隨著網路科技的演變，越來越多人在網路上發表個人生活記事的言論，本論文的重點在於透過分析網路使用者所撰寫文章的壓力事件、負面情緒、症狀與負面行為特徵來預測憂鬱傾向。研究中所提出的壓力事件導向模型(Stressful Life Event-Driven Model)即是用以判斷網路使用者是否有憂鬱傾向。分析台大知名BBS站(PTT)的憂鬱症版(Prozac)的使用者文章，用以觀察與訓練，並利用中央研究院CKIP斷詞系統做文章斷詞處理。利用各特徵值計算一段時間區間內文章的憂鬱傾向分數值，對照心理學專家的標記結果當成判斷的依據，便可協助預測網路使用者的憂鬱傾向。針對壓力事件的擷取，我們主要是參照臨床在壓力事件評估所用到的兩個量表，包括社會再調適量表(Social Readjustment Rating Scale)及日常瑣事量表(Hassles Scale)。然後整理成問卷進行調查，以此判斷各壓力事件對於網路使用者的影響程度，並利用HowNet知識庫來擴展相關的壓力事件詞，由實驗結果可以發現擴展的詞彙對於整體的效能有顯著的幫助。而與其他評估準則的預測效能相比，本研究的整體憂鬱傾向預測效能也要來得好。

With the evolution of Internet technology, more and more people begin to post their story or daily on the blog, micro blog or Twitter. The purpose of this paper is to predict web authors’ depression tendency by analyze stressful life event, negative emotion, symptom and negative behavior in their posts. In this work, Stressful Life Event-Driven Model is introduced to determine web authors whether they have depression tendency. We collected and analyzed web articles from the Prozac Board of a well-known BBS site (PTT) constructed by Taiwan University. The articles were segmented and labeled by using Chinese Word Segmentation System with Unknown Word Extraction that developed by ACADEMIA SINICA. We combine Social Readjustment Rating Scale, Hassles scale and HowNet knowledge base to extract stressful life event lexicon. The depression tendency score was calculated. Thus we could predict web authors’ depression tendency. The final result shows the precision, recall, and F-measure is about 61% and the performance of proposed model is better than other baseline model.

[1]American Psychiatric Association, Diagnostic and Statistical Manual of Mental Disorders, Fourth Edition - Text Revision (DSMIV-TR), Amer Psychiatric Pub., 2000
[2]AMERICAN PSYCHOLOGICAL ASSOCIATION(2012), “Hard-hitting hormones: The stress-depression link”, http://sciencenordic.com/how-stress-can-cause-depression
[3]AMERICAN PSYCHOLOGICAL ASSOCIATION(2011), ”The Impact of Stress”, http://www.apa.org/news/press/releases/stress/2011/impact.aspx
[4]Alan H.S, Chan, K. Chen, Elaine Y.L. Chong, “Work Stress of Teachers from Primary and Secondary Schools in Hong Kong”, International MultiConference of Engineers and Computer Science , 2010
[5]Cohen, T. Kamarck & R. Mermelstein , “A global measure of perceived stress”, Journal of Health and Social Behavior 24 (4): 385–396., 1983
[6]Dong Zhendong, Dong Qiang(1999-2013), “HowNet Knowledge DataBase”, http://www.keenage.com/
[7]Elkan C., Log-linear models and conditional random field, CIKM 2008
[8]Hsieh-Cheng Chiang, ” Automatic Capture and Detect Blog Message of Suicidal Ideation”, Thesis of Institute of Information Management, Yuan Ze University, 2011
[9]Holmes TH, Rahe RH, “The Social Readjustment Rating Scale”, J Psychosom Res 11 (2): 213–8., 1967
[10]Jorn Bakker, Rafal Kocielnik, Mykola Pechenizkiy, Natalia Sidorova, Leszek Holenderski, “Stess@work: From Measuring Stress to its Understanding,Prediction and Handling with Personalized Coaching”, Proceedings of the 2nd ACM SIGHIT International Health Informatics Symposium Pages 673-678, 2012
[11]Mykola Pechenizkiy, Jorn Bakker, Natalia Sidorova, “What’s your current stress level? Detection of stress patterns from GSR sensor data”, IEEE 11th International Conference on Data Mining Workshops Pages 573-580, 2011
[12]Po-Ming Su., “Predicting Web User’s Tendency of Depression Using Event-Driven Negative Emotion Model”, Thesis of Institute of Medical Informatics, National Cheng Kung University,2012
[13]P. G. Holeyannavar, S. K. Itagi, “Stress and Emotional Competence of Primary School Teachers”, Kamla-Raj 2012 Enterprise J Psychology , 3(1): 29-38, 2012
[14]Pastorino, E. & Doyle-Portillo, S., “What is Psychology?. 2nd Ed.”, Belmont, CA: Thompson Higher Education., 2009
[15]R. Jay Turner and Blair Wheaton, “Checklist Measurement of Stressful Life Events”, Measuring Stress-A Guide for Health and Social Scientists: pp.29-32,1995
[16]R. Plutchik, “Emotion: Theory, research, and experience: Vol. 1.” in Theories of emotion, 1, New York: Academic, 1980,pp. 3-33.
[17]Rafal Kocielnik, Mykola Pechenizkiy, Natalia Sidorova, “Stress Analytics in Education”, Poster presented at Proceedings of the 5th International Conference on Educational Data Mining, 2012
[18]Shou-Nian Wang., ”Predicting logger’s Tendency of Depression Using Multiple Passive Factors Analysis Model”, Thesis of Institute of Medical Informatics, National Cheng Kung University, 2011
[19]Sheldon Cohen, Ronald C. Kessler, and Lynn Underwood Gordon, “Strategies for Measuring Stress in Studies of Psychiatric and Physical Disorders”, Measuring Stress-A Guide for Health and Social Scientists: pp.3-5,1995
[20] Ti-Ku ,Yao , ” Design and Develop an Assistant System for Depression Quantization and Estimation”, Thesis of Institute of Computer Science and Information Engineering, Southern Taiwan University of Science and Technology, 2008
[21]Tiong-Thye Goh and Yen-Pei Huang,” Monitoring youth depression risk in Web 2.0”, The journal of information and knowledge management systems, 2009
[22]W.-H. Lu, R.S.-J. Lin,Y.-C. Chan, K.-H. Chen, “Overcoming Terminology Barrier Using Web Resources for Cross-Language Medical Information Retrieval,” in AMIA Annu Symp Proc. 2006, vol. 2006, pp. 519–523.
[23]Wikipedia(2012), ”Power low”, http://en.wikipedia.org/wiki/Power_law
[24]W.-H. Lu, S.-J. Lin,Y.-C. Chan, K.-H. Chen, “Semi-Automatic Construction of the Chinese-English MeSH Using Web-Based Term Translation Method,” in AMIA Annu Symp Proc. 2005, vol. 2005, pp. 475–479.
[25]WebMD(2011),“Stress and Depression”, http://www.webmd.com/depression/features/stress-depression
[26]Wikipedia(2012),”Stressor”, http://en.wikipedia.org/wiki/Stressor#cite_note-1
[27]World Health Organization, “The International Statistical Classification of Diseases and Related Health Problems 10th Revision (ICD-10)”, http://apps.who.int/classifications/apps/icd/icd10online, 2007
[28]林思恩(2009), 「東亞七國快樂指數 香港倒數第二 台灣人最不快樂」, http://www.gospelherald.com.hk/news/soc_1311.htm
[29]陳盤銘, 「壓力管理及相關疾病與治療」, 人文社會學報 第三期 2007年3月號