The Effect of Multiple Replies for Natural Language Generation Chatbots

被引:1
作者
Chen, Eason [1 ]
机构
[1] Natl Taiwan Normal Univ, Taipei, Taiwan
来源
EXTENDED ABSTRACTS OF THE 2022 CHI CONFERENCE ON HUMAN FACTORS IN COMPUTING SYSTEMS, CHI 2022 | 2022年
关键词
Natural Language Generation; Chatbot; Multiple Replies; Improve Chatting Experience;
D O I
10.1145/3491101.3516800
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
In this research, by responding to users' utterances with multiple replies to create a group chat atmosphere, we alleviate the problem that Natural Language Generation chatbots might reply with inappropriate content, thus causing a bad user experience. Because according to our findings, users tend to pay attention to appropriate replies and ignore inappropriate replies. We conducted a 2 (single reply vs. five replies) x 2 (anonymous avatar vs. anime avatar) repeated measures experiment to compare the chatting experience in different conditions. The result shows that users will have a better chatting experience when receiving multiple replies at once from the NLG model compared to the single reply. Furthermore, according to the effect size of our result, to improve the chatting experience for NLG chatbots which is single reply and anonymous avatar, providing five replies will have more benefits than setting an anime avatar.
引用
收藏
页数:5
相关论文
共 12 条
  • [1] Bengio Y, 2001, ADV NEUR IN, V13, P932
  • [2] Brooke J, 1996, Usability evaluation in industry, P189, DOI DOI 10.1201/9781498710411-35
  • [3] Gunasekara Lakindu, 2019, 2019 National Information Technology Conference (NITC), P1, DOI 10.1109/NITC48475.2019.9114440
  • [4] Higashinaka R, 2015, P 2015 C EMP METH NA, DOI DOI 10.18653/V1/D15-1268
  • [5] Usability testing of a healthcare chatbot: Can we use conventional methods to assess conversational user interfaces?
    Holmes, Samuel
    Moorhead, Anne
    Bond, Raymond
    Zheng, Huiru
    Coates, Vivien
    McTear, Michael
    [J]. PROCEEDINGS OF THE 31ST EUROPEAN CONFERENCE ON COGNITIVE ERGONOMICS: DESIGN FOR COGNITION (ECCE 2019), 2019, : 207 - 214
  • [6] Holtzman A, 2020, Arxiv, DOI arXiv:1904.09751
  • [7] Laugwitz B, 2008, LECT NOTES COMPUT SC, V5298, P63, DOI 10.1007/978-3-540-89350-9_6
  • [8] Radford Alec, 2019, OpenAI Blog, V1, P9
  • [9] Rahman AM, 2017, IEEE REG 10 HUMANIT, P75, DOI 10.1109/R10-HTC.2017.8288910
  • [10] Organizing and the process of sensemaking
    Weick, KE
    Sutcliffe, KM
    Obstfeld, D
    [J]. ORGANIZATION SCIENCE, 2005, 16 (04) : 409 - 421