簡易檢索 / 詳目顯示
| 研究生： |
李家明 Li, Chia-Ming |
|---|---|
| 論文名稱： |
大型語言模型擬人化程度與訊息類型對線上保險投保決策之影響 Effects of LLM Chatbot Anthropomorphism and Message Type on Purchase Intention and Choice Closure in Online Insurance |
| 指導教授： |
簡士鎰
Chien, Shih-Yi |
| 口試委員: |
林斯寅
Lin, Szu-Yin 康藝晃 Kang, Yi-huang |
| 學位類別： |
碩士
Master |
| 系所名稱： |
商學院 - 資訊管理學系 Department of Management Information System |
| 論文出版年： | 2026 |
| 畢業學年度： | 114 |
| 語文別： | 英文 |
| 論文頁數： | 92 |
| 中文關鍵詞： | 保險科技 、大型語言模型 、擬人化 、訊息類型 、選擇閉合 |
| 外文關鍵詞： | InsurTech, Large Language Models (LLMs), Anthropomorphism, Message Type, Choice Closure |
| 相關次數： | 點閱：9 下載：0 |
| 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 |
隨著保險科技（InsurTech）與大型語言模型（Large Language Models, LLMs）快速發展，線上保險平台雖提升投保便利性，消費者仍可能因商品複雜、資訊不對稱與風險不確定性，產生理解困難、決策猶豫與信任不足。本研究探討 LLM 聊天機器人的擬人化設計與訊息呈現方式，如何與消費者於線上保險情境中的購買意願及選擇閉合相關，並檢視社會臨場感與信任所呈現的觀察性群組差異。本研究採 2（保險情境／固定呈現順序：長期個人傷害保險／短期旅遊平安保險）× 2（聊天機器人擬人化程度：高／低）× 2（訊息類型：敘事／結構化事實）混合實驗設計，納入 60 名有效受試者，結合問卷與眼動追蹤資料分析。結果顯示，高擬人化條件顯著提升社會臨場感。以受試者層級的平均分數進行分組後，高社會臨場感組呈現較高的整體信任；高整體信任組亦呈現較高的購買意願與選擇閉合。相較於敘事式訊息，事實式訊息帶來較高購買意願。擬人化程度與訊息類型則對選擇閉合未呈現顯著的實驗效果。眼動結果顯示，高擬人化條件下，受試者對頭像與輸入動畫位置的視覺注意力在描述上較高，但未達顯著。結果發現線上保險聊天機器人宜結合清楚、具體且可比較的結構化資訊，以及適度的人性化互動線索，以支持社會臨場感、信任與購買意願。
This study examines how LLM chatbot anthropomorphism and message type influence purchase intention and choice closure in online insurance. Using a 2 × 2 × 2 mixed design with 60 participants, the results showed that high anthropomorphism increased social presence, which was associated with greater trust, purchase intention, and choice closure. Factual messages produced higher purchase intention than narrative messages, while neither anthropomorphism nor message type significantly affected choice closure. These findings suggest that online insurance chatbots should provide clear, comparable information while using appropriate human-like cues to strengthen trust and support consumer decisions.
摘要 2
Abstract 3
Table of Contents 4
Tables 7
Figures 8
Chapter 1 INTRODUCTION 9
Chapter 2 RELATED WORK 16
2.1 LLM Chatbot Anthropomorphism 16
2.1.1 The Concept and Dimensions of Anthropomorphism 16
2.1.2 The Concept of Social Presence 19
2.2 The Concept of Trust 20
2.2.1 Social Presence and Trust 20
2.3 The Concept of Message Type 21
2.3.1 Narrative Messages 21
2.3.2 Factual Messages 23
2.3.3 The Effects of Message Type on Decision Outcomes 24
2.4 Purchase Intention and Choice Closure 25
2.4.1 Purchase Intention 25
2.4.2 Choice Closure 26
2.4.3 Trust Differences in Purchase Intention and Choice Closure 26
2.5 Research Framework and Hypotheses Summary 27
Chapter 3 LLM CHATBOT SETUP AND PILOT EVALUATION 29
3.1 Experimental Design and Research Framework 29
3.2 Experimental Context and System Development 30
3.2.1 Experimental Scenario 31
3.2.2 Underlying System Architecture: LLM (Qwen2.5:14B) 32
3.3 Variable Manipulations 34
3.3.1 Manipulation of Anthropomorphism 34
3.3.2 Manipulation of Message Type 35
3.4 Pilot Test Design and Manipulation Checks 36
3.4.1 Pilot Experiment Design and Participants 37
3.4.2 Manipulation-Check Measures 37
3.4.3 Data Analysis and Criteria for Manipulation Checks 38
Chapter 4 MAIN STUDY DESIGN 42
4.1 Research Purpose and Overview 42
4.2 Experimental Design and Participants 42
4.3 Experimental Procedure 44
4.3.1 Eye-Tracking Equipment and Data Collection 45
4.4 Questionnaire Measures 46
4.4.1 Purchase Intention 47
4.4.2 Choice Closure 47
4.4.3 Social Presence 47
4.4.4 Trust 48
Chapter 5 RESULTS 49
5.1 Valid Sample and Allocation of Experimental Conditions 49
5.2 Scale Reliability and Statistical Tests 50
5.2.1 Scale Reliability 50
5.2.2 Hypothesis Testing Methods 51
5.3 Mixed-Design ANOVA Results 52
5.3.1 Mixed-Design Analysis of Variance for Purchase Intention 52
5.3.2 Mixed-Design Analysis of Variance for Choice Closure 53
5.3.3 Mixed-Design Analysis of Variance for Social Presence 54
5.3.4 Mixed-Design Analysis of Variance for Cognitive Trust 56
5.3.5 Mixed-Design Analysis of Variance for Affective Trust 57
5.4 ANOVA Analyses of Group Differences 58
5.4.1 H2: Observed Differences in Trust by Social-Presence Group 59
5.4.2 H4a: Observed Differences in Purchase Intention by Trust Group 59
5.4.3 H4b: Observed Differences in Choice Closure by Trust Group 59
5.5 Hypothesis Verification 60
5.5.1 H1: High Anthropomorphism Will Increase Social Presence 60
5.5.2 H2: Observed Differences in Trust by Social-Presence Group 60
5.5.3 H3a: Narrative Messages Will Increase Purchase Intention 61
5.5.4 H3b: Narrative Messages Increase Choice Closure 61
5.5.5 H4a: Observed Differences in Purchase Intention by Trust Group 62
5.5.6 H4b: Observed Differences in Choice Closure by Trust Group 62
5.6 Eye-Tracking Results 63
5.6.1 Eye-Tracking Data Availability and Analytical Approach 63
5.6.2 Visual Attention to the Avatar and Typing Indicator 64
5.7 Summary of Research Findings 67
Chapter 6 GENERAL DISCUSSION 69
6.1 Theoretical Insights 70
6.2 Managerial Implications 74
6.3 Limitations and Future Research 77
REFERENCE 83
Appendix A 87
Appendix B 89
Appendix C 90
Appendix D 91
Appendix E 92
Ajzen, I. (1991). The theory of planned behavior. Organizational Behavior and Human Decision Processes, 50(2), 179–211.
Airenti, G. (2015). The cognitive bases of anthropomorphism: From relatedness to empathy. International Journal of Social Robotics, 7(1), 117–127.
Araujo, T. (2018). Living up to the chatbot hype: The influence of anthropomorphic design cues and communicative agency framing on conversational agent and company perceptions. Computers in Human Behavior, 85, 183–189.
Bradley, A., Hastings, J., & Ahmed, K. M. (2025). Introducing Axlerod: An LLM-based chatbot for assisting independent insurance agents. In 2025 IEEE Cyber Awareness and Research Symposium (CARS) (pp. 1–6). IEEE.
Braddock, K., & Dillard, J. P. (2016). Meta-analytic evidence for the persuasive effect of narratives on beliefs, attitudes, intentions, and behaviors. Communication Monographs, 83(4), 446–467.
Cai, N., Gao, S., & Yan, J. (2024). How the communication style of chatbots influences consumers’ satisfaction, trust, and engagement in the context of service failure. Humanities and Social Sciences Communications, 11, Article 687.
Cao, L., Yang, Q., & Yu, P. S. (2021). Data science and AI in FinTech: An overview. International Journal of Data Science and Analytics, 12(2), 81–99.
Chattaraman, V., Kwon, W. S., Gilbert, J. E., & Ross, K. (2019). Should AI-based conversational digital assistants employ social- or task-oriented interaction style? A task-competency and reciprocity perspective for older adults. Computers in Human Behavior, 90, 315–330.
Chien, S.-Y., Wang, Y.-F., Cheng, K.-T., & Chen, Y.-C. (2025). Comparative study of XAI perception between eastern and western cultures. International Journal of Human–Computer Interaction, 41(17), 11192–11208.
Cohn, M., Pushkarna, M., Olanubi, G. O., Moran, J. M., Padgett, D., Mengesha, Z., & Heldreth, C. (2024, May). Believing anthropomorphism: Examining the role of anthropomorphic cues on trust in large language models. In Extended Abstracts of the CHI Conference on Human Factors in Computing Systems (pp. 1-15).
Diallo, M. F. (2012). Effects of store image and store brand price-image on store brand purchase intention: Application to an emerging market. Journal of Retailing and Consumer Services, 19(3), 360-367.
Deck, C., & Jahedi, S. (2015). The effect of cognitive load on economic decision making: A survey and new experiments. European Economic Review, 78, 97–119.
Eling, M., & Lehmann, M. (2018). The impact of digitalization on the insurance value chain and the insurability of risks. The Geneva Papers on Risk and Insurance—Issues and Practice, 43(3), 359–396.
Epley, N., Waytz, A., & Cacioppo, J. T. (2007). On seeing human: A three-factor theory of anthropomorphism. Psychological Review, 114(4), 864–886.
Escalas, J. E. (2004). Narrative processing: Building consumer connections to brands. Journal of Consumer Psychology, 14(1–2), 168–180.
Escalas, J. E. (2007). Self-referencing and persuasion: Narrative transportation versus analytical elaboration. Journal of Consumer Research, 33(4), 421–429.
Feine, J., Gnewuch, U., Morana, S., & Maedche, A. (2019). A taxonomy of social cues for conversational agents. International Journal of Human-Computer Studies, 132, 138–161.
Gnewuch, U., Morana, S., Adam, M. T. P., & Maedche, A. (2018). Faster is not always better: Understanding the effect of dynamic response delays in human-chatbot interaction. In Proceedings of the 26th European Conference on Information Systems (ECIS).
Go, E., & Sundar, S. S. (2019). Humanizing chatbots: The effects of visual, identity and conversational cues on humanness perceptions. Computers in Human Behavior, 97, 304–316.
Green, M. C., & Appel, M. (2024). Narrative transportation: How stories shape how we see ourselves and the world. In B. Gawronski (Ed.), Advances in experimental social psychology (Vol. 70, pp. 1–82). Academic Press.
Green, M. C., & Brock, T. C. (2000). The role of transportation in the persuasiveness of public narratives. Journal of Personality and Social Psychology, 79(5), 701–721.
Gu, Y., Botti, S., & Faro, D. (2013). Turning the page: The impact of choice closure on satisfaction. Journal of Consumer Research, 40(2), 268–283.
Gu, Y., Botti, S., & Faro, D. (2018). Seeking and avoiding choice closure to enhance outcome satisfaction. Journal of Consumer Research, 45(4), 792–809.
Guidroz, T., Ardila, D., Li, J., Mansour, A., Jhun, P., Gonzalez, N., Ji, X., Sanchez, M., Kakarmath, S., Bellaiche, M. M. J., Garrido, M. Á., Ahmed, F., Choudhary, D., Hartford, J., Xu, C., Serrano Echeverria, H. J., Wang, Y., Shaffer, J., Cao, E. Y., . . . Duong, Q. (2025). LLM-based text simplification and its effect on user comprehension and cognitive load. arXiv.
Johnson, D., & Grayson, K. (2005). Cognitive and affective trust in service relationships. Journal of Business Research, 58(4), 500–507.
Klein, K., & Martinez, L. F. (2023). The impact of anthropomorphism on customer satisfaction in chatbot commerce: An experimental study in the food sector. Electronic Commerce Research, 23(4), 2789–2825.
Komiak, S. Y. X., & Benbasat, I. (2006). The effects of personalization and familiarity on trust and adoption of recommendation agents. MIS Quarterly, 30(4), 941–960.
Li, M., & Wang, R. (2023). Chatbots in e-commerce: The effect of chatbot language style on customers’ continuance usage intention and attitude toward brand. Journal of Retailing and Consumer Services, 71, Article 103209.
Lien, N. H., & Chen, Y. L. (2013). Narrative ads: The effect of argument strength and story format. Journal of Business Research, 66(4), 516–522.
Mitchell, V.-W. (1999). Consumer perceived risk: Conceptualisations and models. European Journal of Marketing, 33(1/2), 163–195. https://doi.org/10.1108/03090569910249229
Nass, C., Steuer, J., & Tauber, E. R. (1994). Computers are social actors. In Conference companion on human factors in computing systems (pp. 72–78). Association for Computing Machinery.
Nguyen, M., Casper Ferm, L.-E., Quach, S., Pontes, N., & Thaichon, P. (2023). Chatbots in frontline services and customer experience: An anthropomorphism perspective. Psychology & Marketing, 40(11), 2201–2225.
Pizzi, G., Vannucci, V., Mazzoli, V., & Donvito, R. (2023). I, chatbot! The impact of anthropomorphism and gaze direction on willingness to disclose personal information and behavioral intentions. Psychology & Marketing, 40(7), 1372–1387.
Schwarcz, D., Cude, B. J., Logue, K. D., & Marquez Alcala, G. (2026). Read but not understood? An empirical analysis of consumer comprehension in homeowners insurance. Virginia Law Review, 112(3), 727–814.
Spears, N., & Singh, S. N. (2004). Measuring attitude toward the brand and purchase intentions. Journal of Current Issues & Research in Advertising, 26(2), 53–66.
Toader, D.-C., Boca, G., Toader, R., Măcelaru, M., Toader, C., Ighian, D., & Rădulescu, A. T. (2020). The effect of social presence and chatbot errors on trust. Sustainability, 12(1), Article 256.
van Laer, T., de Ruyter, K., Visconti, L. M., & Wetzels, M. (2014). The extended transportation-imagery model: A meta-analysis of the antecedents and consequences of consumers’ narrative transportation. Journal of Consumer Research, 40(5), 797–817.
Zhang, M., Nazir, M. S., Farooqi, R., & Ishfaq, M. (2022). Moderating role of information asymmetry between cognitive biases and investment decisions: A mediating effect of risk perception. Frontiers in Psychology, 13, Article 828956.
