Personalized Mental Well-Being & Lifestyle Insight App for College Students

Abstract

College students today often face stress, low motivation, and unhealthy lifestyle habits that affect their overall well-being. Many existing mental health apps are complex or attempt diagnosis, which can be unsafe without professional support. This project proposes a Personalized Mental Well-Being and Lifestyle Insight Application that provides a simple, safe, and non-diagnostic platform for students. The app allows users to track their mood through weekly check-ins, monitor lifestyle habits, and select activities that make them happy. Based on this data, it generates personalized suggestions using a rule-based approach and offers motivational support through a chatbot. The system focuses on privacy, simplicity, and ethical design, making it a practical solution to help students better understand and improve their well-being.

Introduction

The project presents MindMate, a personalized mental well-being and lifestyle insight application designed specifically for college students. Recognizing that students frequently experience stress, poor sleep, low motivation, and unhealthy routines, the system aims to support well-being through awareness and positive lifestyle changes rather than diagnosing mental health conditions.

Initially planned as an AI-based emotion detection system using video, audio, and text analysis, the project was redesigned after consultation with mental health professionals due to concerns about reliability, ethics, and safety. Instead, MindMate adopts a non-diagnostic, rule-based approach that focuses on mood tracking, lifestyle monitoring, and personalized recommendations.

The application allows users to complete weekly mood check-ins, track habits such as sleep, exercise, and daily activities, and select personal happiness activities. Based on this information, a rule-based insight engine generates safe, personalized suggestions to encourage healthier behaviors and improved self-awareness. The platform emphasizes privacy, transparency, and user consent while avoiding harmful scoring systems or medical judgments.

The system follows a layered architecture consisting of a Flutter-based mobile application, backend services using FastAPI/Node.js, Firebase Firestore for data storage, Firebase Authentication for secure access, a rule-based recommendation engine, an NLP-enabled chatbot, and a React.js admin dashboard displaying only anonymous aggregated trends. The chatbot provides motivational and supportive interactions using sentiment detection and keyword-based responses.

The workflow includes user authentication, consent collection, mood assessment, lifestyle tracking, data storage, insight generation, chatbot interaction, and anonymous institutional analytics. The methodology prioritizes simplicity, ethical design, personalization, and privacy. Mood data, lifestyle information, and user-selected activities are analyzed using predefined rules rather than complex AI models, ensuring explainability and safety.

Evaluation results indicate that users found the application easy to use due to its emoji-based interface, sliders, and minimal typing requirements. The system successfully tracked mood and lifestyle patterns, generated useful personalized suggestions, and provided supportive chatbot interactions. Users appreciated the absence of diagnostic features and scoring systems, which increased trust and comfort.

Technically, MindMate is implemented using Flutter, Firebase Firestore, Firebase Authentication, and the Llama 3.1 8B Instant model hosted on Groq Cloud for chatbot functionality. A rule-based crisis detection system scans messages for risk indicators before AI processing, ensuring safer interactions. Overall, the project demonstrates a practical, ethical, privacy-focused, and student-centered approach to promoting mental well-being through self-awareness and healthy lifestyle improvements.

Conclusion

This project presents a Personalized Mental Well-Being and Lifestyle Insight Application designed specifically for college students. The system focuses on providing a simple, safe, and non-diagnostic platform to help users understand their mood and daily habits without creating pressure or making medical judgments. By integrating weekly mood assessment, lifestyle tracking, and personalized happiness activities, the application offers meaningful insights through a rule-based recommendation system. The inclusion of a chatbot further enhances user engagement byproviding motivational and supportive interactions. Unlike many existing applications, this system avoids complex analytics and scoring, ensuring a positive and non-judgmental user experience. It also prioritizes user privacy and security by using consent-based data collection and anonymous data analysis for the admin dashboard. Overall, the project demonstrates that a user-friendly and ethically designed solution can effectively support student well-being. It provides a strong foundation for future enhancements while maintaining a balance between technology, simplicity, and mental health safety

References

[1] World Health Organization, “Mental Health: Strengthening Our Response,” 2022. [Online]. Available: https://www.who.int [2] American Psychiatric Association, “Mental Health Apps and Their Use,” 2021. [3] Google, “Google Fit API Documentation.” [Online]. Available: https://developers.google.com/fit [4] Google Firebase, “Firebase Documentation: Authentication and Firestore.” [Online]. Available: https://firebase.google.com/docs [5] S. Bird, E. Loper, and E. Klein, “Natural Language Toolkit (NLTK),” 2009. [Online]. Available: https://www.nltk.org/ [6] D. Jurafsky and J. H. Martin, Speech and Language Processing, 3rd ed., 2023. [7] A. F. Shatte, D. M. Hutchinson, and S. J. Teague, “Machine Learning in Mental Health: A Review,” Journal of Medical Internet Research, 2019. [8] J. E. Bardram, “Mobile and Wearable Technologies for Mental Health,” IEEE Pervasive Computing, 2020. [9] Kaggle, “Datasets and Machine Learning Resources,” [Online]. Available: https://www.kaggle.com/

Copyright

Copyright © 2026 Akanksha Chodankar, Rujuta Patil, Gunjan Karekar, Prerana Jadhav, Gayatri Machale. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.