1. NCCU Academic Hub
  2. Publications
  3. College of Foreign Languages and Literature
  4. Theses
  5. Item

Publications-Theses

Article View/Open

Publication Export

Google ScholarTM

NCCU Library

Citation Infomation

Related Publications in TAIR

題名 基於患者滿意度之線上醫療諮詢醫生回應後設語篇分析與提示工程應用
Metadiscourse Analysis of Doctor Responses Based on Patient Satisfaction in Online Medical Consultations and Its Applications in Prompt Engineering
作者 黃靖涵
Huang, Ching-Han
貢獻者 張瑜芸<br>許展嘉
Chang, Yu-Yun<br>Hsu, Chan-Chia
黃靖涵
Huang, Ching-Han
關鍵詞 線上醫療諮詢
後設語篇
同理心
滿意度
提示工程
Online medical consultation
Metadiscourse
Empathy
Satisfaction
Prompt engineering
日期 2025
上傳時間 4-Aug-2025 15:05:34 (UTC+8)
摘要 本研究旨在探討台灣華語線上醫療諮詢裡醫師回應的後設語篇策略如何影響病患滿意度，並嘗試將研究發現應用於病患滿意度評估的提示工程。本研究採用 Hyland (2005) 的後設語篇理論框架，觀察交互式標記與互動式標記的使用，探究醫師回應中的組織結構與互動模式。本研究語料來源為台灣e院線上醫療諮詢平台，收集具有病患滿意度評分的醫師回應，建為語料庫，進行量化與質化分析。量化分析結果顯示，不同滿意度回應間在交互式與互動式後設語篇標記的使用上均呈現顯著差異。質化分析發現，令人滿意的回應更頻繁地使用明確的因果標記、個人化指涉與同理心表達，而不滿意的回應則傾向模糊的表達方式，且缺乏互動性。將這些研究發現應用於 GPT-4o 的病患滿意度分類提示設計，結果顯示思維鏈提示在此任務中表現最佳。本研究透過探討醫師回應中的語言策略與病患滿意度之間的關聯性，為台灣華語線上醫療諮詢溝通研究提供貢獻，並展示如何將這些分析結果應用於自動化評估患者滿意度的提示工程。
This study investigates how metadiscourse strategies in doctors’ responses influence patient satisfaction in Taiwan Mandarin Online Medical Consultations (OMC), and explores the application of these insights to prompt engineering for automated patient satisfaction assessment. This study relies on Hyland’s (2005) framework to analyze the organization and interaction of doctors’ responses, examining the use of interactive and interactional devices. Based on a self-compiled corpus of doctor responses with patient satisfaction ratings from Taiwan e-Hospital, this study conducts both quantitative and qualitative analyses. The quantitative analysis reveals significant linguistic differences between the satisfactory and unsatisfactory groups in their use of both interactive and interactional metadiscourse devices. The qualitative analysis shows that satisfactory responses more frequently employ explicit causal transitions and personalized references with empathetic expressions, while unsatisfactory responses tend to be vague and less interactive. Incorporating these insights into GPT-4o prompt design for patient satisfaction classification, this study shows that Chain-of-Thought prompting yields the best performance. The study contributes to OMC communication research by detailing how doctors’ linguistic strategies correlate with patients’ satisfaction, and demonstrates how such insights can optimize prompt engineering for automated evaluation.
參考文獻 Akbar, S. A., Hossain, M. M., Wood, T., Chin, S.-C., Salinas, E. M., Alvarez, V., & Cornejo, E. (2024). HalluMeasure: Fine-grained hallucination measurement using chain-of-thought reasoning. In Y. Al-Onaizan, M. Bansal, & Y.-N. Chen (Eds.), Proceedings of the 2024 conference on empirical methods in natural language processing (pp. 15020–15037). Association for Computational Linguistics. https://doi.org/10.18653/v1/2024.emnlp-main.837 Al Nazi, Z., Hossain, M. R., & Al Mamun, F. (2025). Evaluation of open and closed-source LLMs for low-resource language with zero-shot, few-shot, and chain-of-thought prompting. Natural Language Processing Journal, 10, 100124. https://doi.org/10.1016/j.nlp.2024.100124 Alam, F., Danieli, M., & Riccardi, G. (2016). Can we detect speakers’ empathy?: A real-life case study. Proceedings of the 7th IEEE International Conference on Cognitive Infocommunications (CogInfoCom), 59–64. https://doi.org/10.1109/CogInfoCom.2016.7804525 Alban, M. W. (2024). Word choice affects social judgments: Relational messages containing low-frequency words get low evaluations [Advance online publication]. Psychological Reports. https://doi.org/10.1177/00332941241287411 Alelaiwi, A. (2019). Multimodal patient satisfaction recognition for smart healthcare. IEEE Access, 7, 174219–174226. https://doi.org/10.1109/ACCESS.2019.2956083 Alter, A. L., & Oppenheimer, D. M. (2008). Effects of fluency on psychological distance and mental construal (or why New York is a large city, but New York is a civilized jungle). Psychological Science, 19(2), 161–167. https://doi.org/10.1111/j.1467-9280.2008.02062.x Azijah, D., & Gulö, I. (2020). Interpersonal metadiscourse markers in Jacinda Ardern speech at Christchurch memorial. Linguistics and Literature Journal, 1(2), 70–77. https://doi.org/10.33365/llj.v1i2.594 Batt-Rawden, S. A., Chisolm, M. S., Anton, B., & Flickinger, T. E. (2013). Teaching empathy to medical students: An updated, systematic review. Academic Medicine, 88(8), 1171–1177. https://doi.org/10.1097/ACM.0b013e318299f3e3 Bigi, S. (2011). The persuasive role of ethos in doctor-patient interactions. Communication & Medicine, 8(1), 67–75. https://doi.org/10.1558/cam.v8i1.67 Bonvicini, K. A., Perlin, M. J., Bylund, C. L., Carroll, G., Rouse, R. A., & Goldstein, M. G. (2009). Impact of communication training on physician expression of empathy in patient encounters. Patient Education and Counseling, 75(1), 3–10. https://doi.org/10.1016/j.pec.2008.09.007 Branch Jr, W. T., Kern, D., Haidet, P., Weissmann, P., Gracey, C. F., Mitchell, G., & Inui, T. (2001). Teaching the human dimensions of care in clinical settings. JAMA, 286(9), 1067–1074. https://doi.org/10.1001/jama.286.9.1067 Brown, T., Mann, B., Ryder, N., Subbiah, M., Kaplan, J. D., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., Agarwal, S., Herbert-Voss, A., Krueger, G., Henighan, T., Child, R., Ramesh, A., Ziegler, D., Wu, J., Winter, C., … Amodei, D. (2020). Language models are few-shot learners. Advances in Neural Information Processing Systems, 33, 1877–1901. Chen, J., Wu, G., Zhang, T., Zhao, B., Wang, R., Zhai, X., & Guo, F. (2024). Exploring factors affecting patient satisfaction in online healthcare: A machine learning approach grounded in empathy theory. Digital Health, 10, 20552076241309223. https://doi.org/10.1177/20552076241309223 Chen, W.-M. (2024). A pragmatic analysis and pedagogical application of persuasive speech in Chinese issue-oriented videos [Master’s thesis, National Taiwan Normal University (Taiwan)]. Cheng, X., & Steffensen, M. S. (1996). Metadiscourse: A technique for improving student writing. Research in the Teaching of English, 30(2), 149–181. https://doi.org/10.58680/rte199615322 Clark, H. H., & Carlson, T. B. (1982). Hearers and speech acts. Language, 58(2), 332–373. Cohen, J. (1960). A coefficient of agreement for nominal scales. Educational and Psychological Measurement, 20(1), 37–46. https://doi.org/10.1177/001316446002000104 Crismore, A., & Farnsworth, R. (1990). Metadiscourse in popular and professional science discourse. In W. Nash (Ed.), The writing scholar: Studies in academic discourse (pp. 118–136). Sage. Cruickshank, I. J., & Ng, L. H. X. (2023). Prompting and fine-tuning open-sourced large language models for stance classification. arXiv preprint arXiv:2309.13734. https://doi.org/10.48550/arXiv.2309.13734 De Witte, N. A., Carlbring, P., Etzelmueller, A., Nordgreen, T., Karekla, M., Haddouk, L., Belmont, A., Øverland, S., Abi-Habib, R., Bernaerts, S., Brugnera, A., Compare, A., Duque, A., Ebert, D. D., Eimontas, J., Kassianos, A. P., Salgado, J., Schwerdtfeger, A., Tohme, P., … Van Daele, T. (2021). Online consultations in mental healthcare during the COVID-19 outbreak: An international survey study on professionals’ motivations and perceived barriers. Internet Interventions, 25, 100405. https://doi.org/10.1016/j.invent.2021.100405 Deng, L., Fatemeh, B., & Gao, X. (2021). Exploring the interactive and interactional metadiscourse in doctoral dissertation writing: A diachronic study. Scientometrics, 126(8), 7223–7250. https://doi.org/10.1007/s11192-021-04064-0 Deng, Y., Xie, Y., Li, Y., Yang, M., Lam, W., & Shen, Y. (2021). Contextualized knowledge-aware attentive neural network: Enhancing answer selection with knowledge. ACM Transactions on Information Systems (TOIS), 40(1), 1–33. https://doi.org/10.1145/3457533 Dhuliawala, S., Komeili, M., Xu, J., Raileanu, R., Li, X., Celikyilmaz, A., & Weston, J. (2023). Chain-of-verification reduces hallucination in large language models. arXiv preprint arXiv:2309.11495. https://doi.org/10.48550/arXiv.2309.11495 Diani, G. (2019). Metadiscourse in web-mediated health communication. Token: A Journal of English Linguistics, 9, 13–34. https://doi.org/10.25951/2955 Du, Y., & Gu, Y. (2024). The development of evaluation scale of the patient satisfaction with telemedicine: A systematic review. BMC Medical Informatics and Decision Making, 24(1), 31. https://doi.org/10.1186/s12911-024-02436-z Flach, P., & Kull, M. (2015). Precision-recall-gain curves: Pr analysis done right. Proceedings of the 29th International Conference on Neural Information Processing Systems, 838–846. https://dl.acm.org/doi/10.5555/2969239.2969333 Flussfisch, T. (2025). An analysis of pragmatic strategies in Chinese and German internet recipes and their pedagogical application [Master’s thesis, National Taiwan Normal University (Taiwan)]. Gilardi, F., Alizadeh, M., & Kubli, M. (2023). ChatGPT outperforms crowd workers for text-annotation tasks. Proceedings of the National Academy of Sciences, 120(30), e2305016120. https://doi.org/10.1073/pnas.2305016120 Guo, Z., Lai, A., Thygesen, J. H., Farrington, J., Keen, T., Li, K., et al. (2024). Large language models for mental health applications: Systematic review. JMIR mental health, 11(1), e57400. https://doi.org/10.2196/57400 Halpern, J. (2003). What is clinical empathy? Journal of General Internal Medicine, 18(8), 670–674. https://doi.org/10.1046/j.1525-1497.2003.21017.x Head, K. J., Forster, A. K., Harsin, A., & Bartlett Ellis, R. J. (2023). Identifying sources of patient dissatisfaction when seeking care for a chronic and complex disease. Patient Experience Journal, 10(2), 94–102. https://doi.org/10.35680/2372-0247.1803 Hojat, M., Gonnella, J. S., Nasca, T. J., Mangione, S., Vergare, M., & Magee, M. (2002). Physician Empathy: Definition, Components, Measurement, and Relationship to Gender and Specialty. American Journal of Psychiatry, 159(9), 1563–1569. https://doi.org/10.1176/appi.ajp.159.9.1563 Howick, J., Moscrop, A., Mebius, A., Fanshawe, T. R., Lewith, G., Bishop, F. L., Mis- tiaen, P., Roberts, N. W., Dieninytė, E., Hu, X.-Y., et al. (2018). Effects of empathic and positive communication in healthcare consultations: A systematic review and meta-analysis. Journal of the Royal Society of Medicine, 111(7), 240–252. https://doi.org/10.1177/0141076818769477 Hsieh, C.-L., & Wu, X.-R. (2023). A Study of Metadiscourse in Chinese-Language Academic Papers. Taiwan Journal of Chinese as a Second Language, (27), 1–39. https://doi.org/10.29748/TJCSL.202312_(27).0001 Huang, J., & Xiao, W. (2024). Use of interactional metadiscourse and identity construction in responses to negative online reviews of Chinese and British hotels. PloS one, 19(12), e0316071. https://doi.org/10.1371/journal.pone.0316071 Huang, Y., Wang, H., Tang, J., et al. (2020). A study of interactional metadiscourse in English travel blogs. Open Journal of Modern Linguistics, 10(06), 785. https://doi.org/10.4236/ojml.2020.106048 Hyland, K. (1998). Exploring corporate rhetoric: Metadiscourse in the CEO’s letter. Journal of Business Communication, 35(2), 224–244. https://doi.org/10.1177/002194369803500203 Hyland, K. (2005). Metadiscourse: Exploring interaction in writing. Continuum. Hyland, K. (2010). Metadiscourse: Mapping interactions in academic writing. Nordic Journal of English Studies, 9(S2), 125–143. https://doi.org/10.35360/njes.220 Hyland, K., & Tse, P. (2004). Metadiscourse in academic writing: A reappraisal. Applied Linguistics, 25(2), 156–177. https://doi.org/10.1093/applin/25.2.156 Intaraprawat, P., & Steffensen, M. S. (1995). The use of metadiscourse in good and poor ESL essays. Journal of Second Language Writing, 4(3), 253–272. https://doi.org/10.1016/1060-3743(95)90012-8 Islam, R., & Moushi, O. M. (2024). Gpt-4o: The cutting-edge advancement in multimodal LLM. Authorea Preprints. Jo, E., Epstein, D. A., Jung, H., & Kim, Y.-H. (2023). Understanding the benefits and challenges of deploying conversational AI leveraging large language models for public health intervention. Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems, 1–16. https://doi.org/10.1145/3544548.3581503 Jones, J. (2011). Using metadiscourse to improve coherence in academic writing. Language Education in Asia, 2(1), 1–14. Kim, L. C., & Lim, J. M.-H. (2013). Metadiscourse in English and Chinese research article introductions. Discourse Studies, 15(2), 129–146. https://doi.org/10.1177/1461445612471476 Kim, S. S., Kaplowitz, S., & Johnston, M. V. (2004). The effects of physician empathy on patient satisfaction and compliance. Evaluation & the Health Professions, 27(3), 237–251. https://doi.org/10.1177/0163278704267037 Kim, Y., Guo, L., Yu, B., & Li, Y. (2023). Can ChatGPT understand causal language in science claims? Proceedings of the 13th Workshop on Computational Approaches to Subjectivity, Sentiment, & Social Media Analysis, 379–389. https://doi.org/10.18653/v1/2023.wassa-1.33 Kojima, T., Gu, S. S., Reid, M., Matsuo, Y., & Iwasawa, Y. (2022). Large language models are zero-shot reasoners. Advances in Neural Information Processing Systems, 35, 22199–22213. Lee, S., Park, S. H., Kim, S., & Seo, M. (2025). Aligning to thousands of preferences via system message generalization. Advances in Neural Information Processing Systems, 37, 73783–73829. Lee, Y.-J., Lim, C.-G., & Choi, H.-J. (2022). Does GPT-3 generate empathetic dialogues? A novel in-context example selection method and automatic evaluation metric for empathetic dialogue generation. Proceedings of the 29th International Conference on Computational Linguistics, 669–683. Leilei, Z., & Fe, L. (2022). The pragmatic functions of the tilde “~” in China’s social media among youth groups. International Journal of Linguistics, Literature and. Translation, 5(12), 136–143. https://doi.org/10.32996/ijllt.2022.5.12.17 Li, C. N., & Thompson, S. A. (1981). Mandarin Chinese: A functional reference grammar. University of California Press. Li, Q., Li, P., Ren, Z., Ren, P., & Chen, Z. (2022). Knowledge bridging for empathetic dialogue generation. Proceedings of the AAAI Conference on Artificial Intelligence, 36(10), 10993–11001. https://doi.org/10.1609/aaai.v36i10.21347 Li, Y. (2023). A practical survey on zero-shot prompt design for in-context learning. arXiv preprint arXiv:2309.13205. https://doi.org/10.48550/arXiv.2309.13205 Lief, H. I., & Fox, R. C. (1963). Training for “detached concern” in medical students. In H. I. Lief, V. F. Lief, & N. R. Lief (Eds.), The psychological basis of medical practice (pp. 12–35). Harper & Row. Lin, C. Y., Wu, Y.-H., & Chen, A. L. (2021). Selecting the most helpful answers in online health question answering communities. Journal of Intelligent Information Systems, 57(2), 271–293. https://doi.org/10.1007/s10844-021-00640-1 Lin, J., Han, Z., Thomas, D. R., Gurung, A., Gupta, S., Aleven, V., & Koedinger, K. R. (2025). How can I get it right? using GPT to rephrase incorrect trainee responses. International Journal of Artificial Intelligence in Education, 35, 482–508. https://doi.org/10.1007/s40593-024-00408-y Ling, Y. (2023). Bio+ Clinical BERT, BERT Base, and CNN performance comparison for predicting drug-review satisfaction. arXiv preprint arXiv:2308.03782. https://doi.org/10.48550/arXiv.2308.03782 Liu, P., Yuan, W., Fu, J., Jiang, Z., Hayashi, H., & Neubig, G. (2023). Pre-train, prompt, and predict: A systematic survey of prompting methods in natural language processing. ACM computing surveys, 55(9), 1–35. https://doi.org/10.1145/3560815 Lloyd, M., Bor, R., & Noble, L. M. (2018). Clinical communication skills for medicine. Elsevier Health Sciences. Lorié, Á., Reinero, D. A., Phillips, M., Zhang, L., & Riess, H. (2017). Culture and non-verbal expressions of empathy in clinical settings: A systematic review. Patient Education and Counseling, 100(3), 411–424. https://doi.org/10.1016/j.pec.2016.09.018 Ma, W.-Y., & Chen, K.-J. (2003). Introduction to CKIP Chinese word segmentation system for the first international Chinese word segmentation bakeoff. Proceedings of the Second SIGHAN Workshop on Chinese Language Processing, 168–171. https://doi.org/10.3115/1119250.1119276 Martin, J. R., & White., P. R. R. (2005). The language of evaluation: Appraisal in English. Palgrave Macmillan. Min, S., Lyu, X., Holtzman, A., Artetxe, M., Lewis, M., Hajishirzi, H., & Zettlemoyer, L. (2022). Rethinking the role of demonstrations: What makes in-context learning work? In Y. Goldberg, Z. Kozareva, & Y. Zhang (Eds.), Proceedings of the 2022 conference on empirical methods in natural language processing (pp. 11048– 11064). Association for Computational Linguistics. https://doi.org/10.18653/v1/2022.emnlp-main.759 Mishra, S., Khashabi, D., Baral, C., Choi, Y., & Hajishirzi, H. (2021). Reframing instructional prompts to GPTk’s language. arXiv preprint arXiv:2109.07830. https://doi.org/10.48550/arXiv.2109.07830 Mousavi, R., Raghu, T., & Frey, K. (2020). Harnessing artificial intelligence to improve the quality of answers in online question-answering health forums. Journal of Management Information Systems, 37(4), 1073–1098. https://doi.org/10.1080/07421222.2020.1831775 Mu, C., Zhang, L. J., Ehrich, J., & Hong, H. (2015). The use of metadiscourse for knowledge construction in Chinese and English research articles. Journal of English for Academic Purposes, 20, 135–148. https://doi.org/10.1016/j.jeap.2015.09.003 Nambisan, P. (2011). Information seeking and social support in online health communities: Impact on patients’ perceived empathy. Journal of the American Medical Informatics Association, 18(3), 298–304. https://doi.org/10.1136/amiajnl-2010-000058 Oniani, D., & Wang, Y. (2020). A qualitative evaluation of language models on automatic question-answering for COVID-19. Proceedings of the 11th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics, 1–9. https://doi.org/10.1145/3388440.3412413 Parviainen, J., & Rantala, J. (2022). Chatbot breakthrough in the 2020s? An ethical reflection on the trend of automated consultations in health care. Medicine, Health Care and Philosophy, 25(1), 61–71. https://doi.org/10.1007/s11019-021-10049-w Pearson, W. S., & Abdollahzadeh, E. (2023). Metadiscourse in academic writing: A systematic review. Lingua, 293, 103561. https://doi.org/10.1016/j.lingua.2023.103561 Peters, G. (2021). Metadiscourse, materiality and morality in communication skills training with simulated patients. Communication & Medicine, 16(3), 251–266. https://doi.org/10.1558/cam.39725 Pollak, K. I., Alexander, S. C., Tulsky, J. A., Lyna, P., Coffman, C. J., Dolor, R. J., Gulbrandsen, P., & Østbye, T. (2011). Physician empathy and listening: Associations with patient satisfaction and autonomy. The Journal of the American Board of Family Medicine, 24(6), 665–672. https://doi.org/10.3122/jabfm.2011.06.110025 Pounds, G. (2011). Empathy as ‘appraisal’. Journal of Applied Linguistics and Professional Practice, 7(2), 139–162. https://doi.org/10.1558/japl.v7i2.145 Pounds, G. (2012). Enhancing empathic skills in clinical practice: A linguistic approach. International Journal of Work Organisation and Emotion, 5(2), 114–131. https://doi.org/10.1504/IJWOE.2012.049516 Qian, Y., Zhang, W.-N., & Liu, T. (2023). Harnessing the power of large language models for empathetic response generation: Empirical investigations and improvements. arXiv preprint arXiv:2310.05140. https://doi.org/10.48550/arXiv.2310.05140 Qiu, Y., Ding, S., Tian, D., Zhang, C., & Zhou, D. (2022). Predicting the quality of answers with less bias in online health question answering communities. Information Processing & Management, 59(6), 103112. https://doi.org/10.1016/j.ipm.2022.103112 Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., & Sutskever, I. (2019). Language models are unsupervised multitask learners. OpenAI. https://api.semanticscholar.org/CorpusID:160025533 Rahmanti, A. R., Yang, H.-C., Bintoro, B. S., Nursetyo, A. A., Muhtar, M. S., Syed-Abdul, S., & Li, Y.-C. J. (2022). Slimme, a chatbot with artificial empathy for personal weight management: System design and finding. Frontiers in Nutrition, 9, 870775. https://doi.org/10.3389/fnut.2022.870775 Reynolds, L., & McDonell, K. (2021). Prompt programming for large language models: Beyond the few-shot paradigm. Extended Abstracts of the 2021 CHI Conference on Human Factors in Computing Systems. https://doi.org/10.1145/3411763.3451760 Riess, H., Kelley, J. M., Bailey, R. W., Dunn, E. J., & Phillips, M. (2012). Empathy training for resident physicians: A randomized controlled trial of a neuroscience-informed curriculum. Journal of General Internal Medicine, 27(10), 1280–1286. https://doi.org/10.1007/s11606-012-2063-z Rivas, R., Montazeri, N., Le, N. X., & Hristidis, V. (2018). Automatic classification of online doctor reviews: Evaluation of text classifier algorithms. Journal of Medical Internet Research, 20(11), e11141. https://doi.org/10.2196/11141 Rizzi, D. A. (1994). Causal reasoning and the diagnostic process. Theoretical Medicine, 15, 315–333. https://doi.org/10.1007/BF01313345 Rosoł, M., Gąsior, J. S., Łaba, J., Korzeniewski, K., & Młyńczak, M. (2023). Evaluation of the performance of GPT-3.5 and GPT-4 on the Polish Medical Final Examination. Scientific Reports, 13(1), 20512. https://doi.org/10.1038/s41598-023-46995-z Russell, A. (2011). The Arab Spring extra-national information flows, social media and the 2011 Egyptian uprising. International Journal of Communication, 5, 10. Ruytenbeek, N., & Decock, S. (2024). Expressing and responding to customer (dis)satisfaction online: New insights from discourse and linguistic approaches. International Journal of Business Communication, 61(1), 3–17. https://doi.org/10.1177/23294884231199740 Schiffrin, D. (1980). Meta-talk: Organizational and evaluate brackets in discourse. Sociological inquiry, 50. https://doi.org/10.1111/j.1475-682X.1980.tb00021.x Searle, J. R. (1969). The structure of illocutionary acts. In Speech acts: An essay in the philosophy of language (pp. 54–71). Cambridge University Press. Senitan, M., Alhaiti, A. H., & Gillespie, J. (2018). Patient satisfaction and experience of primary care in Saudi Arabia: A systematic review. International Journal for Quality in Health Care, 30(10), 751–759. https://doi.org/10.1093/intqhc/mzy104 Smith, A. (2006). Cognitive empathy and emotional empathy in human behavior and evolution. The Psychological Record, 56(1), 3–21. https://doi.org/10.1007/BF03395534 Soltner, C., Giquello, J., Monrigal-Martin, C., & Beydon, L. (2011). Continuous care and empathic anaesthesiologist attitude in the preoperative period: Impact on patient anxiety and satisfaction. British Journal of Anaesthesia, 106(5), 680–686. https://doi.org/10.1093/bja/aer034 Stueber, K. (2019). Empathy. In E. N. Zalta (Ed.), The Stanford encyclopedia of philosophy (Fall 2019). Metaphysics Research Lab, Stanford University. https://plato.stanford.edu/archives/fall2019/entries/empathy/ Sun, S. (2011). Meta-analysis of cohen’s kappa. Health Services and Outcomes Research Methodology, 11, 145–163. https://doi.org/10.1007/s10742-011-0077-3 Tan, L., Le, M. K., Yu, C. C., Liaw, S. Y., Tierney, T., Ho, Y. Y., Lim, E., Lim, D., Ng, R., Ngeow, C., & Low, J. (2021). Defining clinical empathy: A grounded theory approach from the perspective of healthcare workers and patients in a multicultural setting. BMJ Open, 11(9), e045224. https://doi.org/10.1136/bmjopen-2020-045224 Tseng, M.-Y., & Zhang, G. (2018). Pragmeme, adaptability, and elasticity in online medical consultations. Journal of Pragmatics, 137, 40–56. https://doi.org/10.1016/j.pragma.2018.09.004 Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, Ł., & Polosukhin, I. (2017). Attention is all you need. Advances in Neural Informa- tion Processing Systems, 30. Vogel, D., Meyer, M., & Harendza, S. (2018). Verbal and non-verbal communication skills including empathy during history taking of undergraduate medical students. BMC Medical Education, 18(1), 157. https://doi.org/10.1186/s12909-018-1260-9 Wang, L., Xu, W., Lan, Y., Hu, Z., Lan, Y., Lee, R. K.-W., & Lim, E.-P. (2023). Plan-and-solve prompting: Improving zero-shot chain-of-thought reasoning by large language models. arXiv preprint arXiv:2305.04091. https://doi.org/10.48550/arXiv.2305.04091 Wei, J., Wang, X., Schuurmans, D., Bosma, M., Xia, F., Chi, E., Le, Q. V., Zhou, D., et al. (2022). Chain-of-thought prompting elicits reasoning in large language models. Advances in Neural Information Processing Systems, 35, 24824–24837. Wind, T. R., Rijkeboer, M., Andersson, G., & Riper, H. (2020). The COVID-19 pandemic: The ‘black swan’ for mental health care and a turning point for e-health. Internet Interventions, 20, 100317. https://doi.org/10.1016/j.invent.2020.100317 Wu, J., Zhang, G., Xing, Y., Liu, Y., Zhang, Z., Dong, Y., & Herrera-Viedma, E. (2023). A sentiment analysis driven method based on public and personal preferences with correlated attributes to select online doctors. Applied Intelligence, 53(16), 19093–19114. https://doi.org/10.1007/s10489-023-04485-9 Wynn, R., & Wynn, M. (2006). Empathy as an interactionally achieved phenomenon in psychotherapy: Characteristics of some conversational resources. Journal of pragmatics, 38(9), 1385–1397. https://doi.org/10.1016/j.pragma.2005.09.008 Xia, J. (2020). “Loving you”: Use of metadiscourse for relational acts in WeChat public account advertisements. Discourse, Context & Media, 37, 100416. https://doi.org/10.1016/j.dcm.2020.100416 Xie, Z. (2020). Two types of verb reduplications in Mandarin Chinese. Studies in Chinese Linguistics, 41(1), 73–108. https://doi.org/10.2478/scl-2020-0003 Xu, H., & Xia, D. (2023). Digital tildes (“~”) may convey more: analyzing innovative uses of tildes in Chinese WeChat messages. Language and Semiotic Studies, 9(3), 443–460. https://doi.org/10.1515/lass-2023-0009 Xu, Y., Wu, G., & Chen, Y. (2022). Predicting patients’ satisfaction with doctors in online medical communities: An approach based on XGBoost algorithm. Journal of Organizational and End User Computing (JOEUC), 34(4), 1–17. https://doi.org/10.4018/JOEUC.287571 Yang, N. (2021). Engaging readers across participants: A cross-interactant analysis of metadiscourse in letters of advice during the COVID-19 pandemic. Journal of Pragmatics, 186, 181–193. https://doi.org/10.1016/j.pragma.2021.10.017 Yang, X., Peynetti, E., Meerman, V., & Tanner, C. (2022). What GPT knows about who is who. arXiv preprint arXiv:2205.07407. https://doi.org/10.48550/arXiv.2205.07407 Zhang, Y. (2021). How doctors do things with empathy in online medical consultations in China: A discourse-analytic approach. Health Communication, 36(7), 816–825. https://doi.org/10.1080/10410236.2020.1712527 Zhang, Y., Lu, W., Ou, W., Zhang, G., Zhang, X., Cheng, J., & Zhang, W. (2020). Chinese medical question answer selection via hybrid models based on CNN and GRU. Multimedia Tools and Applications, 79, 14751–14776. https://doi. org/10.1007/s11042-019-7240-1 Zhou, R., & Li, S. (2023). A study on the persuasive function of metadiscourse in hotel responses to negative reviews on tripadvisor. English Language Teaching, 16(6), 1–55. https://doi.org/10.5539/elt.v16n6p55
描述 碩士
國立政治大學
語言學研究所
111555008
資料來源 http://thesis.lib.nccu.edu.tw/record/#G0111555008
資料類型 thesis
dc.contributor.advisor 張瑜芸<br>許展嘉zh_TW
dc.contributor.advisor Chang, Yu-Yun<br>Hsu, Chan-Chiaen_US
dc.contributor.author (Authors) 黃靖涵zh_TW
dc.contributor.author (Authors) Huang, Ching-Hanen_US
dc.creator (作者) 黃靖涵zh_TW
dc.creator (作者) Huang, Ching-Hanen_US
dc.date (日期) 2025en_US
dc.date.accessioned 4-Aug-2025 15:05:34 (UTC+8)-
dc.date.available 4-Aug-2025 15:05:34 (UTC+8)-
dc.date.issued (上傳時間) 4-Aug-2025 15:05:34 (UTC+8)-
dc.identifier (Other Identifiers) G0111555008en_US
dc.identifier.uri (URI) https://nccur.lib.nccu.edu.tw/handle/140.119/158695-
dc.description (描述) 碩士zh_TW
dc.description (描述) 國立政治大學zh_TW
dc.description (描述) 語言學研究所zh_TW
dc.description (描述) 111555008zh_TW
dc.description.abstract (摘要) 本研究旨在探討台灣華語線上醫療諮詢裡醫師回應的後設語篇策略如何影響病患滿意度，並嘗試將研究發現應用於病患滿意度評估的提示工程。本研究採用 Hyland (2005) 的後設語篇理論框架，觀察交互式標記與互動式標記的使用，探究醫師回應中的組織結構與互動模式。本研究語料來源為台灣e院線上醫療諮詢平台，收集具有病患滿意度評分的醫師回應，建為語料庫，進行量化與質化分析。量化分析結果顯示，不同滿意度回應間在交互式與互動式後設語篇標記的使用上均呈現顯著差異。質化分析發現，令人滿意的回應更頻繁地使用明確的因果標記、個人化指涉與同理心表達，而不滿意的回應則傾向模糊的表達方式，且缺乏互動性。將這些研究發現應用於 GPT-4o 的病患滿意度分類提示設計，結果顯示思維鏈提示在此任務中表現最佳。本研究透過探討醫師回應中的語言策略與病患滿意度之間的關聯性，為台灣華語線上醫療諮詢溝通研究提供貢獻，並展示如何將這些分析結果應用於自動化評估患者滿意度的提示工程。zh_TW
dc.description.abstract (摘要) This study investigates how metadiscourse strategies in doctors’ responses influence patient satisfaction in Taiwan Mandarin Online Medical Consultations (OMC), and explores the application of these insights to prompt engineering for automated patient satisfaction assessment. This study relies on Hyland’s (2005) framework to analyze the organization and interaction of doctors’ responses, examining the use of interactive and interactional devices. Based on a self-compiled corpus of doctor responses with patient satisfaction ratings from Taiwan e-Hospital, this study conducts both quantitative and qualitative analyses. The quantitative analysis reveals significant linguistic differences between the satisfactory and unsatisfactory groups in their use of both interactive and interactional metadiscourse devices. The qualitative analysis shows that satisfactory responses more frequently employ explicit causal transitions and personalized references with empathetic expressions, while unsatisfactory responses tend to be vague and less interactive. Incorporating these insights into GPT-4o prompt design for patient satisfaction classification, this study shows that Chain-of-Thought prompting yields the best performance. The study contributes to OMC communication research by detailing how doctors’ linguistic strategies correlate with patients’ satisfaction, and demonstrates how such insights can optimize prompt engineering for automated evaluation.en_US
dc.description.tableofcontents 1 Introduction 1 1.1 Background and Motivation 1 1.2 Research Gaps 4 1.3 Research Questions and Hypotheses 5 1.4 Organization 6 2 Literature Review 7 2.1 Metadiscourse 7 2.1.1 Overview of Metadisocurse 7 2.1.2 Metadiscourse and Empathy 10 2.2 Empathy 11 2.2.1 Definition of Empathy 11 2.2.2 Empathy in Medical Consultation 12 2.3 Satisfaction Classification 14 3 Methodology 17 3.1 Data Collection 17 3.2 Data Annotation 20 3.3 Data Analysis 22 3.4 GPT and Prompt Engineering 22 3.4.1 Generative Pre-trained Transformer (GPT) 23 3.4.2 Prompt Engineering 24 3.5 Model Evaluation 25 3.6 Interim Summary 27 4 Results of Metadiscourse Analysis 29 4.1 Distribution of Metadiscourse Devices 29 4.2 Use of Interactive Metadiscourse Devices 31 4.2.1 Transitions 31 4.2.2 Frame Markers 33 4.2.3 Endophoric Markers 35 4.2.4 Evidential Markers 37 4.2.5 Code Glosses 39 4.3 Use of Interactional Metadiscourse Devices 40 4.3.1 Hedges 40 4.3.2 Boosters 41 4.3.3 Attitude Markers 45 4.3.4 Self-mentions 46 4.3.5 Engagement Markers 48 4.4 Interim Summary 50 5 Satisfaction Classification through Prompt Engineering 53 5.1 Experimental Setup 53 5.2 Results of Classification Task 62 5.3 Discussion of Classification Task 64 6 Conclusions 76 6.1 Summary 76 6.2 Contributions 77 6.3 Limitations and Future Research 79 References 81zh_TW
dc.format.extent 3297002 bytes-
dc.format.mimetype application/pdf-
dc.source.uri (資料來源) http://thesis.lib.nccu.edu.tw/record/#G0111555008en_US
dc.subject (關鍵詞) 線上醫療諮詢zh_TW
dc.subject (關鍵詞) 後設語篇zh_TW
dc.subject (關鍵詞) 同理心zh_TW
dc.subject (關鍵詞) 滿意度zh_TW
dc.subject (關鍵詞) 提示工程zh_TW
dc.subject (關鍵詞) Online medical consultationen_US
dc.subject (關鍵詞) Metadiscourseen_US
dc.subject (關鍵詞) Empathyen_US
dc.subject (關鍵詞) Satisfactionen_US
dc.subject (關鍵詞) Prompt engineeringen_US
dc.title (題名) 基於患者滿意度之線上醫療諮詢醫生回應後設語篇分析與提示工程應用zh_TW
dc.title (題名) Metadiscourse Analysis of Doctor Responses Based on Patient Satisfaction in Online Medical Consultations and Its Applications in Prompt Engineeringen_US
dc.type (資料類型) thesisen_US
dc.relation.reference (參考文獻) Akbar, S. A., Hossain, M. M., Wood, T., Chin, S.-C., Salinas, E. M., Alvarez, V., & Cornejo, E. (2024). HalluMeasure: Fine-grained hallucination measurement using chain-of-thought reasoning. In Y. Al-Onaizan, M. Bansal, & Y.-N. Chen (Eds.), Proceedings of the 2024 conference on empirical methods in natural language processing (pp. 15020–15037). Association for Computational Linguistics. https://doi.org/10.18653/v1/2024.emnlp-main.837 Al Nazi, Z., Hossain, M. R., & Al Mamun, F. (2025). Evaluation of open and closed-source LLMs for low-resource language with zero-shot, few-shot, and chain-of-thought prompting. Natural Language Processing Journal, 10, 100124. https://doi.org/10.1016/j.nlp.2024.100124 Alam, F., Danieli, M., & Riccardi, G. (2016). Can we detect speakers’ empathy?: A real-life case study. Proceedings of the 7th IEEE International Conference on Cognitive Infocommunications (CogInfoCom), 59–64. https://doi.org/10.1109/CogInfoCom.2016.7804525 Alban, M. W. (2024). Word choice affects social judgments: Relational messages containing low-frequency words get low evaluations [Advance online publication]. Psychological Reports. https://doi.org/10.1177/00332941241287411 Alelaiwi, A. (2019). Multimodal patient satisfaction recognition for smart healthcare. IEEE Access, 7, 174219–174226. https://doi.org/10.1109/ACCESS.2019.2956083 Alter, A. L., & Oppenheimer, D. M. (2008). Effects of fluency on psychological distance and mental construal (or why New York is a large city, but New York is a civilized jungle). Psychological Science, 19(2), 161–167. https://doi.org/10.1111/j.1467-9280.2008.02062.x Azijah, D., & Gulö, I. (2020). Interpersonal metadiscourse markers in Jacinda Ardern speech at Christchurch memorial. Linguistics and Literature Journal, 1(2), 70–77. https://doi.org/10.33365/llj.v1i2.594 Batt-Rawden, S. A., Chisolm, M. S., Anton, B., & Flickinger, T. E. (2013). Teaching empathy to medical students: An updated, systematic review. Academic Medicine, 88(8), 1171–1177. https://doi.org/10.1097/ACM.0b013e318299f3e3 Bigi, S. (2011). The persuasive role of ethos in doctor-patient interactions. Communication & Medicine, 8(1), 67–75. https://doi.org/10.1558/cam.v8i1.67 Bonvicini, K. A., Perlin, M. J., Bylund, C. L., Carroll, G., Rouse, R. A., & Goldstein, M. G. (2009). Impact of communication training on physician expression of empathy in patient encounters. Patient Education and Counseling, 75(1), 3–10. https://doi.org/10.1016/j.pec.2008.09.007 Branch Jr, W. T., Kern, D., Haidet, P., Weissmann, P., Gracey, C. F., Mitchell, G., & Inui, T. (2001). Teaching the human dimensions of care in clinical settings. JAMA, 286(9), 1067–1074. https://doi.org/10.1001/jama.286.9.1067 Brown, T., Mann, B., Ryder, N., Subbiah, M., Kaplan, J. D., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., Agarwal, S., Herbert-Voss, A., Krueger, G., Henighan, T., Child, R., Ramesh, A., Ziegler, D., Wu, J., Winter, C., … Amodei, D. (2020). Language models are few-shot learners. Advances in Neural Information Processing Systems, 33, 1877–1901. Chen, J., Wu, G., Zhang, T., Zhao, B., Wang, R., Zhai, X., & Guo, F. (2024). Exploring factors affecting patient satisfaction in online healthcare: A machine learning approach grounded in empathy theory. Digital Health, 10, 20552076241309223. https://doi.org/10.1177/20552076241309223 Chen, W.-M. (2024). A pragmatic analysis and pedagogical application of persuasive speech in Chinese issue-oriented videos [Master’s thesis, National Taiwan Normal University (Taiwan)]. Cheng, X., & Steffensen, M. S. (1996). Metadiscourse: A technique for improving student writing. Research in the Teaching of English, 30(2), 149–181. https://doi.org/10.58680/rte199615322 Clark, H. H., & Carlson, T. B. (1982). Hearers and speech acts. Language, 58(2), 332–373. Cohen, J. (1960). A coefficient of agreement for nominal scales. Educational and Psychological Measurement, 20(1), 37–46. https://doi.org/10.1177/001316446002000104 Crismore, A., & Farnsworth, R. (1990). Metadiscourse in popular and professional science discourse. In W. Nash (Ed.), The writing scholar: Studies in academic discourse (pp. 118–136). Sage. Cruickshank, I. J., & Ng, L. H. X. (2023). Prompting and fine-tuning open-sourced large language models for stance classification. arXiv preprint arXiv:2309.13734. https://doi.org/10.48550/arXiv.2309.13734 De Witte, N. A., Carlbring, P., Etzelmueller, A., Nordgreen, T., Karekla, M., Haddouk, L., Belmont, A., Øverland, S., Abi-Habib, R., Bernaerts, S., Brugnera, A., Compare, A., Duque, A., Ebert, D. D., Eimontas, J., Kassianos, A. P., Salgado, J., Schwerdtfeger, A., Tohme, P., … Van Daele, T. (2021). Online consultations in mental healthcare during the COVID-19 outbreak: An international survey study on professionals’ motivations and perceived barriers. Internet Interventions, 25, 100405. https://doi.org/10.1016/j.invent.2021.100405 Deng, L., Fatemeh, B., & Gao, X. (2021). Exploring the interactive and interactional metadiscourse in doctoral dissertation writing: A diachronic study. Scientometrics, 126(8), 7223–7250. https://doi.org/10.1007/s11192-021-04064-0 Deng, Y., Xie, Y., Li, Y., Yang, M., Lam, W., & Shen, Y. (2021). Contextualized knowledge-aware attentive neural network: Enhancing answer selection with knowledge. ACM Transactions on Information Systems (TOIS), 40(1), 1–33. https://doi.org/10.1145/3457533 Dhuliawala, S., Komeili, M., Xu, J., Raileanu, R., Li, X., Celikyilmaz, A., & Weston, J. (2023). Chain-of-verification reduces hallucination in large language models. arXiv preprint arXiv:2309.11495. https://doi.org/10.48550/arXiv.2309.11495 Diani, G. (2019). Metadiscourse in web-mediated health communication. Token: A Journal of English Linguistics, 9, 13–34. https://doi.org/10.25951/2955 Du, Y., & Gu, Y. (2024). The development of evaluation scale of the patient satisfaction with telemedicine: A systematic review. BMC Medical Informatics and Decision Making, 24(1), 31. https://doi.org/10.1186/s12911-024-02436-z Flach, P., & Kull, M. (2015). Precision-recall-gain curves: Pr analysis done right. Proceedings of the 29th International Conference on Neural Information Processing Systems, 838–846. https://dl.acm.org/doi/10.5555/2969239.2969333 Flussfisch, T. (2025). An analysis of pragmatic strategies in Chinese and German internet recipes and their pedagogical application [Master’s thesis, National Taiwan Normal University (Taiwan)]. Gilardi, F., Alizadeh, M., & Kubli, M. (2023). ChatGPT outperforms crowd workers for text-annotation tasks. Proceedings of the National Academy of Sciences, 120(30), e2305016120. https://doi.org/10.1073/pnas.2305016120 Guo, Z., Lai, A., Thygesen, J. H., Farrington, J., Keen, T., Li, K., et al. (2024). Large language models for mental health applications: Systematic review. JMIR mental health, 11(1), e57400. https://doi.org/10.2196/57400 Halpern, J. (2003). What is clinical empathy? Journal of General Internal Medicine, 18(8), 670–674. https://doi.org/10.1046/j.1525-1497.2003.21017.x Head, K. J., Forster, A. K., Harsin, A., & Bartlett Ellis, R. J. (2023). Identifying sources of patient dissatisfaction when seeking care for a chronic and complex disease. Patient Experience Journal, 10(2), 94–102. https://doi.org/10.35680/2372-0247.1803 Hojat, M., Gonnella, J. S., Nasca, T. J., Mangione, S., Vergare, M., & Magee, M. (2002). Physician Empathy: Definition, Components, Measurement, and Relationship to Gender and Specialty. American Journal of Psychiatry, 159(9), 1563–1569. https://doi.org/10.1176/appi.ajp.159.9.1563 Howick, J., Moscrop, A., Mebius, A., Fanshawe, T. R., Lewith, G., Bishop, F. L., Mis- tiaen, P., Roberts, N. W., Dieninytė, E., Hu, X.-Y., et al. (2018). Effects of empathic and positive communication in healthcare consultations: A systematic review and meta-analysis. Journal of the Royal Society of Medicine, 111(7), 240–252. https://doi.org/10.1177/0141076818769477 Hsieh, C.-L., & Wu, X.-R. (2023). A Study of Metadiscourse in Chinese-Language Academic Papers. Taiwan Journal of Chinese as a Second Language, (27), 1–39. https://doi.org/10.29748/TJCSL.202312_(27).0001 Huang, J., & Xiao, W. (2024). Use of interactional metadiscourse and identity construction in responses to negative online reviews of Chinese and British hotels. PloS one, 19(12), e0316071. https://doi.org/10.1371/journal.pone.0316071 Huang, Y., Wang, H., Tang, J., et al. (2020). A study of interactional metadiscourse in English travel blogs. Open Journal of Modern Linguistics, 10(06), 785. https://doi.org/10.4236/ojml.2020.106048 Hyland, K. (1998). Exploring corporate rhetoric: Metadiscourse in the CEO’s letter. Journal of Business Communication, 35(2), 224–244. https://doi.org/10.1177/002194369803500203 Hyland, K. (2005). Metadiscourse: Exploring interaction in writing. Continuum. Hyland, K. (2010). Metadiscourse: Mapping interactions in academic writing. Nordic Journal of English Studies, 9(S2), 125–143. https://doi.org/10.35360/njes.220 Hyland, K., & Tse, P. (2004). Metadiscourse in academic writing: A reappraisal. Applied Linguistics, 25(2), 156–177. https://doi.org/10.1093/applin/25.2.156 Intaraprawat, P., & Steffensen, M. S. (1995). The use of metadiscourse in good and poor ESL essays. Journal of Second Language Writing, 4(3), 253–272. https://doi.org/10.1016/1060-3743(95)90012-8 Islam, R., & Moushi, O. M. (2024). Gpt-4o: The cutting-edge advancement in multimodal LLM. Authorea Preprints. Jo, E., Epstein, D. A., Jung, H., & Kim, Y.-H. (2023). Understanding the benefits and challenges of deploying conversational AI leveraging large language models for public health intervention. Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems, 1–16. https://doi.org/10.1145/3544548.3581503 Jones, J. (2011). Using metadiscourse to improve coherence in academic writing. Language Education in Asia, 2(1), 1–14. Kim, L. C., & Lim, J. M.-H. (2013). Metadiscourse in English and Chinese research article introductions. Discourse Studies, 15(2), 129–146. https://doi.org/10.1177/1461445612471476 Kim, S. S., Kaplowitz, S., & Johnston, M. V. (2004). The effects of physician empathy on patient satisfaction and compliance. Evaluation & the Health Professions, 27(3), 237–251. https://doi.org/10.1177/0163278704267037 Kim, Y., Guo, L., Yu, B., & Li, Y. (2023). Can ChatGPT understand causal language in science claims? Proceedings of the 13th Workshop on Computational Approaches to Subjectivity, Sentiment, & Social Media Analysis, 379–389. https://doi.org/10.18653/v1/2023.wassa-1.33 Kojima, T., Gu, S. S., Reid, M., Matsuo, Y., & Iwasawa, Y. (2022). Large language models are zero-shot reasoners. Advances in Neural Information Processing Systems, 35, 22199–22213. Lee, S., Park, S. H., Kim, S., & Seo, M. (2025). Aligning to thousands of preferences via system message generalization. Advances in Neural Information Processing Systems, 37, 73783–73829. Lee, Y.-J., Lim, C.-G., & Choi, H.-J. (2022). Does GPT-3 generate empathetic dialogues? A novel in-context example selection method and automatic evaluation metric for empathetic dialogue generation. Proceedings of the 29th International Conference on Computational Linguistics, 669–683. Leilei, Z., & Fe, L. (2022). The pragmatic functions of the tilde “~” in China’s social media among youth groups. International Journal of Linguistics, Literature and. Translation, 5(12), 136–143. https://doi.org/10.32996/ijllt.2022.5.12.17 Li, C. N., & Thompson, S. A. (1981). Mandarin Chinese: A functional reference grammar. University of California Press. Li, Q., Li, P., Ren, Z., Ren, P., & Chen, Z. (2022). Knowledge bridging for empathetic dialogue generation. Proceedings of the AAAI Conference on Artificial Intelligence, 36(10), 10993–11001. https://doi.org/10.1609/aaai.v36i10.21347 Li, Y. (2023). A practical survey on zero-shot prompt design for in-context learning. arXiv preprint arXiv:2309.13205. https://doi.org/10.48550/arXiv.2309.13205 Lief, H. I., & Fox, R. C. (1963). Training for “detached concern” in medical students. In H. I. Lief, V. F. Lief, & N. R. Lief (Eds.), The psychological basis of medical practice (pp. 12–35). Harper & Row. Lin, C. Y., Wu, Y.-H., & Chen, A. L. (2021). Selecting the most helpful answers in online health question answering communities. Journal of Intelligent Information Systems, 57(2), 271–293. https://doi.org/10.1007/s10844-021-00640-1 Lin, J., Han, Z., Thomas, D. R., Gurung, A., Gupta, S., Aleven, V., & Koedinger, K. R. (2025). How can I get it right? using GPT to rephrase incorrect trainee responses. International Journal of Artificial Intelligence in Education, 35, 482–508. https://doi.org/10.1007/s40593-024-00408-y Ling, Y. (2023). Bio+ Clinical BERT, BERT Base, and CNN performance comparison for predicting drug-review satisfaction. arXiv preprint arXiv:2308.03782. https://doi.org/10.48550/arXiv.2308.03782 Liu, P., Yuan, W., Fu, J., Jiang, Z., Hayashi, H., & Neubig, G. (2023). Pre-train, prompt, and predict: A systematic survey of prompting methods in natural language processing. ACM computing surveys, 55(9), 1–35. https://doi.org/10.1145/3560815 Lloyd, M., Bor, R., & Noble, L. M. (2018). Clinical communication skills for medicine. Elsevier Health Sciences. Lorié, Á., Reinero, D. A., Phillips, M., Zhang, L., & Riess, H. (2017). Culture and non-verbal expressions of empathy in clinical settings: A systematic review. Patient Education and Counseling, 100(3), 411–424. https://doi.org/10.1016/j.pec.2016.09.018 Ma, W.-Y., & Chen, K.-J. (2003). Introduction to CKIP Chinese word segmentation system for the first international Chinese word segmentation bakeoff. Proceedings of the Second SIGHAN Workshop on Chinese Language Processing, 168–171. https://doi.org/10.3115/1119250.1119276 Martin, J. R., & White., P. R. R. (2005). The language of evaluation: Appraisal in English. Palgrave Macmillan. Min, S., Lyu, X., Holtzman, A., Artetxe, M., Lewis, M., Hajishirzi, H., & Zettlemoyer, L. (2022). Rethinking the role of demonstrations: What makes in-context learning work? In Y. Goldberg, Z. Kozareva, & Y. Zhang (Eds.), Proceedings of the 2022 conference on empirical methods in natural language processing (pp. 11048– 11064). Association for Computational Linguistics. https://doi.org/10.18653/v1/2022.emnlp-main.759 Mishra, S., Khashabi, D., Baral, C., Choi, Y., & Hajishirzi, H. (2021). Reframing instructional prompts to GPTk’s language. arXiv preprint arXiv:2109.07830. https://doi.org/10.48550/arXiv.2109.07830 Mousavi, R., Raghu, T., & Frey, K. (2020). Harnessing artificial intelligence to improve the quality of answers in online question-answering health forums. Journal of Management Information Systems, 37(4), 1073–1098. https://doi.org/10.1080/07421222.2020.1831775 Mu, C., Zhang, L. J., Ehrich, J., & Hong, H. (2015). The use of metadiscourse for knowledge construction in Chinese and English research articles. Journal of English for Academic Purposes, 20, 135–148. https://doi.org/10.1016/j.jeap.2015.09.003 Nambisan, P. (2011). Information seeking and social support in online health communities: Impact on patients’ perceived empathy. Journal of the American Medical Informatics Association, 18(3), 298–304. https://doi.org/10.1136/amiajnl-2010-000058 Oniani, D., & Wang, Y. (2020). A qualitative evaluation of language models on automatic question-answering for COVID-19. Proceedings of the 11th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics, 1–9. https://doi.org/10.1145/3388440.3412413 Parviainen, J., & Rantala, J. (2022). Chatbot breakthrough in the 2020s? An ethical reflection on the trend of automated consultations in health care. Medicine, Health Care and Philosophy, 25(1), 61–71. https://doi.org/10.1007/s11019-021-10049-w Pearson, W. S., & Abdollahzadeh, E. (2023). Metadiscourse in academic writing: A systematic review. Lingua, 293, 103561. https://doi.org/10.1016/j.lingua.2023.103561 Peters, G. (2021). Metadiscourse, materiality and morality in communication skills training with simulated patients. Communication & Medicine, 16(3), 251–266. https://doi.org/10.1558/cam.39725 Pollak, K. I., Alexander, S. C., Tulsky, J. A., Lyna, P., Coffman, C. J., Dolor, R. J., Gulbrandsen, P., & Østbye, T. (2011). Physician empathy and listening: Associations with patient satisfaction and autonomy. The Journal of the American Board of Family Medicine, 24(6), 665–672. https://doi.org/10.3122/jabfm.2011.06.110025 Pounds, G. (2011). Empathy as ‘appraisal’. Journal of Applied Linguistics and Professional Practice, 7(2), 139–162. https://doi.org/10.1558/japl.v7i2.145 Pounds, G. (2012). Enhancing empathic skills in clinical practice: A linguistic approach. International Journal of Work Organisation and Emotion, 5(2), 114–131. https://doi.org/10.1504/IJWOE.2012.049516 Qian, Y., Zhang, W.-N., & Liu, T. (2023). Harnessing the power of large language models for empathetic response generation: Empirical investigations and improvements. arXiv preprint arXiv:2310.05140. https://doi.org/10.48550/arXiv.2310.05140 Qiu, Y., Ding, S., Tian, D., Zhang, C., & Zhou, D. (2022). Predicting the quality of answers with less bias in online health question answering communities. Information Processing & Management, 59(6), 103112. https://doi.org/10.1016/j.ipm.2022.103112 Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., & Sutskever, I. (2019). Language models are unsupervised multitask learners. OpenAI. https://api.semanticscholar.org/CorpusID:160025533 Rahmanti, A. R., Yang, H.-C., Bintoro, B. S., Nursetyo, A. A., Muhtar, M. S., Syed-Abdul, S., & Li, Y.-C. J. (2022). Slimme, a chatbot with artificial empathy for personal weight management: System design and finding. Frontiers in Nutrition, 9, 870775. https://doi.org/10.3389/fnut.2022.870775 Reynolds, L., & McDonell, K. (2021). Prompt programming for large language models: Beyond the few-shot paradigm. Extended Abstracts of the 2021 CHI Conference on Human Factors in Computing Systems. https://doi.org/10.1145/3411763.3451760 Riess, H., Kelley, J. M., Bailey, R. W., Dunn, E. J., & Phillips, M. (2012). Empathy training for resident physicians: A randomized controlled trial of a neuroscience-informed curriculum. Journal of General Internal Medicine, 27(10), 1280–1286. https://doi.org/10.1007/s11606-012-2063-z Rivas, R., Montazeri, N., Le, N. X., & Hristidis, V. (2018). Automatic classification of online doctor reviews: Evaluation of text classifier algorithms. Journal of Medical Internet Research, 20(11), e11141. https://doi.org/10.2196/11141 Rizzi, D. A. (1994). Causal reasoning and the diagnostic process. Theoretical Medicine, 15, 315–333. https://doi.org/10.1007/BF01313345 Rosoł, M., Gąsior, J. S., Łaba, J., Korzeniewski, K., & Młyńczak, M. (2023). Evaluation of the performance of GPT-3.5 and GPT-4 on the Polish Medical Final Examination. Scientific Reports, 13(1), 20512. https://doi.org/10.1038/s41598-023-46995-z Russell, A. (2011). The Arab Spring extra-national information flows, social media and the 2011 Egyptian uprising. International Journal of Communication, 5, 10. Ruytenbeek, N., & Decock, S. (2024). Expressing and responding to customer (dis)satisfaction online: New insights from discourse and linguistic approaches. International Journal of Business Communication, 61(1), 3–17. https://doi.org/10.1177/23294884231199740 Schiffrin, D. (1980). Meta-talk: Organizational and evaluate brackets in discourse. Sociological inquiry, 50. https://doi.org/10.1111/j.1475-682X.1980.tb00021.x Searle, J. R. (1969). The structure of illocutionary acts. In Speech acts: An essay in the philosophy of language (pp. 54–71). Cambridge University Press. Senitan, M., Alhaiti, A. H., & Gillespie, J. (2018). Patient satisfaction and experience of primary care in Saudi Arabia: A systematic review. International Journal for Quality in Health Care, 30(10), 751–759. https://doi.org/10.1093/intqhc/mzy104 Smith, A. (2006). Cognitive empathy and emotional empathy in human behavior and evolution. The Psychological Record, 56(1), 3–21. https://doi.org/10.1007/BF03395534 Soltner, C., Giquello, J., Monrigal-Martin, C., & Beydon, L. (2011). Continuous care and empathic anaesthesiologist attitude in the preoperative period: Impact on patient anxiety and satisfaction. British Journal of Anaesthesia, 106(5), 680–686. https://doi.org/10.1093/bja/aer034 Stueber, K. (2019). Empathy. In E. N. Zalta (Ed.), The Stanford encyclopedia of philosophy (Fall 2019). Metaphysics Research Lab, Stanford University. https://plato.stanford.edu/archives/fall2019/entries/empathy/ Sun, S. (2011). Meta-analysis of cohen’s kappa. Health Services and Outcomes Research Methodology, 11, 145–163. https://doi.org/10.1007/s10742-011-0077-3 Tan, L., Le, M. K., Yu, C. C., Liaw, S. Y., Tierney, T., Ho, Y. Y., Lim, E., Lim, D., Ng, R., Ngeow, C., & Low, J. (2021). Defining clinical empathy: A grounded theory approach from the perspective of healthcare workers and patients in a multicultural setting. BMJ Open, 11(9), e045224. https://doi.org/10.1136/bmjopen-2020-045224 Tseng, M.-Y., & Zhang, G. (2018). Pragmeme, adaptability, and elasticity in online medical consultations. Journal of Pragmatics, 137, 40–56. https://doi.org/10.1016/j.pragma.2018.09.004 Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, Ł., & Polosukhin, I. (2017). Attention is all you need. Advances in Neural Informa- tion Processing Systems, 30. Vogel, D., Meyer, M., & Harendza, S. (2018). Verbal and non-verbal communication skills including empathy during history taking of undergraduate medical students. BMC Medical Education, 18(1), 157. https://doi.org/10.1186/s12909-018-1260-9 Wang, L., Xu, W., Lan, Y., Hu, Z., Lan, Y., Lee, R. K.-W., & Lim, E.-P. (2023). Plan-and-solve prompting: Improving zero-shot chain-of-thought reasoning by large language models. arXiv preprint arXiv:2305.04091. https://doi.org/10.48550/arXiv.2305.04091 Wei, J., Wang, X., Schuurmans, D., Bosma, M., Xia, F., Chi, E., Le, Q. V., Zhou, D., et al. (2022). Chain-of-thought prompting elicits reasoning in large language models. Advances in Neural Information Processing Systems, 35, 24824–24837. Wind, T. R., Rijkeboer, M., Andersson, G., & Riper, H. (2020). The COVID-19 pandemic: The ‘black swan’ for mental health care and a turning point for e-health. Internet Interventions, 20, 100317. https://doi.org/10.1016/j.invent.2020.100317 Wu, J., Zhang, G., Xing, Y., Liu, Y., Zhang, Z., Dong, Y., & Herrera-Viedma, E. (2023). A sentiment analysis driven method based on public and personal preferences with correlated attributes to select online doctors. Applied Intelligence, 53(16), 19093–19114. https://doi.org/10.1007/s10489-023-04485-9 Wynn, R., & Wynn, M. (2006). Empathy as an interactionally achieved phenomenon in psychotherapy: Characteristics of some conversational resources. Journal of pragmatics, 38(9), 1385–1397. https://doi.org/10.1016/j.pragma.2005.09.008 Xia, J. (2020). “Loving you”: Use of metadiscourse for relational acts in WeChat public account advertisements. Discourse, Context & Media, 37, 100416. https://doi.org/10.1016/j.dcm.2020.100416 Xie, Z. (2020). Two types of verb reduplications in Mandarin Chinese. Studies in Chinese Linguistics, 41(1), 73–108. https://doi.org/10.2478/scl-2020-0003 Xu, H., & Xia, D. (2023). Digital tildes (“~”) may convey more: analyzing innovative uses of tildes in Chinese WeChat messages. Language and Semiotic Studies, 9(3), 443–460. https://doi.org/10.1515/lass-2023-0009 Xu, Y., Wu, G., & Chen, Y. (2022). Predicting patients’ satisfaction with doctors in online medical communities: An approach based on XGBoost algorithm. Journal of Organizational and End User Computing (JOEUC), 34(4), 1–17. https://doi.org/10.4018/JOEUC.287571 Yang, N. (2021). Engaging readers across participants: A cross-interactant analysis of metadiscourse in letters of advice during the COVID-19 pandemic. Journal of Pragmatics, 186, 181–193. https://doi.org/10.1016/j.pragma.2021.10.017 Yang, X., Peynetti, E., Meerman, V., & Tanner, C. (2022). What GPT knows about who is who. arXiv preprint arXiv:2205.07407. https://doi.org/10.48550/arXiv.2205.07407 Zhang, Y. (2021). How doctors do things with empathy in online medical consultations in China: A discourse-analytic approach. Health Communication, 36(7), 816–825. https://doi.org/10.1080/10410236.2020.1712527 Zhang, Y., Lu, W., Ou, W., Zhang, G., Zhang, X., Cheng, J., & Zhang, W. (2020). Chinese medical question answer selection via hybrid models based on CNN and GRU. Multimedia Tools and Applications, 79, 14751–14776. https://doi. org/10.1007/s11042-019-7240-1 Zhou, R., & Li, S. (2023). A study on the persuasive function of metadiscourse in hotel responses to negative reviews on tripadvisor. English Language Teaching, 16(6), 1–55. https://doi.org/10.5539/elt.v16n6p55zh_TW