簡易檢索 / 詳目顯示

研究生: 夏柏仁
Hsia, Po-Jen
論文名稱: 對話式系統中的決策:聊天機器人的使用者回覆時間與選擇超載
Decision-Making in Conversational Systems: User Response Time and Choice Overload on Chatbots
指導教授: 雷松亞
Ray, Soumya
口試委員: 林福仁
Lin, Fu-Ren
王俊程
Wang, Jyun-Cheng
學位類別: 碩士
Master
系所名稱: 科技管理學院 - 服務科學研究所
Institute of Service Science
論文出版年: 2018
畢業學年度: 106
語文別: 英文
論文頁數: 52
中文關鍵詞: 對話式系統聊天機器人決策使用行為系統反應時間使用者回覆時間
外文關鍵詞: conversational system, chatbot, decision-making, usage behavior, system response time, user response time
相關次數: 點閱:1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
  • 對話式系統近年來因為大量的智慧型裝置、物聯網、人工智慧的使用,而逐漸 成長。對話式系統著眼於和人類溝通以及模仿人類對話的互動。這類的互動使得對 話式系統和傳統的電腦介面有著根本的不同。在本研究中,我們試圖在聊天機器人 中尋找使用者的決策是否受對話介面的限制所影響。我們為 AsiaYo 這間台灣旅遊 訂房平台新創設計了一個電子商務聊天機器人。在這項合作中,我們建立了一個能 夠邀請顧客和聊天機器人對話以尋找理想中未來於亞洲度假住宿的臉書聊天機器 人。由於這套聊天機器人可以視為其傳統網站或手機應用程式的替代平台,我們深 入調查很多過去在這些平台中的一些假設是否一樣為真,特別是針對系統延遲以及 顯示項目的多寡是否影響使用者的使用經驗的部分。
    本研究的結果顯示使用者對於聊天機器人中的系統延遲以及選項多寡受相當程
    度的影響。我們亦在本研究中藉由上述的發現提供數個基於理論以及實務上的洞悉
    及建議以作為未來聊天機器人中的使用者經驗之參考。


    Conversational systems are highly growing recently with the increasing use of mobile devices, Internet of Things, and artificial intelligence. Conversational systems aim to communicate with humans in a dialogue flow style and imitate human-to-human interaction. This style of interaction makes conversational systems fundamentally different from traditional computer systems. In this study we are looking for how limitations of conversational interface impacts decision- making of users in chatbot context. We’ve designed an e-commerce chatbot for AsiaYo, a Taiwanese e-commerce firm that provides an accommodation platform for travelers. In collaboration with AsiaYo, we created a Facebook chatbot that invited potential customers to engage in a conversation to find an accommodation for an upcoming or future vacation in Asia. Given that e- commerce chatbots serve as an alternative to traditional menu-driven website and mobile applications, we investigated whether many of the traditional assumptions held true in a conversational setting. We wondered how the latency and limited display options of chatbots might affect users.
    The result shows that users are affected in interesting ways by latency of system and number of options displayed in chatbot. We then provided several theoretical and practical insights base on these relations to help improve future user experience design for chatbots.

    1 Introduction ............................................................................................................10 2 Let’s Chat About Chatbots........................................................................................12 2.1 History of Chatbots ............................................................................................... 12 2.2 Research about Chatbots ...................................................................................... 13 2.3 Challenges of Researching Chatbots ...................................................................... 15 3 Decision Making on Chatbots ..................................................................................16 3.1 System Response Time .......................................................................................... 17 3.2 Choice Overload .................................................................................................... 19 4 Building a Chatbot Research System ........................................................................26 4.1 Chatbot Platforms ................................................................................................. 26 4.2 Our Chatbot System Architecture .......................................................................... 26 5 Study Design............................................................................................................29 5.1 Experiment Design ................................................................................................ 29 5.2 Variables ............................................................................................................... 30 5.2.1 Independent Variables......................................................................................... 30 5.2.2 Dependent Variables............................................................................................ 31 5.3 Experiment Procedure........................................................................................... 31 6 Data Analysis and Results ........................................................................................33 6.1 System Response Time .......................................................................................... 33 6.2 Number of Filters Tried.......................................................................................... 35 6.3 Post-hoc survey ..................................................................................................... 42 7 Discussion ...............................................................................................................44 7.1 System Response Time & User Response Time ...................................................... 44 7.2 Choice Overload in Chatbots ................................................................................. 45 8 Limitations ..............................................................................................................47 9 Future Work ............................................................................................................48 9.1 Detailed Study of Chatbot Conversation Flow........................................................48 9.2 Designing Flexible Workflow for Chatbots ............................................................. 49 10 References.............................................................................................................50

    Arnold, S. J., Oum, T. H., & Tigert, D. J. (1983). Determinant attributes in retail patronage: seasonal, temporal, regional, and international comparisons. Journal of Marketing Research, 149-157.
    Ball, G., & Breese, J. (2000). Emotion and personality in a conversational agent. Embodied conversational agents, 189-219.
    Bechwati, N. N., & Xia, L. (2003). Do computers sweat? The impact of perceived effort of online decision aids on consumers’ satisfaction with the decision process. Journal of Consumer Psychology, 13(1-2), 139-148.
    Boies, S. J. (1974). User behavior on an interactive computer system. IBM Systems Journal, 13(1), 2-18.
    Buehler, R., Griffin, D., & Ross, M. (1994). Exploring the" planning fallacy": Why people underestimate their task completion times. Journal of personality and social psychology, 67(3), 366.
    Butler, T. W. (1983). Computer response time and user performance. Paper presented at the Proceedings of the SIGCHI Conference on Human Factors in Computing Systems, Boston, Massachusetts, USA.
    Chai, J., Lin, J., Zadrozny, W., Ye, Y., Budzikowska, M., Horvath, V., . . . Wolf, C. (2000).
    Comparative evaluation of a natural language dialog based system and a menu driven system for information access: a case study. Paper presented at the Content-Based Multimedia Information Access - Volume 2, Paris, France.
    Coniam, D. (2008). Evaluating the language resources of chatbots for their potential in English as a second language. ReCALL, 20(1), 98-116.
    Guynes, J. L. (1988). Impact of system response time on state anxiety. Commun. ACM, 31(3), 342-347. doi:10.1145/42392.42402
    Hollander, S. C., & Rassuli, K. M. (1999). Shopping with other people's money: The marketing management implications of surrogate-mediated consumer decision making. The Journal of Marketing, 102-118.
    Hoxmeier, J. A., & DiCesare, C. (2000). System response time and user satisfaction: An experimental study of browser-based applications. AMCIS 2000 Proceedings, 347.
    Huang, J., Zhou, M., & Yang, D. (2007). Extracting Chatbot Knowledge from Online Discussion Forums. Paper presented at the IJCAI.
    Hutchinson, J. M. (2005). Is more choice always desirable? Evidence and arguments from leks, food selection, and environmental enrichment. Biological reviews, 80(1), 73- 92.
    Iyengar, S. S., & Lepper, M. R. (2000). When choice is demotivating: Can one desire too much of a good thing? Journal of personality and social psychology, 79(6), 995.
    Iyengar, S. S., Wells, R. E., & Schwartz, B. (2006). Doing better but feeling worse: Looking for the “best” job undermines satisfaction. Psychological Science, 17(2), 143- 150.
    Jessup, R. K., Veinott, E. S., Todd, P. M., & Busemeyer, J. R. (2009). Leaving the store empty-handed: Testing explanations for the too-much-choice effect using decision field theory. Psychology & Marketing, 26(3), 299-320.
    Kahn, B. E., & Lehmann, D. R. (1991). Modeling choice among assortments.
    Lee, J., & Geistfeld, L. V. (1998). Enhancing consumer choice: are we making appropriate recommendations? Journal of Consumer Affairs, 32(2), 227-250.
    Luger, E., & Sellen, A. (2016). Like having a really bad PA: the gulf between user expectation and experience of conversational agents. Paper presented at the Proceedings of the 2016 CHI Conference on Human Factors in Computing Systems.
    March, J. G. (1978). Bounded rationality, ambiguity, and the engineering of choice. The Bell Journal of Economics, 587-608.
    Miller, R. B. (1968). Response time in man-computer conversational transactions. Paper presented at the Proceedings of the December 9-11, 1968, fall joint computer conference, part I.
    Mogilner, C., Rudnick, T., & Iyengar, S. S. (2008). The mere categorization effect: How the presence of categories increases choosers' perceptions of assortment variety and outcome satisfaction. Journal of Consumer Research, 35(2), 202-215.
    Morkes, J., Kernal, H. K., & Nass, C. (1999). Effects of Humor in Task-Oriented Human-Computer Interaction and Computer-Mediated Communication: A Direct Test of SRCT Theory. Human–Computer Interaction, 14(4), 395-435. doi:10.1207/S15327051HCI1404_2
    Mowen, J. C., & Grove, S. J. (1983). Search behavior, price paid and the comparison other an equity theory analysis of post–purchase satisfaction. International Fare in Consumer Satisfaction and Complaining Behaviofr Bloomington: Indiana University School of Business.
    Park, J.-Y., & Jang, S. S. (2013). Confused by too many choices? Choice overload in tourism. Tourism Management, 35, 1-12.
    Payne, J. W., Bettman, J. R., & Johnson, E. J. (1993). The adaptive decision maker: Cambridge University Press.
    Reutskaja, E., & Hogarth, R. M. (2009). Satisfaction in choice as a function of the
    number of alternatives: When “goods satiate”. Psychology & Marketing, 26(3), 197-203. Rotter, J. B. (1966). Generalized expectancies for internal versus external control of
    reinforcement. Psychological monographs: General and applied, 80(1), 1.
    Saito, M., & Ohmura, K. (1998). A cognitive model for searching for III-defined
    targets on the Web: the relationship between search strategies and user satisfaction. Paper presented at the Proceedings of the 21st annual international ACM SIGIR conference on Research and development in information retrieval, Melbourne, Australia.
    Scheibehenne, B., Greifeneder, R., & Todd, P. M. (2010). Can there ever be too many options? A meta-analytic review of choice overload. Journal of Consumer Research, 37(3), 409-425.
    Schwartz, B. (2000). Self-determination: The tyranny of freedom. American psychologist, 55(1), 79.
    Shawar, B. A., & Atwell, E. (2003). Using the Corpus of Spoken Afrikaans to generate an Afrikaans chatbot. Southern African Linguistics and Applied Language Studies, 21(4), 283-294.
    Shawar, B. A., & Atwell, E. (2007). Chatbots: are they really useful? Paper presented at the Ldv Forum.
    Shneiderman, B. (1984). Response time and display rate in human performance with computers. ACM Computing Surveys (CSUR), 16(3), 265-285.
    Simonson, I. (1990). The effect of purchase quantity and timing on variety-seeking behavior. Journal of Marketing Research, 150-162.
    Taylor, S. E. (1989). Positive illusions: Creative self-deception and the healthy mind: Basic Books.
    Taylor, S. E., & Brown, J. D. (1988). Illusion and well-being: a social psychological perspective on mental health. Psychological bulletin, 103(2), 193.
    Weizenbaum, J. (1966). ELIZA—a computer program for the study of natural language communication between man and machine. Communications of the ACM, 9(1), 36-45.
    Zamora, J. (2017). Rise of the chatbots: Finding a place for artificial intelligence in India and US. Paper presented at the Proceedings of the 22nd International Conference on Intelligent User Interfaces Companion.

    QR CODE