-grounded response generation, a persistent emotional state, and synchronized embodied output into a single interaction loop.
Nishanth Chidambaram, K. Paliwal, Kayla Hom et al.· 1 citation· ⚡1
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
