數位平台日益依賴推薦訊息協助使用者處理複雜資訊，推薦訊息已不只是單純提供選項，更能針對推薦形成的原因以及推薦來自於演算法或人類，提供啟發式推薦來源線索（Heuristic Source Cues），進而影響使用者對推薦所感知到的推薦品質與採納意願。隨著基於大型語言模型（Large Language Models, LLM）的推薦系統逐漸普及，推薦內容開始可以透過自然語言對話介面呈現，這使得過去關於推薦來源與訊息呈現方式或框架（Framing）如何影響使用者判斷的理論需重新檢視。過去研究多著重於提升推薦準確性與改善推薦解釋機制，較少探討推薦訊息的呈現框架如何影響使用者感受。在面對推薦結果時，使用者在評估推薦結果時，往往不會直接分析底層推薦邏輯，而會依賴推薦來源線索（如演算法分析或其他使用者偏好）形成判斷；同時，行為決策研究也指出，相同資訊以不同框架呈現，例如強調獲益或避免損失，也會導致使用者產生不同的評估結果。然而在LLM對話式推薦情境中，推薦來源與訊息呈現框架如何分別及共同影響使用者評估仍缺乏深入探討。本研究透過模擬基於LLM對話式推薦介面，探討推薦來源（來自演算法分析或相似需求使用者選擇的推薦來源）與訊息呈現框架（強調獲益或損失）對使用者感知的推薦訊息品質、對推薦訊息的信任及採納意願的影響。最終，研究結果顯示訊息框架對感知推薦品質、信任與推薦採納意願具有顯著影響，其中強調獲益的訊息呈現較強調損失的好，而推薦來源的影響較為有限而不顯著。總結本研究，在LLM推薦環境中，如何呈現推薦內容可能比推薦來源本身更能影響使用者判斷。本研究擴展推薦系統與決策行為相關研究於LLM情境中的應用，並提供對話式推薦系統設計之實務建議。

Digital platforms increasingly rely on recommendation messages to help users evaluate alternatives. Beyond suggesting options, these messages provide heuristic source cues indicating why recommendations are made and whether they originate from algorithms or humans. As LLM-based recommender systems increasingly deliver recommendations through conversational interfaces, existing theories of heuristic cues and message framing require reexamination. Prior research has focused on recommendation accuracy and explanation mechanisms, while paying less attention to how message framing shapes user perceptions. Users often rely on heuristic source cues, rather than underlying recommendation logic, when evaluating recommendations, whereas behavioral decision research suggests that gain–loss framing also influences evaluations. However, little is known about how heuristic source cues and message framing separately and jointly affect user evaluations in LLM-based conversational recommendation contexts. This study investigates how heuristic source cues (algorithmic vs. peer-based) and gain–loss framing affect perceived recommendation quality, trust, and intention to follow recommendations. Results show that message framing significantly improves perceived recommendation quality, trust, and intention to follow recommendations, with gain framing outperforming loss framing, whereas heuristic source cues have limited and nonsignificant effects. Overall, in LLM-based recommendation environments, recommendation presentation appears more influential than source attribution in shaping user judgments. This study extends recommender system and behavioral decision research to LLM contexts and provides practical implications for conversational recommender system design.

Acharya, N., Sassenberg, A.-M., & Soar, J. (2022). Consumers’ Behavioural Intentions to Reuse Recommender Systems: Assessing the Effects of Trust Propensity, Trusting Beliefs and Perceived Usefulness. Journal of Theoretical and Applied Electronic Commerce Research, 18(1), 55–78.
Adomavicius, G., & Tuzhilin, A. (2005). Toward the next generation of recommender systems: A survey of the state-of-the-art and possible extensions. IEEE Transactions on Knowledge and Data Engineering, 17(6), 734–749.
Bogdan, A., Dospinescu, N., & Dospinescu, O. (2025). Beyond Credibility: Understanding the Mediators Between Electronic Word-of-Mouth and Purchase Intention (arXiv:2504.05359). ArXiv.
Chaiken, S. (1980). Heuristic versus systematic information processing and the use of source versus message cues in persuasion. Journal of personality and social psychology, 39(5), 752.
Chang, K. C., Hsu, C. L., Chen, M. C., & Kuo, N. T. (2019). How a branded website creates customer purchase intentions. Total quality management & business excellence, 30(3-4), 422-446.
Chen, D. & Liang, H. (2006) Shaping consumer perception to motivate online shopping: a prospect theory perspective. Proceedings of the Fifth Annual Workshop on HCI Research in MIS, Milwaukee, WI, USA. Shopping: A Prospect Theory Perspective.
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.
Dietvorst, B. J., Simmons, J. P., & Massey, C. (2015). Algorithm Aversion: People Erroneously Avoid Algorithms After Seeing Them Err.
Gai, P. J., & Klesse, A. K. (2019). Making recommendations more effective through framings: Impacts of user-versus item-based framings on recommendation click-throughs. Journal of Marketing, 83(6), 61-75.
Gao, C., Lei, W., He, X., De Rijke, M., & Chua, T.-S. (2021). Advances and challenges in conversational recommender systems: A survey. AI Open, 2, 100–126.
Gedikli, F., Jannach, D., & Ge, M. (2014). How should I explain? A comparison of different explanation types for recommender systems. International Journal of Human-Computer Studies, 72(4), 367–382.
Gigerenzer, G., & Gaissmaier, W. (2011). Heuristic Decision Making. Annual Review of Psychology, 62(1), 451–482.
Guo, X. (2025). Framing Effects on Consumer Decision-Making in Online Retail. Highlights in Business, Economics and Management.
Herlocker, J. L., Konstan, J. A., & Riedl, J. (2000). Explaining collaborative filtering recommendations. Proceedings of the 2000 ACM Conference on Computer Supported Cooperative Work, CSCW ’00, 241–250.
Indrawati, Putri Yones, P. C., & Muthaiyah, S. (2023). eWOM via the TikTok application and its influence on the purchase intention of somethinc products. Asia Pacific Management Review, 28(2), 174–184.
Jannach, D., Resnick, P., Tuzhilin, A., & Zanker, M. (2016). Recommender systems—Beyond matrix completion. Commun. ACM, 59(11), 94–102.
Kahneman, D. (2011). Thinking, fast and slow. macmillan.
Kumar, S., Stacia, J. C., Suriana, Y., Sari, D., & Hasan, M. (2020). Website Quality and Purchase Intention: The Role of Participation, E-Wom, and Trust. AFEBI Management and Business Review, 5(2), 1.
Lee, J. D., & See, K. A. (2004). Trust in Automation: Designing for Appropriate Reliance. Human Factors, 46(1), 50–80.
Lee, H. C., Liu, S. F., & Cheng, Y. C. (2018). Positive or negative? The influence of message framing, regulatory focus, and product type. International Journal of Communication, 12, 18-18.
Lee, Y., Chen, A. N., & Wang, W. (2025). Push it cross the finish line—designing online interfaces to induce choice closure at the postdecision prepurchase stage. Information Systems Research, 36(3), 1821-1845.
Leibenstein, H. (1950). Bandwagon, Snob, and Veblen Effects in the Theory of Consumers’ Demand. The Quarterly Journal of Economics, 64(2), 183.
Levin, I. P., Schneider, S. L., & Gaeth, G. J. (1998). All Frames Are Not Created Equal: A Typology and Critical Analysis of Framing Effects. Organizational Behavior and Human Decision Processes, 76(2), 149–188.
Liao, M., & Sundar, S. S. (2022). When E-Commerce Personalization Systems Show and Tell: Investigating the Relative Persuasive Appeal of Content-Based versus Collaborative Filtering. Journal of Advertising, 51(2), 256–267.
Liu, W., & Wang, Y. (2025). Evaluating Trust in Recommender Systems: A User Study on the Impacts of Explanations, Agency Attribution, and Product Types. International Journal of Human–Computer Interaction, 41(2), 1280–1292.
Logg, J. M., Minson, J. A., & Moore, D. A. (2019). Algorithm appreciation: People prefer algorithmic to human judgment. Organizational Behavior and Human Decision Processes, 151, 90–103.
Mazzù, M. F., Andria, A., Baccelloni, A., & De Angelis, M. (2025). The impact of humans vs. AI recommendation on consumer reactions to products exposure. Electronic Commerce Research.
Qahri-Saremi, H., & Montazemi, A. R. (2019). Factors affecting the adoption of an electronic word of mouth message: A meta-analysis. Journal of Management Information Systems, 36(3), 969-1001.
Petty, R. E., & Cacioppo, J. T. (1986). The elaboration likelihood model of persuasion. In Advances in experimental social psychology (Vol. 19, pp. 123-205). Academic Press.
Putri Ramdhani, A., Zulfiani, I., Putrika Iwank, K., & Hendriana, E. (2025). Influence of EWOM, Perceived Risk and Trust on Purchase Intention in M-Commerce. International Journal of Scientific Research and Management (IJSRM), 13(08), 9510–9529.
Segev, S., Fernandes, J., & Wang, W. (2015). The Effects of Gain Versus Loss Message Framing and Point of Reference on Consumer Responses to Green Advertising. Journal of Current Issues & Research in Advertising, 36(1), 35–51.
Sinha, R. R., & Swearingen, K. (2001). Comparing recommendations made by online systems and friends. DELOS, 106(1), 1-6.
Sun, R., Li, X., Akella, A., & Konstan, J. A. (2024). Large Language Models as Conversational Movie Recommenders: A User Study (arXiv:2404.19093). arXiv.
Sun, Z., Fu, S., & Jiang, T. (2022). Gain-framed product descriptions are more appealing to elderly consumers in live streaming E-commerce: Implications from a controlled experiment. Data and Information Management, 6(4), 100022.
Tintarev, N., & Masthoff, J. (2007). A Survey of Explanations in Recommender Systems. 2007 IEEE 23rd International Conference on Data Engineering Workshop, 801–810.
Tversky, A., & Kahneman, D. (1981). The framing of decisions and the psychology of choice. science, 211(4481), 453-458.
Unger, F., & Steul-Fischer, M. (2020). The effect of message framing and the presentation of health vs. Social consequences on health risk perception. Zeitschrift Für Die Gesamte Versicherungswissenschaft, 109(5), 399–411.
Wu, L., Zheng, Z., Qiu, Z., Wang, H., Gu, H., Shen, T., Qin, C., Zhu, C., Zhu, H., Liu, Q., Xiong, H., & Chen, E. (2024). A Survey on Large Language Models for Recommendation(arXiv:2305.19860). arXiv.
Xu, N., & Wang, H. (2018). Research on Impact of Recommenders and Recommended Information on Consumers’ Purchase Intention in Social E-commerce. Proceedings of the 2018 International Seminar on Education Research and Social Science (ISERSS 2018). 2018 International Seminar on Education Research and Social Science (ISERSS 2018).
Zhao, Y., Wang, L., Tang, H., & Zhang, Y. (2020). Electronic word-of-mouth and consumer purchase intentions in social e-commerce. Electronic Commerce Research and Applications, 41, 100980.
Zhao, Z., Fan, W., Li, J., Liu, Y., Mei, X., Wang, Y., Wen, Z., Wang, F., Zhao, X., Tang, J., & Li, Q. (2024). Recommender Systems in the Era of Large Language Models (LLMs). IEEE Transactions on Knowledge and Data Engineering, 36(11), 6889–6907.