情感分析為基礎之行動個人化情緒管理系統之設計與評估

Design and Evaluation of Personalized Emotion Management System Based on Sentiment Analysis

林靖雅(Jing-Ya Lin)

指導教授 ： 王淑玲

國立臺中科技大學/資訊與流通學院/資訊管理系碩士班/碩士(2020年)

摘要

隨著行動科技與網際網路技術的迅速發展，運用行動心智健康照護系統來支持個人化心智健康照護已逐漸受到重視。本研究希望幫助使用者做好個人化情緒照護，運用深度學習、以及情感分析技術來發展互動式的個人化情緒照護功能，目標在輔助使用者做好日常自我情緒管理照護。另一方面，本系統依據認知行為治療(CBT)架構，建立個人情緒歷程記錄功能，可作為使用者進一步接受心理諮商或治療之參考資訊，有助於增進專業人員診療的效能。具體而言，本研究首先發展一套雛型「個人化情緒管理系統」，透過智能情緒互動服務、情緒量表以及記錄每天的生活點滴，與分析使用者日常的情緒歷程，並透過社群平台提供給使用者適當的衛教資訊。本研究並進一步結合健康信念模型(Health Belief Model,HBM)及科技接受模型(Technology Acceptance Mode, TAM)建立研究模型，並藉由所建立的研究模型評估使用者對於個人化情緒管理系統的使用意圖。本研究結果顯示受試者認同本系統所提供之功能可輔助使用者情緒健康照護。本研究之模型評估測試結果顯示，大多數構面對於提升使用者的使用意圖均有顯著影響效果。透過本研究結果顯示受試者認同於行動個人化情緒管理系統對於使用意圖具有正向顯著影響效果。

關鍵字

行動心智健康照護 ； 情感分析 ； 深度學習 ； 認知行為治療(CBT) ； 健康信念模型(Health Belief Model, HBM)

並列摘要

With the rapid development of mobile technology and Internet technology, the application of mobile mental healthcare system to support personalized mental health care has been paid more and more attention. This study intents to aid users for personalized emotional healthcare appropriately. This study applies machine learning, emotional analysis technology to implement an interactive personalized emotional healthcare function, the goal is to assist users in daily self-emotional management healthcare. In particular, the system according to cognitive behavioral therapy (CBT) architecture, designed a personal emotional process recording function for further counseling or treatment aiding information and help to enhance the effectiveness of professional diagnosis and treatment. Especially, this study develops a prototype system
"personalized emotion management system" to record and analyze the user's daily emotional journey through intelligent emotional interaction services, emotional scales and daily mood diaries, and to provide users with appropriate healthcare information through community platforms. Finally, this study combines the Health Belief Model (HBM) and the Technology Acceptance Model (TAM) to build a research model and applies the research model to evaluate the user's intent to use a personalized emotion management system. The results show that subjects assent that the system can aid users to prevent emotion problems. After evaluation by the research model, most of the research Facets has a significant effectiveness on intention to use. Through the personalized emotion management system of this study, it can improve mental health care and prevention effectiveness.

並列關鍵字

Mobile emotion healthcare ； Sentiment Analysis ； Deep Learning ； Cognitive Behavioral Therapy ； Health Belief Model

參考文獻

Diener, E., Suh, E. M., Lucas, R. E., & Smith, H. L. (1999). Subjective well-being: Three decades of progress. Psychological bulletin, 125(2), 276-302.

Agrebi, S., & Jallais, J. (2015). Explain the intention to use smartphones for mobile shopping. J. Retailing Consum. Serv., 22, 16-23.

Ajzen, I.(1991). The Theory of Planned Behavior. Organizational Behavior and Human Decision Processes, 50, 179-211.

Alpaydin, E. (2014). Introduction To Machine Learning,Third Edition. The MIT, 49-64.

Anthes, Emily. (2016). Mental health: there's an app for that. Nature, 532 (7597), 20-23.