成功大學博碩士論文系統

簡易檢索 / 詳目顯示

回結果列表

研究生：	黃彥軒 Huang, Yen-Shuan
論文名稱：	應用負面想法憂鬱模型預測網路使用者憂鬱傾向 Predicting Web User’s Tendency of Depression Using Negative Thought-Driven Depression 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：	2015
畢業學年度：	103
語文別：	英文
論文頁數：	100
中文關鍵詞：	憂鬱症、憂鬱傾向、負面想法、負面情緒、症狀
外文關鍵詞：	Depression, Depression Tendency, Negative thought, Negative Emotion, Symptom
相關次數：	點閱：125 下載：6
分享至:	分享至facebook 分享至twitter

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

　　憂鬱症已成為近代社會中的問題了。人們可能會注意自己的身體健康，但精神健康就很少關心。在2012年10月9號出版的報告，世界衛生組織以斗大的標題寫著：憂鬱症是全球危機。由此可見，憂鬱症已經是全球關心的議題之一。如今，網路已成社會的縮影。隨著行動網路和裝置越來越流行，人們開始會把各式各樣的東西放在網路上，例如：想法、心情、感覺和各種瑣事等等。而我們可以在網路上找尋這類的文章，給有憂鬱傾向的作者一些提醒和即時的幫助。
　　在本論文中，我們提出了以負面想法導向憂鬱的模型（NTDM）來預測憂鬱傾向。我們希望可以找到憂鬱症徵兆的人而不是要診斷是否有憂鬱症。因此，我們參考了憂鬱症的診斷標準和憂鬱症的量表來得到我們所要的憂鬱症特徵。我們使用了負面想法、負面情緒和症狀來作為我們判斷憂鬱傾向的特徵。此外，我們建立了三個辭典來給模型使用，分別是負面想法辭典、負面情緒情辭典和症狀辭典NTDM是預測單一文章的憂鬱傾向，我們還提出了NTDMlong用來預測長時間的文章。我們從知名的BBS站(PTT)收集文章來觀察、訓練和實驗。我們也把這些文章給專家標記是否有憂鬱傾向。
　　實驗結果顯示，我們的模型比起蘇柏鳴提出的應用事件導向負面情緒模型(ENDE)和王壽年題提出的多重消極因素分析模型(MPFA)來的好。這證明了著重於負面想法的模型是有助於找出憂鬱傾向的文章，甚至可能會比著重於負面情緒的模型來的好。

　　Melancholia is problem in recent society. People probably will pay attention to physical heath but mental health. WHO said “DEPRESSION: A Global Crisis” in October 9 2012. Depression is a global public health concern. Nowadays, network already is a society of microcosm. With mobile network become popular, people prefer to post something on the internet, including thinking, mood, feeling and trifles. However, we want to mine article on web and find who has depression tendency, that we can remind the author and give immediately treatment.
　　In this work, we propose a Negative Thought-Driven Depression Model (NTDM) to predict depression tendency. We find sign of depression and the goal is not diagnose depression. Therefore, we refer to diagnostic criteria and depression scale for finding features of depression. We use negative thought, negative emotion and symptom to predict depression tendency. Furthermore, we build three lexicons for NTDM, there are negative thought lexicon, negative emotion lexicon and symptom lexicon. NTDM to predict depression tendency for single article. We also propose NTDMlong to predict depression tendency for long term articles. We collected some user’s articles from a well-known BBS station (PTT), to observe, train and experiment. These articles also were labeled depression tendency by experts.
　　The experiment results showed the performance by using our model was better than using ENDE model and MPFA model. We get conclusion that identifies the major negative thought to predict depression tendency is helpful, even better than the model of major negative emotion.

摘要	III
Abstract	V
致謝	VII
Table of Contents	VIII
List of Tables	X
List of Figures	XII
Chapter 1	Introduction	1
1	Research Background	1
1.1	The invisible killer in society	1
1.2	The social networks in web	2
2	Problem and Motivation	2
3	Research Target	5
4	Research Method	5
5	Organization of this Dissertation	6
Chapter 2	Related Research	7
1	Depression	7
1.1	Diagnostic Criteria	7
1.2	Depression scale	8
2	Negative thought (thinking)	12
3	Emotion	12
4	ABC Theory of Emotion	13
5	Similar target of research	15
Chapter 3	Method	16
1	Framework of system	16
2	Features of Depression	17
3	Lexicon	18
3.1	Negative Thought Lexicon	19
3.2	Negative Emotion Lexicon	23
3.3	Symptom Lexicon	26
4	Negative Thought-Driven Depression Model	27
5	Feature Function	30
5.1	N-Thought Feature Function	31
5.2	Thought-Emotion Feature Function	33
5.3	Thought-Symptom Feature Function	34
6	Predicting long term depression tendency	35
Chapter 4	Experiments and Analysis	37
1	Dataset	37
2	Evaluation Metrics	38
3	Experiments of coverage with Lexicons	40
3.1	Parameter Selection	40
3.2	Results of Experiments	40
4	Experiments of Depression Tendency with different Lexicon	43
4.1	Parameter Selection	43
4.2	Results of Experiments	43
5	Experiments of Depression Tendency with different model	54
5.1	Parameter Selection	54
5.2	Results of Experiments	55
6	Experiments of Depression Tendency with NTDMlong	67
6.1	Dataset for two week articles	67
6.2	Threshold for NTDMlong	69
6.3	Baseline	70
6.4	Results of Experiments	70
7	Example of positive article	73
7.1	Example of positive single article	73
7.2	Example of positive two week articles	78
8	Example of negative article	85
8.1	Example of negative single article	85
8.2	Example of negative two week articles	87
9	Discussion of Experiments	93
Chapter 5	Conclusions and Future Works	95
1	Conclusions	95
2	Future Works	96
Reference	97

                                    

[1] Gromov, Gregory R. The roads and crossroads of Internet history. The WWW Consortium, 1996.
[2] AMERICAN PSYCHIATRIC ASSOCIATION, et al. DSM 5. American Psychiatric Association, 2013.
[3] John Tung Foundation. The develop of Adolescent Depressive Mood Self-Detecting Scale (ADMSS) and it’s reliability, validity and index scores. Taipei: John Tung Foundation, 2006.
[4] Beck, Aaron T.; STEER, Robert A.; BROWN, Gregory K. Beck Depression Inventory. 2005.
[5] Hamiltom, Max. Rating depressive patients. Journal of Clinical Psychiatry, 1980.
[6] Belmaker, R. H.; AGAM, Galila. Major depressive disorder. New England Journal of Medicine, 2008, 358.1: 55-68.
[7] WORLD HEALTH ORGANIZATION, et al. The ICD-10 classification of mental and behavioural disorders. Geneva. World Health Organization, 1992.
[8] Radloff LS. The CES-D scale: a self-report depression scale for research in the general population. Applied Psychological Measurement. 1977;1:385-401.
[9] Eaton, William W., et al. "Center for Epidemiologic Studies Depression Scale: review and revision (CESD and CESD-R)." 2004.
[10] Fennell, Melanie JV, et al. Distraction in neurotic and endogenous depression: an investigation of negative thinking in major depressive disorder. Psychological Medicine, 1987, 17.02: 441-452.
[11] Beck, Aaron T. The development of depression: A cognitive model. 1974.
[12] Rude, Stephanie S., et al. Self-report and cognitive processing measures of depressive thinking predict subsequent major depressive disorder. Cognitive Therapy and Research, 2010, 34.2: 107-115.
[13] Plutchik, R. "The Nature of Emotions". American Scientist. Retrieved 14 April 2011.
[14] Esposito, A.; HOFFMANN, Alessandro Vinciarelli Rüdiger; MÜLLER, Vincent C. Cognitive Behavioural Systems. Springer Berlin Heidelberg, 2012.
[15] Virkler, Henry. A Christian's Guide to Critical Thinking. Wipf and Stock Publishers, 2006.
[16] Ellis, Albert. Expanding the ABCs of RET. Journal of Rational Emotive Therapy, 1984, 2.2: 20-24.
[17] Huguo, Yao. Happy just around the corner - in the collective ABC Theory of emotion courses in counseling. Ideological and theoretical education, 2011, 2: 82-85.
[18] Tu-Ku, Y. A. O. Design and Develop an Assistant System for Depression Quantization and Estimation. Master’s thesis of Southern Taiwan University, 2008.
[19] Shou-Nian Wang. Predicting Blogger's Tendency of Depression Using Multiple Passive Factors Analysis Model. Master’s thesis of National Cheng Kung University, 2011.
[20] Sheng-JiaHong. Using Stressful Life Event-Driven Model To Predict Web User’s Depression Tendency. Master’s thesis of National Cheng Kung University, 2013.
[21] Po-MingSu. Predicting Web User's Tendency of Depression Using Event-Driven Negative Emotion Model. Master’s thesis of National Cheng Kung University, 2012.
[22] Hsieh-Cheng Chiang. Automatic Capture and Detect Blog Message of Suicidal Ideation. 2010.
[23] Huang, Yen-Pei; GOH, Tiong; LIEW, Chern Li. Hunting suicide notes in web 2.0-Preliminary findings. In: Multimedia Workshops, 2007. ISMW'07. Ninth IEEE International Symposium on. IEEE, 2007. p. 517-521.
[24] Goh, Tiong-Thye; HUANG, Yen-Pei. Monitoring youth depression risk in Web 2.0. VINE, 2009, 39.3: 192-202.
[25] Beck, Aaron T.; STEER, Robert A.; BROWN, Gregory K. Beck Depression Inventory. 2005.
[26] Pennebaker, James W.; FRANCIS, Martha E.; BOOTH, Roger J. Linguistic inquiry and word count: LIWC 2001. Mahway: Lawrence Erlbaum Associates, 2001, 71: 2001.
[27] Huang jin-Lan, et al Chinese version [Linguistic inquiry and word count] build dictionary of Chinese Journal of Psychology, 2012, 54.2: 185-201.
[28] Tang, Contrast material consumption and consumption experience: Exploration and Application Analysis words, National Science Council college students thematic research report, 2011.
[29] Chang, Yen-Ping, et al. Living with Gratitude: Spouse’s Gratitude on One’s Depression. Journal of Happiness Studies, 2013, 14.4: 1431-1442.
[30] Dong, Zhendong; DONG, Qiang. HowNet. 2000.
[31] Yan, Jiajun, et al. The Creation of a Chinese Emotion Ontology Based on HowNet. Engineering Letters, 2008, 16.1: 166-171.
[32] Li Ji; REN, Fuji. A proposal for creating a chinese emotion thesaurus with tag of emotion intensity. In: Natural Language Processing and Knowledge Engineering, 2009. NLP-KE 2009. International Conference on. IEEE, 2009. p. 1-8.
[33] Ku, Lun‐Wei; CHEN, Hsin‐Hsi. Mining opinions from the Web: Beyond relevance retrieval. Journal of the American Society for Information Science and Technology, 2007, 58.12: 1838-1850.
[34] Lu, Pei-Yu; CHANG, Yu-Yun; HSIEH, Shu-Kai. Causing Emotion in Collocation: An Exploratory Data Analysis. In: ROCLING. 2013.
[35] Zeng, Yi-Ching; KLYUEV, Vitaly; WU, Shih-Hung. An Opinion Mining Technique For Chinese Blogs. In: Future Information Technology, Application, and Service. Springer Netherlands, 2012. p. 281-289.
[36] Feng, Shi, et al. Extracting common emotions from blogs based on fine-grained sentiment clustering. Knowledge and information systems, 2011, 27.2: 281-302.
[37] Lu, Wen-Hsiang, et al. Semi-automatic construction of the Chinese-English MeSH using web-based term translation method. In: AMIA Annual Symposium Proceedings. American Medical Informatics Association, 2005. p. 475.
[38] Lu, Wen-Hsiang, et al. Overcoming Terminology Barrier Using Web Resources for Cross-Language Medical Information Retrieval. In: AMIA Annual Symposium Proceedings. American Medical Informatics Association, 2006. p. 519.

校內：2020-08-18公開
校外：2020-08-18公開

簡易檢索 / 詳目顯示

相關論文