Background: Mental health disorders among college students have surged in recent years, exacerbated by barriers such as stigma, cost associated with treatment, and limited access to mental health providers. Artificial intelligence (AI)-driven chatbots have emerged as scalable, stigma-free tools to deliver evidence-based mental health support, yet their efficacy specifically for college populations remains underexplored.

Objective: This systematic rapid review evaluates the effectiveness of chatbots in improving mental health outcomes (e.g., anxiety, depression) and well-being among college students while identifying key design features and implementation barriers.

Methods: Four databases (PubMed, PsycInfo, Applied Science & Technology Source, ACM Digital Library) were searched for studies published between 2014 and 2024. Two reviewers independently screened articles using predefined PICO criteria, extracted data and assessed quality via the PEDro scale. Included studies focused on chatbot interventions targeting DSM-5-defined mental health conditions or well-being in college students.

Results: Nine studies (n=1,082 participants) were included, with eight reported statistically significant improvements in anxiety (e.g., GAD-7 reductions), depression (e.g., PHQ-9 scores), or well-being. Effective chatbots frequently incorporated cognitive-behavioral therapy (CBT), daily interactions, and cultural personalization (e.g., 22% depression reduction with Woebot; p<0.05). However, heterogeneity in study quality (PEDro scores: 1-7), high attrition rates (up to 61%), and reliance on self-reported outcomes limited generalizability.

Conclusions: Though the use of chatbots for the improvement of mental health and well-being is promising based on the review's results, future research should prioritize rigorous RCTs, standardized outcome measures (e.g., PHQ-9, GAD-7), and strategies to improve attrition.