ChatGPT, Loneliness, and Well-Being among International PhD Students in Malaysia: A Mixed-Methods Study

Background: Despite access to university counseling services, many students underutilize them due to cultural stigma, language barriers, and perceived irrelevance. As a result, ChatGPT has emerged as an informal, always-available support system. This study investigates how international PhD students in Malaysia navigate loneliness, mental well-being, and social disconnection through interactions with Generative AI (mainly ChatGPT. Methods: Using a mixed-methods design, the study surveyed 155 international doctoral students and analyzed quantitative responses across four dimensions: loneliness, well-being (WHO-5), perceived social support, and AI-facilitated emotional support. Additionally, open-ended responses were examined using Latent Dirichlet Allocation (LDA) to identify emergent themes. Results: Quantitative findings showed that ChatGPT use was modestly associated with greater loneliness (r = 0.17) and lower perceived social support (r = −0.16), with only a weak positive link to well-being (r = 0.11). Regression analysis confirmed these small effects, while qualitative themes revealed that students used ChatGPT mainly for emotional venting and productivity, underscoring its value as short-term support but also its potential to displace human interaction. More specifically, thematic analysis revealed two dominant student experiences: (1) emotional venting and calmness, and (2) productivity through non-judgmental dialogue. Conclusions: These findings suggest that while ChatGPT offers emotional reprieve and academic clarity, it may also displace human interaction. This study highlights the promise and pitfalls of AI-driven mental support in higher education. It urges institutions to enhance peer networks, foster culturally responsive mentoring, and develop ethical AI usage guidelines to support international doctoral students holistically.