AI-Powered Mental Health Analyser and Personality Mapping System

Abstract

This Paper presents the development of an AI-powered mental health analyser that evaluates personality traits and general well-being by using machine learning algorithms. By analysing user-provided inputs and survey data, the system provides personalised feedback and recommendations to improve mental health. Experimental results demonstrate the model accuracy and potential benefits for user seeking better mental health awareness. Understanding personality traits is key to education, employment and mental health. Experimental results demonstrate the model accuracy. Traditional psychometric approaches take long time and require survey and lack scalable automation. Recent progress in NLP and ML has enabled behaviour patterns to be inferred from linguistic signals. The present study proposes an AI-driven, web-based personality assessment model using sentiment analysis and trait mapping based on OCEAN (Openness, Conscientiousness, Extraversion, Agreeableness, Neuroticism) . Personality traits will be predicted from user-generated text with Python-based backend processing, including models such as Logistic Regression, Random Forest, and BERT.

Introduction

The text presents an AI-powered system for automated personality and mental health assessment, leveraging NLP and machine learning techniques. Traditional personality tests like MBTI, Big Five Inventory, and 16-PF are limited by manual scoring and subjective bias. The proposed system uses language patterns, sentiment analysis, and structural features of user-generated text to predict Big Five (OCEAN) personality traits—Openness, Conscientiousness, Extraversion, Agreeableness, and Neuroticism—while integrating behavioral and biometric data for mental health insights.

The system includes modules such as login, dashboard, questionnaire pages, assessment engine, history, and result visualization. Backend processing uses Python and AI/ML models, while the frontend is built with React.js/Flutter/HTML-CSS, and data storage employs MySQL or MongoDB for secure record-keeping. Users receive real-time feedback on their mental health and personality, with visualizations such as mood trends and radar charts, and abnormal patterns trigger alerts.

Methodology highlights:

• Data collection combines text, speech, and IoT-based biometric inputs.

• AI/ML and NLP algorithms map personality traits and emotional states.

• Dynamic Big Five questionnaires assess personality; mental health screening evaluates depression, anxiety, and stress.

• Local processing ensures privacy, avoiding external cloud sharing.

Results and discussion:

• The system accurately identifies stress, anxiety, and depression using combined physiological and language data.

• Provides real-time, actionable feedback, enhancing user awareness and engagement compared to static assessments.

• The approach is scalable, affordable, and applicable to healthcare, education, and personal use.

• Challenges include data diversity, algorithm improvement, and privacy management.

Conclusion

The Psyche Compass project demonstrated how advanced AI combined with sensor technologies could be integrated into mental health systems to provide users with actionable feedback and provide real-time analyses. Additional research is necessary due to the availability of larger datasets, stronger features, and clinical validation.

References

[1] In 2024, Tseng et al. published a study on Mind-Me, an artificial intelligence personality assessment tool. The journal\'s scientific publications were published in Multimedia Tools and Applications 83.12: 35943-35955. [2] Goyal, Shanky, and colleagues developed a mental health assessment tool called Mind-Lift that uses artificial intelligence for students. Neuroscience Informatics 2025: 100208. [3] Saxena and Shivya (2017).AI in personality assessment and writing. [4] A survey on Artificial Intelligence\'s application to the study of personality traits and disorders in social media. By Ellouze, Mourad, and Lamia Hadrich Belguith. pp. [5] The ACM Transactions on Asian and Low-Resource Language Information Processing (2024). Shatte, A. B, Hutchinson, D. M, Teague, S. J. [6] Psychological Medicine, 49(9), 1426-1448 (2018): A scoping analysis of machine learning in mental health.

Copyright

Copyright © 2025 Mayur Pillewan, Nehal Lekurwale, Prince Soni, Shreyash Maske, Jitu Patankar, Om Shastrakar, Prattyush Banerjee, Sagar Raut. 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.