000			02807nam a22002417a 4500
003			ft8872
005			20251210140256.0
008			251210b ||||| |||| 00| 0 eng d
041			_aengtag
050			_aT58.5 C36 2025
082			_a..
100	1		_a Camu, Jaspher D.; Peñaredondo, Kiann A
245			_aEmoshown: AI-powered emotional wellness hub with sentiment analysis, anomaly detection, and collaborative filtering
264		1	_a. _b. _cc2025
300			_bCapstone Project: (Bachelor of Science in Information Technology) - Pamantasan ng Lungsod ng Maynila, 2025
336			_2text _atext _btext
337			_2unmediated _aunmediated _bunmediated
338			_2volume _avolume _bvolume
505			_aABSTRACT: This study explores the EmoShown mobile application, designed to enhance emotional wellness through advanced artificial intelligence technologies. With the rising prevalence of mental health issues and the limitations of traditional emotional tracking tools, many individuals lack access to intelligent and responsive support systems capable of detecting emotional changes and providing personalized interventions. EmoShown addresses this gap by integrating three core AI-driven components: sentiment analysis, anomaly detection, and collaborative filtering. The app employs the VADER sentiment analysis algorithm to classify journal entries and emojis into emotional categories, the Isolation Forest model to detect anomalous emotional states, and collaborative filtering with matrix factorization to recommend personalized support activities based on user preferences and behavior. Evaluation of these models was conducted using confusion matrix analyses. EmoShown incorporates the VADER algorithm, achieving an accuracy of 85%, a precision of 0.86, and a recall of 0.85 for sentiment analysis. The anomaly detection feature, powered by Isolation Forest, identifies emotional pattern deviations with an accuracy of 92%, a precision of 0.74, and a recall of 1.0. The collaborative filtering system, utilizing matrix factorization, delivers personalized activity recommendations with an accuracy of 81%, and a precision and recall of 0.81. These results highlight the app’s effectiveness in providing useful information and personalized support. The app fills the gaps in traditional emotional health tools, offering a comprehensive, data-driven approach to mental wellness. By integrating user mood journals, sentiment interpretation, and preference-based recommendations, EmoShown delivers proactive emotional insights and early detection of mental health concerns. Future work will focus on enhancing AI model performance, ensuring robust data privacy, and expanding features to cater to diverse user needs.
526			_aF
655			_aacademic writing
942			_2lcc _cMS
999			_c37318 _d37318