簡易檢索 / 詳目顯示

研究生: 王壽年
Wang, Shou-Nian
論文名稱: 應用多重消極因素分析模型預測部落客的憂鬱傾向
Predicting Blogger's Tendency of Depression Using Multiple Passive Factors Analysis Model
指導教授: 盧文祥
Lu, Wen-Hsiang
學位類別: 碩士
Master
系所名稱: 電機資訊學院 - 醫學資訊研究所
Institute of Medical Informatics
論文出版年: 2011
畢業學年度: 99
語文別: 中文
論文頁數: 64
中文關鍵詞: 憂鬱症憂鬱傾向部落格情緒事件症狀負面想法
外文關鍵詞: Depression, Depression Tendency, Blog, Emotion, Event, Symptom, Negative Thought
相關次數: 點閱:185下載:1
分享至:
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報
  • 大多數的人們會將他們的正面情緒和負面情緒寫進部落格中,本論文的重點在透過分析部落格文章中的負面情緒來預測部落客的憂鬱傾向。本研究提出多重消極因素分析模型(Multiple Passive Factors Analysis Model)和情緒趨勢分析(Emotion Trend Analysis)方法用以判斷部落格作者是否具有憂鬱情緒。我們從痞客邦(PIXNET)收集了大量的部落格文章,用以觀察、訓練與實驗,並且利用中央研究院CKIP斷詞系統做文章斷詞處理。同時我們使用從實際罹患憂鬱症患者和自殺者案例的部落格文章中透過半自動萃取技術抽取負面情緒、觸發事件、症狀和負面想法詞彙做為辭典。四個辭典被運用在多重消極因素分析型的計算中,每一篇部落格文章皆會得到一個情緒分數(Emotion Score)。我們針對每一個部落格使用程式自動繪製情緒趨勢曲線(Emotion Trend Curve),將其所有的情緒分數依照時間序列連成一條情緒分數曲線(Emotion Score Curve)。這種情緒趨勢中出現由低分到高分、持續維持在高分或是高頻率變動的情緒分數可以幫助預測部落格作者是否具有憂鬱傾向。實驗結果證明本研究提出的方法可以明顯判斷實際患有憂鬱症患者部落格和正常人部落格,而在判斷含有憂鬱情緒的部落格方面也具有86.92%的正確性。在未來這項研究期望和專業醫師或醫學專家合作,進一步驗證情緒分數和與其臨界值。另一方面也期望在不久的將來提供線上服務以幫助部落格使用者做憂鬱情緒的自我檢測。

    Most of bloggers write affective articles with their positive or negative emotion in web blogs. This paper focused on analyzing negative emotions in web blogs to predict depression tendency of bloggers. The objective of this paper is to analyze blog posts for bloggers and use the proposed Multiple Passive Factors Analysis Model(MPFA) to predict the depression tendency of bloggers. We collect large amounts of blog posts in Chinese from PIXNET Taiwan. The posts were segmented using Chinese Word Segmentation System with Unknown Word Extraction and POS Tagging from ACADEMIA SINICA. Four categories of terms, including emotion, event, depression symptom related and negative thought, were semi-automatically extracted for each post. The emotion score is calculated for each post by the proposed MPFA model. We design a way of drawing emotion trend curve to present emotion trend of a blogger in a period of time. This emotion trend can help medical experts to predict the depression tendency of a blogger based on the three cases, including negative emotion scores changing from low to high and a duration keeping at high negative emotion score and frequent emotion variation. Experimental results showed that our proposed model is effective to predict bloggers’ depression tendency. The future work of this research is to provide predicted results to doctors or medical experts to verify reasonable negative emotion scores for depression patients and the threshold.

    摘要 IV ABSTRACT VI 誌謝 VIII 第一章 序論 1 1.1 憂鬱的台灣社會 1 1.2 網路社群的發展 1 1.3 研究動機與問題 2 1.4研究方法 3 1.5 研究目標 4 1.6 論文架構 4 第二章 文獻探討 5 2.1 憂鬱症(DEPRESSION) 5 2.1.1 症狀 5 2.1.2 病因 5 2.1.3診斷 6 2.1.4 治療 6 2.1.5 流行病學 6 2.2情緒(EMOTION) 7 2.3 部落格中的情緒辨識 9 2.4 生物心理社會模式(BIOPSYCHOSOCIAL MODEL) 9 2.5 相似目標之研究 10 第三章 方法 11 3.1系統架構 11 3.2 特殊的情緒相關詞典(LEXICON) 12 3.2.1 情緒詞典(EMOTION LEXICON) 14 3.2.2 觸發事件詞典(TRIGGERING EVENT LEXICON) 16 3.2.3 症狀詞典(SYMPTOM LEXICON) 16 3.2.4 負面想法詞典(NEGATIVE THOUGHT LEXICON) 17 3.3 多重消極因素分析模型(MULTIPLE PASSIVE FACTORS ANALYSIS MODEL, MPFA MODEL) 18 3.3.1負面情緒特徵函數(NE FEATURE FUNCTION) 21 3.3.2負面情緒-觸發事件特徵函數(NE-TE FEATURE FUNCTION) 22 3.3.3負面情緒-症狀特徵函數(NE-S FEATURE FUNCTION) 23 3.3.4負面情緒-負面想法特徵函數(NE-NT FEATURE FUNCTION) 24 3.4 情緒趨勢分析 (EMOTION TREND ANALYSIS) 25 第四章 實驗與分析 28 4.1實驗資料和使用技術 28 4.1.1 資料集(DATA SET) 28 4.1.2 使用技術 31 4.2實驗評估 32 4.2.1估計多重消極因素分析模型(MPFA MODEL)特徵函數的權重係數 32 4.2.2評估多重消極因素分析模型(MPFA MODEL)和情緒趨勢分析(EMOTION TREND ANALYSIS) 35 4.3 錯誤分析 48 4.3.1 正確判斷的例子(只探討正確的判斷成正確的) 49 4.3.2 不正確判斷的例子 52 4.4 以程式自動判定的實驗結果與分析 54 4.4.1實驗結果 54 4.4.2結果分析 55 第五章 結論與未來工作 59 5.1結論 59 5.2未來研究方向 59 參考文獻 61

    [1] G.L. Engel, “The need for a new medical model: a challenge for biomedical medicine.” Science, New Series, vol. 196, no. 4286., pp. 129-136, Apr. 8, 1977.
    [2] American Psychiatric Association, Diagnostic and Statistical Manual of Mental Disorders, Fourth Edition - Text Revision (DSMIV-TR), Amer Psychiatric Pub, 2000.
    [3] R. Hirschfeld, “History and evolution of the monoamine hypothesis of depression,” The Journal of Clinical Psychiatry, vol.61, pp.4-6, 2000.
    [4] R.S. Duman, G.R. Heninger, E.J. Nestler, “A molecular and cellular theory of depression,” Arch Gen Psychiatry, vol.54, no. 7 , pp. 597-606, Jul. 1997.
    [5] D. Debanne, N.C. Guérineau, B.H. Gähwiler, S.M. Thompson, “Paired-pulse facilitation and depression at unitary synapses in rat hippocampus: quantal fluctuation affects subsequent release,” The Journal of Physiology, vol.491, no. 1, pp.163-176, 1996.
    [6] P. Videbech, B. Ravnkilde, “Hippocampal volume and depression: A meta-analysis of MRI studies,” American Journal of Psychiatry, vol.161, pp. 1957–1966, Nov. 2004.
    [7] R.L. Carhart-Harris, H.S. Mayberg, A.L. Malizia, D. Nutt, “Mourning and melancholia revisited: Correspondences between principles of Freudian metapsychology and empirical findings in neuropsychiatry,” Annals of General Psychiatry, vol.7:9,July 2008.
    [8] S. Freud, J. Strachey, A. Richards, On Metapsychology: The Theory of Psychoanalysis. Penguin Books, 1984, pp. 251-268.
    [9] V.E. Frankl, Man's search for ultimate meaning. New York, NY, USA: Basic Books, 2000, pp. 139-140.
    [10] A. Maslow, The Farther Reaches of Human Nature. New York, NY, USA: Viking Books, 1971, pp.318.
    [11] E.S. Paykel, J.K. Meyers, M.N. Dienelt, G.L. Klerman, J.J. Lindenthal, M.P. Pepper, “Life events and depression : A controlled study,” Archives of General Psychiatry, vol. 21, no. 6, pp. 753-760, 1969.
    [12] 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.
    [13] P. Cuijpers, A. van Straten, F. Smit, C. Mihalopoulos, A. Beekman, “Preventing the onset of depressive disorders: a meta-analytic review of psychological interventions,” American Journal of Psychiatry, vol.165, pp. 1272–1280, Oct. 2008.
    [14] H. Christensen, K.M. Griffiths, “The prevention of depression using the Internet,” Medical Journal of Australia, vol.177, pp. 122-125, Oct. 2002.
    [15] H. Christensen, K.M. Griffiths, A.F. Jorm, “Delivering interventions for depression by using the internet: randomised controlled trial,” BMJ, vol. 328, no. 7434, Jan. 2004.
    [16] World Health Organization, “Depression,” http://www.who.int/mental_health/management/depression/definition/en.
    [17] Ronald de Sousa, “Emotion,” http://plato.stanford.edu/entries/emotion, 2010.
    [18] W. James, "What Is an Emotion?" Mind, vol. 9, no. 34, pp. 188-205, Apr. 1884.
    [19] Wikipedia, “Cannon–Bard theory,” http://en.wikipedia.org/wiki/Cannon–Bard_theory.
    [20] R. Plutchik, “Emotion: Theory, research, and experience: Vol. 1.” in Theories of emotion, 1, New York: Academic, 1980, pp. 3-33.
    [21] J.A. Russell, “A circumplex model of affect,” Journal of Personality and Social Psychology, vol.39, pp. 1161-1178, 1980.
    [22] R.E. Thayer, The biopsychology of mood and arousal. New York: Oxford University Press, 1989.
    [23] Fractal.org, “The Nature of Emotions by by Plutchik,” http://www.fractal.org/Bewustzijns-Besturings-Model/Nature-of-emotions.htm.
    [24] T.-L. Wu, et al., “Interactive content presentation based on expressed emotion and physiological feedback,” in Proceeding of the 16th ACM international conference on Multimedia. 2008, ACM: Vancouver, British Columbia, Canada, pp. 1009-1010.
    [25] K.H.-Y. Lin, H.-H. Chen, “Ranking reader emotions using pairwise loss minimization and emotional distribution regression,” in Proceedings of the Conference on Empirical Methods in Natural Language Processing. 2008, Association for Computational Linguistics.
    [26] X. Ni, et al., “Exploring in the weblog space by detecting informative and affective articles,” in Proceedings of the 16th international conference on World Wide Web. 2007, ACM: Banff, Alberta, Canada. p. 281-290.
    [27] J. Bar-Ilan, “An outsider's view on "topic-oriented blogging",” in Proceedings of the 13th international World Wide Web conference on Alternate track papers posters. 2004, ACM: New York, NY, USA. pp. 28-34.
    [28] G. Leshed, J.J. Kaye, “Understanding how bloggers feel: recognizing affect in blog posts,” in CHI '06 extended abstracts on Human factors in computing systems. 2006, ACM: Montreal, Canada. pp. 1019-1024.
    [29] C. Yang, K.H.-Y. Lin, H.-H. Chen, “Emotion Classification Using Web Blog Corpora,” in Proceedings of the IEEE/WIC/ACM International Conference on Web Intelligence. 2007, IEEE Computer Society. pp. 275-278.
    [30] C. Yang, K.H.-Y. Lin, H.-H. Chen, “Building Emotion Lexicon from Weblog Corpora,” in Proceedings of ACL-2007, poster, Prague, Czech, pp. 133-136, 2007.
    [31] J. Lafferty, A. McCallum, F. Pereira, “Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data,” in 18th International Conf. on Machine Learning, Morgan Kaufmann, pp. 282–289, 2001.
    [32] S. Cohen, T.B. Herbert, “Health psychology: Psychological factors and physical disease from the perspective of human psychoneuroimmunology,” Annual Review of Psychology, vol. 47, pp. 113-142, 1996.
    [33] A. Baum, D.M. Posluszny, “Health psychology: Mapping biobehavioral contributions to health and illness.” Annual Review of Psychology, vol. 50, pp. 137-163, 1999.
    [34] Y.-P. Huang, T. Goh, C.L. Liew, “Hunting Suicide Notes in Web 2.0–Preliminary Findings,” in 9th IEEE ISM Workshops, 2007.
    [35] T.-T. Goh, Y.-P. Huang, “Monitoring youth depression risk in Web 2.0,” The Journal of Information and Knowledge Management Systems, vol. 39, no. 3, 2009.
    [36] 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.
    [37] 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.
    [38] 廖顯忠,「分析隱含於部落格文章的事件、情緒與需求」,國立成功大學資訊工程所碩士論文,2010。
    [39] 姚迪谷,「設計及發展憂鬱情緒量化評估輔助系統」,國立南台科技大學資訊工程所碩士論文,2008。
    [40] 蔡崇煌、黃素雲。「代謝症候群之生物心理社會模式探討」,家庭醫學與基層醫療,第24卷,第11期。
    [41] 林思恩,「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,2009。
    [42] 張家銘,「EQ殺手 — 認識憂鬱」, http://www.depression.org.tw/knowledge/know_info_part.asp?paper_id=64,2009。
    [43] 財團法人董氏基金會,「憂鬱情緒自我篩檢」, http://www.jtf.org.tw/psyche/melancholia/overblue.asp。

    無法下載圖示 校內:2013-09-05公開
    校外:不公開
    電子論文尚未授權公開,紙本請查館藏目錄
    QR CODE