請用此 Handle URI 來引用此文件:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/93374
完整後設資料紀錄
DC 欄位 | 值 | 語言 |
---|---|---|
dc.contributor.advisor | 莊裕澤 | zh_TW |
dc.contributor.advisor | Yuh-Jzer Joung | en |
dc.contributor.author | 楊子瑩 | zh_TW |
dc.contributor.author | Tzu-Ying Yang | en |
dc.date.accessioned | 2024-07-30T16:11:56Z | - |
dc.date.available | 2024-07-31 | - |
dc.date.copyright | 2024-07-30 | - |
dc.date.issued | 2024 | - |
dc.date.submitted | 2024-07-27 | - |
dc.identifier.citation | [ 1 ] Agras, W. S., Walsh, B. T., Fairburn, C.G., Wilson, G. T., & Kraemer, H. C. (2000). A Multicenter Comparison of Cognitive-Behavioral Therapy and Interpersonal Psychotherapy for Bulimia Nervosa. Arch Gen Psychiatry. 2000;57(5):459–466. doi:10.1001/archpsyc.57.5.459
[ 2 ] Banerjee, S., & Lavie, A. (2005). METEOR: An Automatic Metric for MT Evaluation with Improved Correlation with Human Judgments. In Proceedings of the ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and/or Summarization (pp. 65–72). [ 3 ] Berk, M. S., Starace, N. K., Black, V. P., & Avina, C. (2020). Implementation of Dialectical Behavior Therapy with Suicidal and Self-Harming Adolescents in a Community Clinic. Archives of Suicide Research, 24(1), 64–81. [ 4 ] Bowen, M. (1978). Family Therapy in Clinical Practice. New York, NY: Jason Aronson. [ 5 ] Bozeman, B. N. (2000). The Efficacy of Solution-Focused Therapy Techniques on Perceptions of Hope in Clients with Depressive Symptoms. Dissertation Abstracts International: Section B: The Sciences and Engineering, 61(2-B), 1117. [ 6 ] CCU MOOCs (2020年5月13日)。5.5 焦點解決短期治療實務案例。[影片] Youtube。https://www.youtube.com/watch?v=e_HaTBszDME [ 7 ] Chen, H., Liu, X., Yin, D., & Tang, J. (2017). A Survey on Dialogue Systems: Recent Advances and New Frontiers. ACM SIGKDD Explorations Newsletter, 19, 25-35. [ 8 ] Cully, J.A., & Teten, A.L. (2008). A Therapist’s Guide to Brief Cognitive Behavioral Therapy. Department of Veterans Affairs South Central MIRECC, Houston. [ 9 ] Denecke, K., Vaaheesan, S., & Arulnathan, A. (2020). A Mental Health Chatbot for Regulating Emotions (SERMO)-Concept and Usability Test. IEEE Transactions on Emerging Topics in Computing, 9(3), 1170–1182. [ 10 ] de Shazer, S., Berg, I. K., Lipchik, E., Nunnally, E., Molnar, A., Gingerich, W., & Weiner-Davis, M. (1986). Brief Therapy: Focused Solution Development. Family Process, 25(2), 207-221. https://doi.org/10.1111/j.1545-5300.1986.00207.x [ 11 ] Dong, Q.-X., Li, L., Dai, D.-M., Zheng, C., Ma, J.-Y., Li, R., Xia, H.-M., Xu, J.-J., Wu, Z.-Y., Chang, B.-B., Sun, X., Sui, & Z.-F. (2022). A Survey for In-Context Learning. arXiv:2301.00234 [ 12 ] EU Commission. (2021). Proposal for a Regulation of the European Parliament and of the Council Laying Down Harmonised Rules on Artificial Intelligence (Artificial Intelligence Act) and Amending Certain Union Legislative Acts (COM(2021) 206 final). https://eur-lex.europa.eu/legal-content/EN/TXT/HTML/?uri=CELEX:52021PC0206&from=EN [ 13 ] Finch, S. E., & Choi, J. D. (2020). Towards Unified Dialogue System Evaluation: A Comprehensive Analysis of Current Evaluation Protocols. Proceedings of the 21th Annual Meeting of the Special Interest Group on Discourse and Dialogue, pages 236–245, 1st virtual meeting. Association for Computational Linguistics. [ 14 ] Fitzpatrick, K. K., Darcy, A., & Vierhile, M. (2017). Delivering Cognitive Behavior Therapy to Young Adults with Symptoms of Depression and Anxiety Using a Fully Automated Conversational Agent (Woebot): A Randomized Controlled Trial. JMIR Mental Health, 4(2), e19. https://doi.org/10.2196/mental.7785 [ 15] Freedman, J., & Combs, G. (1996). Narrative Therapy: The Social Construction of Preferred Realities. New York, NY: W. W. Norton. [ 16 ] Gao, J.; Liu, Y.; Deng, H.; Wang, W.; Cao, Y.; Du, J.; and Xu, R. (2021). Improving Empathetic Response Generation by Recognizing Emotion Cause in Conversations. Findings of the Association for Computational Linguistics: EMNLP 2021 (pp. 807–819) [ 17 ] Gingerich, W. J., & Peterson, L. T. (2013). Effectiveness of Solution-Focused Brief Therapy: A Systematic Qualitative Review of Controlled Outcome Studies. Research on Social Work Practice, 23(3), 266–283. [ 18 ] Harilal, N., Shah, R., Sharma, S., & Bhutani, V. (2020). CARO: An Empathetic Health Conversational Chatbot for People with Major Depression. In Proceedings of the 7th ACM IKDD CoDS and 25th COMAD (CoDS COMAD 2020) (pp. 349–350). Association for Computing Machinery. https://doi.org/10.1145/3371158.3371220 [ 19 ] Hofmann, S. G., Asnaani, A., Vonk, I. J. J., Sawyer, A. T., & Fang, A. (2012). The Efficacy of Cognitive Behavioral Therapy: A Review of Meta-Analyses. Cognitive Therapy and Research, 36 (5), 427–440. https://doi.org/10.1007/s10608-012-9476-1 [ 20 ] Hsu, S.-L., Shah, R. S., Senthil, P., Ashktorab, Z., Dugan, C., Geyer, W., & Yang, D. (2023). Helping the Helper: Supporting Peer Counselors via AI-Empowered Practice and Feedback. arXiv preprint arXiv:2305.08982 [ 21 ] Ji, Z., Lee, N., Frieske, R., Yu, T., Su, D., Xu, Y., Ishii, E., Bang, Y. J., Madotto, A., & Fung, P. (2023). Survey of Hallucination in Natural Language Generation. ACM Computing Surveys, 55 (12), Article 248, 38 pages. https://doi.org/10.1145/3571730 [ 22 ] Kendrick, T., Pilling, S., Mavranezouli, I., Ruane, C., Eadon, H., & Kapur, N. (2022). Management of Depression in Adults: Summary of Updated NICE Guidance. BMJ, 378, o1557. https://doi.org/10.1136/bmj.o1557 [ 23 ] Lazarus, A. A. (1989). The practice of multimodal therapy: Systematic, comprehensive, and effective psychotherapy. Johns Hopkins University Press. [ 24 ] Lewis, M., Liu, Y., Goyal, N., Ghazvininejad, M., Mohamed, A., Levy, O., Stoyanov, V., & Zettlemoyer, L. (2020). BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (ACL 2020) (pp. 7871–7880). Association for Computational Linguistics [ 25 ] Liu, J. M., Li, D., Cao, H., Ren, T., Liao, Z., & Wu, J. (2023). ChatCounselor: A Large Language Models for Mental Health. arXiv preprint. https://arxiv.org/abs/2309.15461 [ 26 ] Liu, X., Wang, J., Sun, J., Yuan, X., Dong, G., Di, P., Wang, W., & Wang, D. (2023). Prompting Frameworks for Large Language Models: A Survey. arXiv preprint arXiv:2311.12785. [ 27 ] Lucas, G. M. , Gratch, J. , King, A. , & Morency, L.‐P. (2014). It's Only a Computer: Virtual Humans Increase Willingness to Disclose. Computers in Human Behavior, 37, 94–100. https://doi.org/10.1016/j.chb.2014.04.043 [ 28 ] Mehlum, L., Ramberg, M., Tørmoen, A. J., Haga, E., Diep, L. M., Stanley, B. H., Miller, A. L., Sund, A. M., & Grøholt, B. (2016). Dialectical Behavior Therapy Compared with Enhanced Usual Care for Adolescents with Repeated Suicidal and Self-Harming Behavior: Outcomes Over a One-Year Follow-Up. Journal of the American Academy of Child & Adolescent Psychiatry, 55, 295–300. https://doi.org/10.1016/j.jaac.2016.01.005 [ 29 ] Miller, W. R., & Rollnick, S. (2013). Motivational Interviewing: Helping People Change (3rd edition). Guilford Press. [ 30 ] Minaee, S., Mikolov, T., Nikzad, N., Chenaghlu, M., Socher, R., Amatriain, X., & Gao, J. (2024). Large Language Models: A Survey. arXiv preprint arXiv:2402.06196. [ 31 ] Moriana, J. A., Galvez-Lara, M., & Corpas, J. (2017). Psychological Treatments for Mental Disorders in Adults: A Review of the Evidence of Leading International Organizations. Clinical Psychology Review, 54, 29-43. https://doi.org/10.1016/j.cpr.2017.03.008 [ 32 ] Oh, J., Jang, S., Kim, H., & Kim, J.-J. (2020). Efficacy of Mobile App-Based Interactive Cognitive Behavioral Therapy Using a Chatbot for Panic Disorder. International Journal of Medical Informatics, 140, 104-171. https://doi.org/10.1016/j.ijmedinf.2020.104171 [ 33 ] Park, S., Choi, J., Lee, S., Oh, C., Kim, C., La, S., Lee, J., & Suh, B. (2019). Designing a Chatbot for a Brief Motivational Interview on Stress Management: Qualitative Case Study. Journal of Medical Internet Research, 21(4), e12231. https://doi.org/10.2196/12231 [ 34 ] Pharmaceutical Technology. (2023, October 24). Pear Therapeutics: A lesson for future DTx developers. Pharmaceutical Technology. https://www.pharmaceutical-technology.com/analyst-comment/pear-therapeutics-a-lesson-for-future-dtx-developers/ [ 35 ] Rashkin, H., Smith, E. M., Li, M., & Boureau, Y.-L. (2019). Towards Empathetic Open-Domain Conversation Models: A New Benchmark and Dataset. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics (pp. 5370–5381). Florence, Italy: Association for Computational Linguistics. https://doi.org/10.18653/v1/P19-1534 [ 36 ] Ratnayake, H., Wang, C. (2024). A Prompting Framework to Enhance Language Model Output. In: Liu, T., Webb, G., Yue, L., Wang, D. (eds) AI 2023: Advances in Artificial Intelligence. AI 2023. Lecture Notes in Computer Science(), vol 14472. Springer, Singapore. https://doi.org/10.1007/978-981-99-8391-9_6 [ 37 ] Rush, A. J., Beck, A. T., Kovacs, M., & Hollon, S. D. (1977). Comparative Efficacy of Cognitive Therapy and Pharmacotherapy in the Treatment of Depressed Outpatients. Cognitive Therapy and Research, 1 (1), 17–37. https://doi.org/10.1007/BF01173502 [ 38 ] Shao, Y., Geng, Z., Liu, Y., Dai, J., Yang, F., Zhe, L., Bao, H., & Qiu, X. (2021). CPT: A Pre-Trained Unbalanced Transformer for Both Chinese Language Understanding and Generation. arXiv preprint arXiv:2109.05729. [ 39 ] Shearin, E. N., & Linehan, M. M. (1994). Dialectical Behavior Therapy for Borderline Personality Disorder: Theoretical and Empirical Foundations. Acta Psychiatrica Scandinavica, 89 (s379), 61–68. [ 40 ] Sun, H., Lin, Z., Zheng, C., Liu, S., & Huang, M. (2021). PsyQA: A Chinese dataset for generating long counseling text for mental health support. arXiv. https://arxiv.org/abs/2106.01702 [ 41 ] Woebot Health. (2021). Woebot Health receives FDA breakthrough device designation. Woebot Health. https://woebothealth.com/woebot-health-receives-fda-breakthrough-device-designation/ [ 42 ] Woebot Health. (n.d.). Woebot Health. https://woebothealth.com/ [ 43 ] Xiang, C. (2023.) 'He Would Still Be Here': Man Dies by Suicide After Talking with AI Chatbot, Widow Says. Vice News. Retrieved March 21, 2023, from https://www.vice.com/en/article/pkadgm/man-dies-by-suicide-after-talking-with-ai-chatbot-widow-says [ 44 ] Yao, B.-Y., Shi, C., Zou, L.-K., Dai, L.-F., Wu, M.-Y., Chen, C., Wang, Z., & Yu K. (2022). D4: A Chinese Dialogue Dataset for Depression-Diagnosis-Oriented Chat. arXiv preprint arXiv:2205.11764. [ 45 ] Yin, J., Chen, Z., Zhou, K., & Yu, C. (2019). A Deep Learning Based Chatbot for Campus Psychological Therapy. arXiv. https://doi.org/10.48550/ARXIV.1910.06707 [ 46 ] 衛生福利部中央健康保險署. (2022). 抗憂鬱藥物使用人數統計. 衛生福利部中央健康保險署. https://www.mohw.gov.tw/dl-16605-eee5f1f6-b653-46ce-9931-9d8fa54959d7.html [ 47 ] 學生輔導法. (2014).學生輔導法. 司法部法律系統. https://law.moj.gov.tw/LawClass/LawAll.aspx?pcode=H0070058 [ 48 ] 王智弘、楊淳斐 (2001)。網路諮商中可行之理論取向與實務技巧。輔導季刊, 37(4),20-27。 | - |
dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/93374 | - |
dc.description.abstract | 憂鬱症是一種常見且嚴重的心理健康問題,影響全球數百萬人。不僅對個人的生活質量產生重大負面影響,對於患者周遭的家人朋友來說是重大的心理負擔,對於社會也是一種負擔。傳統的心理治療方法如認知行為治療(CBT)、焦點解決治療(SFBT)等療法在治療憂鬱症方面已有顯著成效。然而,這些治療方法通常需要由專業的心理治療師進行,而許多患者因資源有限或汙名化而難以獲得適當的治療,也受限於時間空間,難以在需要的時候取得適時的幫助。
近年來,大型語言模型(LLM)的迅速發展為心理健康領域帶來了新的希望。LLM具備處理自然語言的強大能力,能夠生成具有連貫性和上下文相關性的對話。因此,本研究希望探索將LLM應用於心理諮商聊天機器人,建立一個能隨時隨地提供情緒支持的聊天機器人,並在對談過程中融入心理治療療法的方法論,作為一個額外的支持管道,以緩解心理諮商資源不足的困境。 本研究的目的是研究使用大型語言模型開發一個具有使用心理治療療法來與使用者對談的聊天機器人的可行性。聊天機器人會依據患者的憂鬱程度及自殺風險,選擇適當的心理治療療法作為對話的主軸。實驗分為兩個階段進行:第一階段,我們將對話歷史作為輸入,利用LLM預測患者的憂鬱程度及自殺風險,並 依據此資訊對應到不同的心理治療療法。第二階段,我們將為每種心理治療療法設計特定的提示,使LLM能夠根據指定的療法技巧與患者進行對話,提供個性化的治療體驗。在評估階段,我們使用多項指標來衡量聊天機器人的表現,包括對話的相關性、一致性、情緒理解、積極性及技巧正確性。結果顯示,本研究三種心理治療療法的對話在情緒理解以外的四項指標都獲得4分以上或接近4分的評分,顯示我們所設計的framework是有助於讓大型語言模型使用特定心理治療療法來與使用者進行對談的。 | zh_TW |
dc.description.abstract | Depression is a common and severe mental health issue affecting millions of people worldwide. Besides the impact on individuals' quality of life, it also places a considerable psychological burden on their families, friends as well as the society. Traditional psychotherapies such as Cognitive Behavioral Therapy (CBT), Solution-Focused Brief Therapy (SFBT), etc., have been proved to be effective in depression treatment. However, these treatments often need to be performed by professional therapists, and many patients struggle to access proper treatment due to the limited resource or stigma of mental illness.
Recently, the rapid development of large language models (LLMs) has brought new hope to the field of mental health. LLMs have powerful natural language processing capabilities, enabling them to generate coherent and contextually relevant conversations. Therefore, this study aims to explore the application of LLMs in creating a psychological counseling chatbot, designed to provide emotional support anytime and anywhere. This chatbot incorporates the methodologies of psychotherapies into its conversations, serving as an additional support channel to address the shortage of psychological counseling resources. The purpose of this study is to examine the feasibility of developing a chatbot using LLMs that can engage in therapeutic conversations with users. The chatbot will determine the appropriate psychotherapy for conversations based on the user's level of depression and suicide risk. The experiment is conducted in two phases. In the first phase, we use conversation history as input and employ LLMs to predict the user's level of depression and suicide risk. Based on the predicted results, the chatbot determine the psychotherapy it would use as the main structure of the following conversation. In the second phase, a specific set of prompts is designed for each psychotherapy. These prompts will serve as instructions to the LLM, allowing it to engage in a dialogue with the patient based on the specified therapy technique, thereby providing a personalized treatment experience for different users. In the evaluation phase, we use a number of metrics to measure the chatbot's performance, including conversation relevance, consistency, emotional understanding, proactivity, and technical accuracy. The results showed that the conversations of the three psychotherapies in this study all scored above or close to 4 points in all four metrics except emotional understanding, indicating that the framework we designed is helpful for large language models to use specific psychotherapies to talk to users. | en |
dc.description.provenance | Submitted by admin ntu (admin@lib.ntu.edu.tw) on 2024-07-30T16:11:56Z No. of bitstreams: 0 | en |
dc.description.provenance | Made available in DSpace on 2024-07-30T16:11:56Z (GMT). No. of bitstreams: 0 | en |
dc.description.tableofcontents | 口試委員會審定書 i
誌謝 ii 摘要 iii ABSTRACT iv 目次 vi 圖次 viii 表次 ix 第一章、緒論 1 1.1 研究背景與動機 1 1.2 研究目的 3 1.3 論文架構 4 第二章、文獻探討 5 2.1 個人化心理治療策略 5 2.2 適合線上進行的心理治療療法 7 2.3 心理健康領域對話系統 9 2.4 基於大型語言模型的分類預測 12 2.5 基於prompt及大型語言模型的對話生成 13 2.6 評估方法 15 2.7 總結 17 第三章、研究方法 19 3.1 研究架構 19 3.2 資料集 20 3.3 實驗方法 24 3.4 研究驗證方法 31 第四章、研究結果 33 4.1 實驗設定 33 4.2 自動評估結果 34 4.3 人工評估結果 40 4.4 對話生成結果分析 45 第五章、結論 50 5.1 研究成果 50 5.2 研究貢獻 51 5.3 研究限制 52 5.4 法規與批准現狀 52 5.5 未來研究方向 53 參考文獻 55 附錄 62 | - |
dc.language.iso | zh_TW | - |
dc.title | 基於大型語言模型的心理輔助聊天機器人可行性研究 | zh_TW |
dc.title | On the Feasibility Study of a Psychotherapy Assistant Chatbot Based on Large Language Models | en |
dc.type | Thesis | - |
dc.date.schoolyear | 112-2 | - |
dc.description.degree | 碩士 | - |
dc.contributor.oralexamcommittee | 陳建錦;楊立偉;陳以錚 | zh_TW |
dc.contributor.oralexamcommittee | Chien-Chin Chen;Li-Wei Yang;Yi-Cheng Chen | en |
dc.subject.keyword | 憂鬱症,對話系統,聊天機器人,大型語言模型,Prompt Framework, | zh_TW |
dc.subject.keyword | Depression,Dialogue System,Chatbot,Large Language Model,Prompt Framework, | en |
dc.relation.page | 126 | - |
dc.identifier.doi | 10.6342/NTU202402229 | - |
dc.rights.note | 同意授權(限校園內公開) | - |
dc.date.accepted | 2024-07-30 | - |
dc.contributor.author-college | 管理學院 | - |
dc.contributor.author-dept | 資訊管理學系 | - |
顯示於系所單位: | 資訊管理學系 |
文件中的檔案:
檔案 | 大小 | 格式 | |
---|---|---|---|
ntu-112-2.pdf 授權僅限NTU校內IP使用(校園外請利用VPN校外連線服務) | 17.25 MB | Adobe PDF | 檢視/開啟 |
系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。