Explore publications.

University students commonly undergo activities in their educational and social environments that may affect their psychological adjustment. Emotional Intelligence (EI) acts as a protective component in preventing psychological adjustment difficulties. Hopelessness acts as a risk factor in the dimension of psychological adjustment. Little research exists in the context of Bangladesh in the intersection of EI and hopelessness. The present research aimed to explore the effects of EI and hopelessness in predicting psychological adjustment of the students at Chittagong University. A cross-sectional survey design was adopted. A total of 100 students aged 18-25 years old, comprising 50 men and 50 women selected randomly from different departments/institutes of Chittagong University. Data was gathered utilizing a Personal Information Form (PIF), Bangla version of the EI Scale (EIS), Hopelessness Scale (BHS), & Bangla Adult Personality Assessment Questionnaire (PAQ). SPSS 16.0 was used to perform the analysis of the information gathered. The inferential statistics revealed moderate to high levels of EI (M = 129.07, SD = 12.84) but low levels of hopelessness (M = 4.55, SD = 3.51) and moderate levels of psychological adjustment (M = 137.28, SD = 25.00). There was a negative correlation between EI measures of hopelessness (r = -.54, p < 0.01) and psychological adjustment (r = -.67, p < 0.01) but a positive association between hopelessness and psychological adjustment (r = 0.50, p < 0.01). Using the regression analysis, psychological adjustment was significantly predicted by the measures of EI (β = -.56, p < 0.01) but hopelessness (β = 0.19, p < 0.05) when taken together explaining 47% of the total variability of psychological adjustment (R² = 0.47, p < 0 EI serves as a protective factor for psychological adjustment in university students, while hopelessness serves as a risk factor for the psychological adjustment of university students. These factors may influence the enhancement of psychological adjustment.

The growing prevalence of mental health issues, particularly depression and suicidal thoughts, points to the need to develop automated tools capable of detecting such sentiments from online communication. This study addresses some critical challenges by introducing a novel sentiment analysis framework for Bangla text, aimed at classifying content into non-depressive, depressive, and suicidal categories. We propose a hybrid deep learning model leveraging the strengths of transformer-based architectures, designed to manage long textual sequences effectively, a critical aspect in the context of natural language processing. Our model integrates RoBERTa (Robustly Optimised BERT Pre-Training Approach) with a Self-Attention Network (SAN), creating a synergistic framework for nuanced sentiment detection in Bangla social media posts, comments, and articles. This method addresses the scarcity of Bangla specific datasets by utilising a dataset curated for the study. The results demonstrate the superiority of our model, achieving an accuracy of 82.58%, alongside precision, recall, and F1-scores of 82%. Subsequently, it emphasises the potential for the proposed model to support early identification of mental health concerns, thereby enabling timely interventions and contributing to mental health awareness and prevention efforts. In the future, deploying the model as a real-time chatbot or browser extension could scan Bangla social media for depressive, non-depressive, and suicidal content and alert professionals to the risk factors.