Abstract:
Traditional psychological assessments for childhood trauma and personality prediction often suffer from bias and inconsistency. This research explores the use of AI and machine learning to develop more objective and accurate diagnostic models. By leveraging advanced ML algorithms, this research proposal aims to enhance mental health evaluations and improve intervention strategies. This research utilized machine learning algorithms such as gradient boosting model, K-nearest neighbors, Liner Regression, Randomforest, SVM in developing objective, scalable, and data-driven models to detect childhood trauma and predict personality traits. This study used Childhood Trauma Questionnaire (CTQ) and the Big Five Inventory 2 Short Form (BFI-2-S) to gather psychological and behavioral information from young adults aged 18–22. Feature selection was done used to optimize model performance. The predictive accuracy was assessed with the help of F1-score, Confusion matrix, MAE, RMSE as the evaluation metrics. This research finding was be quite useful for diagnostics in mental health by enabling precise and early detection of psychological problems and providing personal interventions in mental health. The contribution of this study to the development of psychological assessments is by introducing AI-driven assessments, therefore making mental health support more reachable, effective, and impartial.
