Summary of the paper

Title Conversational Gaze modelling in First Encounter Robot Dialogues
Authors Kristiina Jokinen
Abstract Given the popularity of humanoid social robots which can talk with humans and maintain human-like communication patterns, an interesting question is whether the users engage themselves with such systems in a manner similar to human-human communication. If the humanoid robot is perceived as a communicative agent, it can be hypothesized that the user’s engagement with the robot resembles social interaction rather than tool manipulation. This paper reports on a pilot study that explores if the hypothesis is supported in the context of a humanoid robot application which reads a digital newspaper interactively for the user. Human eye-gaze patterns are used as an objective measure of the engagement with the robot. The study found support for the hypothesis, but concludes that the interaction is socially less binding than with humans.
Topics Conversation Management, Gaze Modelling, First Encounter Human-Robot Interaction, Eye-Tracking
Full paper Conversational Gaze modelling in First Encounter Robot Dialogues
Bibtex @InProceedings{JOKINEN18.16,
  author = {Kristiina Jokinen},
  title = {Conversational Gaze modelling in First Encounter Robot Dialogues},
  booktitle = {Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018)},
  year = {2018},
  month = {may},
  date = {7-12},
  location = {Miyazaki, Japan},
  editor = {Hanae Koiso and Patrizia Paggio},
  publisher = {European Language Resources Association (ELRA)},
  address = {Paris, France},
  isbn = {979-10-95546-16-0},
  language = {english}
Powered by ELDA © 2018 ELDA/ELRA