Emoshown: AI-powered emotional wellness hub with sentiment analysis, anomaly detection, and collaborative filtering

By: Camu, Jaspher D.; Peñaredondo, Kiann A
Language: English Publisher: . . c2025Description: Capstone Project: (Bachelor of Science in Information Technology) - Pamantasan ng Lungsod ng Maynila, 2025Content type: text Media type: unmediated Carrier type: volumeGenre/Form: academic writingDDC classification: .. LOC classification: T58.5 C36 2025
Contents:
ABSTRACT: 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.
Tags from this library: No tags from this library for this title. Log in to add tags.
    Average rating: 0.0 (0 votes)

ABSTRACT: 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.

Filipiniana

There are no comments for this item.

to post a comment.

© Copyright 2024 Phoenix Library Management System - Pinnacle Technologies, Inc. All Rights Reserved.