通訊軟體盛行，再加上自然語言處理的進步，人工智慧的應用又以聊天機器 人更為備受關注。有圖書館將聊天機器人導入，以提供新式的即時數位參考服務， 解決人工即時參考服務的問題。本研究目的在於建置國立臺灣師範大學(簡稱臺 師大)圖書館參考諮詢機器人並調查其使用評價。
本研究建置之參考諮詢機器人採用臺師大圖書館參考問答紀錄與常問問答 集作為問答語料，LINE Bot 作為開發平台，以 Python 程式語言編寫程式，並使 用 Jieba 進行中文斷詞、提取關鍵字，運用 Dice 係數計算問題與關鍵字相似度比 對，Beautiful Soup 協助擷取臺師大圖書館網站與館藏系統資訊，達成擁有館藏 查詢、開館查詢與問答語料庫回覆三大功能之參考諮詢機器人。
使用評估測試方面，請十名臺師大學生執行以問答語料中歸納之五個分類加 上館藏與開館查詢功能，設計而成的七項任務，依據機器人之回覆給予五分量表 滿意度。結果顯示，整體而言受測者對於參考諮詢機器人之回覆感到滿意，提問 之回覆正確率為 70%，系統中的回覆正確率則為 82.86%，滿意度較高的任務回 覆，其正確率也較高，唯獨任務五—針對「資源查詢指引」類別進行提問—滿意 度是七項任務中最低的，但其系統中回覆正確率卻有 90.00%。
未來研究可以擴增問答語料庫問答紀錄、增進問題比對的精確度、改進答案 呈現方式，以更加完善參考諮詢機器人之功能並解決任務五滿意度偏低之問題。

Communication software is prevalent, and with the advancement of natural language processing, chatbots are a popular application of artificial intelligence. Some libraries have developed chatbots to provide a new type of real-time digital reference service to solve the problem of manual instant reference service. The purpose of this study is to develop a reference chatbot for National Taiwan Normal University Library (NTNU Library) and evaluate its performance from aspects of users.
The reference chatbot developed in this study uses the reference question and answer set of NTNU Library and the FAQs as a question and answer corpus. The development platform is Line Bot, the programming language is Python, and the tool for performing Chinese word segmentation and keyword extraction is Jieba. Dice coefficient is used for the calculation of the similarity between a problem and keywords, and Beautiful Soup assists in crawling the information of the library website and OPAC of NTNU. The reference chatbot developed in this study comprises three functions: inquiry about library collection, inquiry about library opening hours and inquiry about Q&A corpus .
In terms of the evaluation test, ten NTNU’s students were asked to perform seven tasks, and the five-level Likert scale were given according to the response of the chatbot. The results showed that the respondents were satisfied with the response of the reference chatbot. The correct response rate was 70%, and the system's response accuracy rate was 82.86%. The response with higher satisfaction was also correct. Only task five, inquiry about the library resources , receives the lowest satisfaction, but the system's response accuracy rate was 90.00%.
Future research can amplify the question and answer corpus, improve the accuracy of problem comparison, and improve the way in which answers are presented, so as to further improve the function of the reference chatbot and solve the problem of low satisfaction of the task five.

一、中文文獻
LINE(2017年3月27日)。【功能介紹】Messaging API【部落格文字資料】。取自http://at-blog.line.me/tw/messaging_api_intro
王宏仁（2017）。【專家剖析】Chatbot三大技術關鍵與最新研究方向【新聞群組】。取自https://www.ithome.com.tw/news/113445
王梅玲與謝寶煖（2014）。圖書資訊學導論。臺北市：五南。
王愛珠（2007）。參考諮詢服務的發展：從傳統線上到線上合作。臺灣圖書館管理季刊，3(4)，28-40 。
马勇强（2018）。智能客服FAQ问答任务的技术选型探讨【部落格文字資料】。取自https://zhuanlan.zhihu.com/p/50799128
许文涛（2018）。一份关于问答系统的小结【部落格文字資料】。取自https://zhuanlan.zhihu.com/p/39561907
李雅惠（2009）。MSN即時數位參考服務之使用研究：以交通大學圖書館為例（碩士論文）。取自https://ir.nctu.edu.tw/handle/11536/39878
姚飞、张成昱、陈武（2014）。清华智能聊天机器人「小图」的移动应用。现代图书情报技术，2014(7/8)，120-126。
姚飞、纪磊、张成昱、陈武（2011）。实时虚拟参考咨询服务新尝试—清华大学图书馆智能聊天机器人。现代图书情报技术，2011(4)，77-81。
柯皓仁（2004）。公共圖書館之數位參考諮詢服務。台北市立圖書館館訊，22(2)，8-19。
洪世昌（2012）。全年無休參考服務。圖書館學與資訊科學大辭典。取自http://terms.naer.edu.tw/detail/1679165/
國立政治大學統計系（2017）。2017 年台灣臺灣寬頻網路使用調查報告。財團法人台灣臺灣網路資訊中心，未出版。
張文宗（2017）。淺談Chatbot聊天機器人之應用。期貨人，64，65-70。
張淳淳（主編）（2003）。參考資源與服務。新北市蘆洲市：空大。
張雅雯（2011）。JT-Bot：以AIML為基礎之Java家教機器人（碩士論文）。取自https://hdl.handle.net/11296/6nz752
彭昱傑（2017）。聊天機器人系統設計與實作（碩士論文）。取自：https://hdl.handle.net/11296/w4jq3k
葉鎮源（2012）。問答系統。圖書館學與資訊科學大辭典。取自http://terms.naer.edu.tw/detail/1678980/
顏理謙（2016）。這些應用都跟聊天機器人有關！。數位時代，271，50-51。
魏彰村（2017）。運用爬蟲技術之主題導向即時通訊聊天機器人設計與實現：以籃球領域諮詢結合LINE APP實作為例（碩士論文）。取自：https://hdl.handle.net/11296/x5pkg5
蘇小鳳（2004）。大學圖書館合作式即時數位參考諮詢服務。圖書資訊學刊，1(4)，1-19。
蘇小鳳（2005）。即時數位參考諮詢服務。臺北市：文華圖書館管理。
蘇小鳳（2007）。大學圖書館即時數位參考諮詢服務之使用者需求與態度。圖書館學與資訊科學，33(2)，48-63。
二、英文文獻
Allison, D. (2011). Chatbots in the library: is it time?. Faculty Publications, UNL Libraries. 280. Retrieved from https://digitalcommons.unl.edu/libraryscience/280
Artificial Iintelligence (n.d.). In Cambridge Dictionary. Retrieved June 23, 2018, from https://dictionary.cambridge.org/zht/%E8%A9%9E%E5%85%B8/%E8%8B%B1%E8%AA%9E/artificial-intelligence#dataset-british
Bakker, T. (2002). Virtual reference services: connecting users with experts and supporting the development of skills. Liber Quarterly, 12, 124-137.
Berube, L. (2003). Digital Reference Overview. Retrieved from http://www.ukoln.ac.uk/public/nsptg/virtual/
Bhardwaj, D., Pakray, P., Bentham, J., & Saha, S. (2016). Question answering system for frequently asked questions. Proceedings of Third Italian Conference on Computational Linguistics (CLiC-it 2016) & Fifth Evaluation Campaign of Natural Language Processing and Speech Tools for Italian. Final Workshop (EVALITA 2016). Retrieved from http://ceur-ws.org/Vol-1749/
Britz, D. (2016, April 6). Deep Learning for Chatbots, Part 1 – Introduction [Web blog message].Retrieved from http://www.wildml.com/2016/04/deep-learning-for-chatbots-part-1-introduction/
Chatbot (2009). In Wikipedia, the free encyclopedia. Retrieved June 24, 2018, from https://en.wikipedia.org/wiki/Chatbot
Copeland, B. J. (1998). Artificial intelligence. In Encyclopædia Britannica. Retrieved June 23, 2018, from https://www.britannica.com/technology/artificial-intelligence
Digital reference Reference (2005). In Wikipedia, the free encyclopedia. Retrieved June 22, 2018, from https://en.wikipedia.org/wiki/Digital_reference
Dowd, J. (2011). I just want my website to talk to me: implementation and trial of a chatbot at the University of Wolverhampton. SCONUL Focus, 51, 35-42.
Gill, N.A. (2017, April 21). Overview of Artificial Intelligence, Deep Learning and NLP in Big Data [Web blog message]. Retrieved from https://www.xenonstack.com/blog/data-science/ai-nlp-big-deep-learning/
Hisle, W.L. (2005). Reference questions in the library of the future. The Chronicle of Higher Education, 52(6), B6.
Holmes, S., Moorhead, A., Bond, R., Zheng, Huiru, Coates, V., & McTear, M. (2018, Janaury). WeightMentor: A New Automated Chatbot for Weight Loss Maintenance. Paper presented at HCI, British. Retrieved from https://www.researchgate.net/publication/328896995_WeightMentor_A_New_Automated_Chatbot_for_Weight_Loss_Maintenance
Jia, Jiyou J. (2009). CSIEC: A computer assisted English learning chatbot based on textual knowledge and reasoning. Knowledge-Based Systems, 22(4), 249-255.
Lankes, R. D. (2004). The digital reference research agenda. Journal of the American Society for Information Science and Technology, 55(4), 301-311.
Lempinen, K. (2017, February 23). What are Chatbots and how they impact Service Management [Web blog message]. Retrieved from http://www.lempinenpartners.com/what-are-chatbots-and-how-they-impact-service-management/
Levine-Clark, M., & Carter, T. (Ed.). (2013). ALA glossary of library and information science. Chicago (pp.213): ALA editions, an imprint of the American Library Association.
McCarthy, J. (2007). What is artificial intelligence?. Retrieved June 22, 2018, from http://www-formal.stanford.edu/jmc/whatisai/
McCarthy, J., Minsky, M.L., Rochester, N., & Shannon, C. E. (1955). A proposal for the Dartmouth summer research project on artificial intelligence. Retrieved January 10, 2019, from http://www-formal.stanford.edu/jmc/history/dartmouth/dartmouth.html
McClure, C. R., Lankes, R. D., Gross, MelissaM., & Choltco-Devlin, Beverly B. (2002). Statistics, measures, and quality standards for assessing digital Reference library services: guidelines and procedures. ERIC Clearinghouse on Information and Technology; Syracuse, NY.
McNeal, M. L., & Newyear, David D. (2013). Introducing chatbots in libraries. Library Technology Reports, 49(8), 5-10.
Molla, A. D. & González, José. (2007). Question Answering in Restricted Domains: An Overview. Computational Linguistics, 33, 41-61. doi:10.1162/coli.2007.33.1.41.
Reference and User Services Association (2017). Guidelines for implementing and maintaining virtual reference services. Retrieved June 20, 2018, from http://www.ala.org/rusa/resources/guidelines/virtrefguidelines
Rouse, M. (n.d.). chatbot. In WhatIs.com. Retrieved January 12, 2019, from https://searchcrm.techtarget.com/definition/chatbot
Sanjeevi, M. (2018, April 19). Chapter 11: ChatBots to Question & Answer systems. [Web blog message]. Retrieved from https://medium.com/deep-math-machine-learning-ai/chapter-11-chatbots-to-question-answer-systems-e06c648ac22a
Sarkar, U. (2013, January 5). Chatbots---an avenue of AI (article#6) [Web blog message]. Retrieved from http://artificialintelli.blogspot.com/2013/01/chatbots-avenue-of-ai.html
Shah, H., Warwick, K., Vallverdú, J. & Wu, D. (2016). Can Machines Talk? Comparison of Eliza with Modern Dialogue Systems. Computers in Human Behavior, 58, 278–295.
Turing, A. M. (1950). Computing machinery and intelligence. Mind, 59(236), 433-460.
Warschauer, M., & Healey, D. (1998). Computers and language learning: An Overview. Language Teaching, 31, 57-71.