@inproceedings{cercas-curry-rieser-2019-crowd,
    title = "A Crowd-based Evaluation of Abuse Response Strategies in Conversational Agents",
    author = "Cercas Curry, Amanda  and
      Rieser, Verena",
    editor = "Nakamura, Satoshi  and
      Gasic, Milica  and
      Zukerman, Ingrid  and
      Skantze, Gabriel  and
      Nakano, Mikio  and
      Papangelis, Alexandros  and
      Ultes, Stefan  and
      Yoshino, Koichiro",
    booktitle = "Proceedings of the 20th Annual SIGdial Meeting on Discourse and Dialogue",
    month = sep,
    year = "2019",
    address = "Stockholm, Sweden",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/W19-5942/",
    doi = "10.18653/v1/W19-5942",
    pages = "361--366",
    abstract = "How should conversational agents respond to verbal abuse through the user? To answer this question, we conduct a large-scale crowd-sourced evaluation of abuse response strategies employed by current state-of-the-art systems. Our results show that some strategies, such as {\textquotedblleft}polite refusal{\textquotedblright}, score highly across the board, while for other strategies demographic factors, such as age, as well as the severity of the preceding abuse influence the user`s perception of which response is appropriate. In addition, we find that most data-driven models lag behind rule-based or commercial systems in terms of their perceived appropriateness."
}