TY - GEN
T1 - When there is no progress with a task-oriented chatbot
T2 - 21st International Conference on Human-Computer Interaction with Mobile Devices and Services, MobileHCI 2019
AU - Li, Chi Hsun
AU - Chen, Ken
AU - Chang, Yung-Ju
PY - 2019/10/1
Y1 - 2019/10/1
N2 - Task-oriented chatbots are increasingly prevalent in our daily life. Research effort has been devoted to advancing our understanding of users' interaction with conversational agents, including conversation breakdowns. However, most research attempts were limited to obversions from a relatively short duration of user interaction with chatbots, where users were aware of being studied. In this study, we conducted a conversation analysis on a three-month conversation log of users conversing with a chatbot of a banking institution. The log consisted of 1,837 users' conversations with this chatbot with 19,449 message exchanges. From this analysis, we show that users more often failed to make a progress in a conversation when they requested information than when they provided information. Furthermore, we uncovered five kinds of intention gaps unexpected to the chatbot, and five major behaviors users adopted to cope with non-progress.
AB - Task-oriented chatbots are increasingly prevalent in our daily life. Research effort has been devoted to advancing our understanding of users' interaction with conversational agents, including conversation breakdowns. However, most research attempts were limited to obversions from a relatively short duration of user interaction with chatbots, where users were aware of being studied. In this study, we conducted a conversation analysis on a three-month conversation log of users conversing with a chatbot of a banking institution. The log consisted of 1,837 users' conversations with this chatbot with 19,449 message exchanges. From this analysis, we show that users more often failed to make a progress in a conversation when they requested information than when they provided information. Furthermore, we uncovered five kinds of intention gaps unexpected to the chatbot, and five major behaviors users adopted to cope with non-progress.
KW - Chatbot
KW - Coping strategy
KW - Human-agent interaction
KW - Interaction gaps
UR - http://www.scopus.com/inward/record.url?scp=85073513857&partnerID=8YFLogxK
U2 - 10.1145/3338286.3344407
DO - 10.1145/3338286.3344407
M3 - Conference contribution
AN - SCOPUS:85073513857
T3 - Proceedings of the 21st International Conference on Human-Computer Interaction with Mobile Devices and Services, MobileHCI 2019
BT - Proceedings of the 21st International Conference on Human-Computer Interaction with Mobile Devices and Services, MobileHCI 2019
PB - Association for Computing Machinery, Inc
Y2 - 1 October 2019 through 4 October 2019
ER -