Why or Why Not? The Effect of Justification Styles on Chatbot Recommendations

ACM Transactions on Information Systems - Tập 39 Số 4 - Trang 1-21 - 2021
Daricia Wilkinson1, Öznur Alkan2, Q. Vera Liao3, Massimiliano Mattetti2, Inge Vejsbjerg2, Bart P. Knijnenburg1, Elizabeth Daly2
1Clemson University, Clemson, SC, USA
2IBM Research, Dublin, Ireland
3IBM Research, Yorktown Heights, NY, USA

Tóm tắt

Chatbots or conversational recommenders have gained increasing popularity as a new paradigm for Recommender Systems (RS). Prior work on RS showed that providing explanations can improve transparency and trust, which are critical for the adoption of RS. Their interactive and engaging nature makes conversational recommenders a natural platform to not only provide recommendations but also justify the recommendations through explanations. The recent surge of interest inexplainable AI enables diverse styles of justification, and also invites questions on how styles of justification impact user perception. In this article, we explore the effect of “why” justifications and “why not” justifications on users’ perceptions of explainability and trust. We developed and tested a movie-recommendation chatbot that provides users with different types of justifications for the recommended items. Our online experiment ( n = 310) demonstrates that the “why” justifications (but not the “why not” justifications) have a significant impact on users’ perception of the conversational recommender. Particularly, “why” justifications increase users’ perception of system transparency, which impacts perceived control, trusting beliefs and in turn influences users’ willingness to depend on the system’s advice. Finally, we discuss the design implications for decision-assisting chatbots.

Từ khóa


Tài liệu tham khảo

Titipat Achakulvisut , Daniel Acuna , Tulakan Ruangrong , and Konrad Kording . 2016. Science concierge: A fast content-based recommendation system for scientific publications. PLoS One 11, 04 ( 2016 ). https://doi.org/10.1371/journal.pone.0158423 Titipat Achakulvisut, Daniel Acuna, Tulakan Ruangrong, and Konrad Kording. 2016. Science concierge: A fast content-based recommendation system for scientific publications. PLoS One 11, 04 (2016). https://doi.org/10.1371/journal.pone.0158423

10.1145/3290605.3300484

10.5555/2846236

10.1037/0033-2909.88.3.588

10.1145/3025171.3025209

10.1145/3209219.3209251

10.1057/ejis.2013.36

10.1145/365024.365304

10.1145/2365952.2365964

10.1007/978-3-319-70284-1_30

10.1016/j.ijhcs.2016.02.002

10.1145/2939672.2939746

10.1007/s11257-008-9051-3

Jesse Dodge Andreea Gane Xiang Zhang Antoine Bordes Sumit Chopra Alexander H. Miller Arthur Szlam and Jason Weston. 2015. Evaluating prerequisite qualities for learning end-to-end dialog systems. arXiv preprint arXiv:1511.06931. Jesse Dodge Andreea Gane Xiang Zhang Antoine Bordes Sumit Chopra Alexander H. Miller Arthur Szlam and Jason Weston. 2015. Evaluating prerequisite qualities for learning end-to-end dialog systems. arXiv preprint arXiv:1511.06931.

10.1145/3301275.3302274

Malin Eiband , Hanna Schneider , and Daniel Buschek . 2018 . Normative vs. pragmatic: Two perspectives on the design of explanations in intelligent systems . In Proceedings of the IUI Workshops. Malin Eiband, Hanna Schneider, and Daniel Buschek. 2018. Normative vs. pragmatic: Two perspectives on the design of explanations in intelligent systems. In Proceedings of the IUI Workshops.

10.1109/CEC-EEE.2006.14

10.1080/10447318.2018.1456150

10.1609/aimag.v32i3.2365

10.1016/j.omega.2004.01.006

10.1145/1378773.1378804

10.1145/3236009

David Gunning , Mark Stefik , Jaesik Choi , Timothy Miller , Simone Stumpf , and Guang-Zhong Yang . 2019. XAI—Explainable artificial intelligence. Science Robotics 4, 37 ( 2019 ). David Gunning, Mark Stefik, Jaesik Choi, Timothy Miller, Simone Stumpf, and Guang-Zhong Yang. 2019. XAI—Explainable artificial intelligence. Science Robotics 4, 37 (2019).

10.1145/358916.358995

10.1080/10705519909540118

10.1145/2678025.2701371

10.1145/2043932.2043960

10.1145/2959100.2959189

10.1145/2963106

10.1007/s11257-011-9118-4

10.5555/2017317.2017325

10.1145/3301275.3302306

10.1145/3290605.3300717

10.1145/1620545.1620576

10.1145/1864349.1864353

10.1145/1518701.1519023

10.1145/1557914.1557930

Kevin McCarthy , James Reilly , Lorraine McGinty , and Barry Smyth . 2004. On the dynamic generation of compound critiques in conversational recommender systems . In Adaptive Hypermedia and Adaptive Web-Based Systems , Paul M. E. De Bra and Wolfgang Nejdl (Eds.). Springer , Berlin , 176–184. Kevin McCarthy, James Reilly, Lorraine McGinty, and Barry Smyth. 2004. On the dynamic generation of compound critiques in conversational recommender systems. In Adaptive Hypermedia and Adaptive Web-Based Systems, Paul M. E. De Bra and Wolfgang Nejdl (Eds.). Springer, Berlin, 176–184.

10.1287/isre.13.3.334.81

10.5555/1759957.1759988

10.1145/3301275.3302313

Tim Miller. 2018. Explanation in artificial intelligence: Insights from the social sciences. Artif. Intell. (2018). Tim Miller. 2018. Explanation in artificial intelligence: Insights from the social sciences. Artif. Intell. (2018).

Cecilie Bertinussen Nordheim. 2018. Trust in Chatbots for Customer Service—Findings from a Questionnaire Study. Master’s thesis. Cecilie Bertinussen Nordheim. 2018. Trust in Chatbots for Customer Service—Findings from a Questionnaire Study. Master’s thesis.

10.1145/1357054.1357222

10.1145/1111449.1111475

Reports and Data . 2019. Global Chatbot Market Size & Analysis | Industry Report , 2019 -2026. https://www.reportsanddata.com/report-detail/chatbot-market. Reports and Data. 2019. Global Chatbot Market Size & Analysis | Industry Report, 2019-2026. https://www.reportsanddata.com/report-detail/chatbot-market.

10.1145/501516.501523

10.1145/506443.506619

10.1145/3338283

10.1145/3314183.3323456

10.1109/TSMCA.2008.2003969

10.1007/s11257-011-9117-5

10.1080/07421222.1996.11518134

10.2753/MIS0742-1222230410

10.1016/j.jsis.2015.10.004

10.5555/3298023.3298238

10.1145/3269206.3271776