Impact of changes in chatbot's facial expressions on user attention and reaction time

PLoS One. 2023 Jul 27;18(7):e0288122. doi: 10.1371/journal.pone.0288122. eCollection 2023.

Abstract

Communication within online platforms supported by chatbots requires algorithms, language processing methods, and an effective visual representation. These are crucial elements for increasing user engagement and making communication more akin to natural conversation. Chatbots compete with other graphic elements within websites or applications, and thus attracting a user's attention is a challenge even before the actual conversation begins. A chatbot may remain unnoticed even with sophisticated techniques at play. Drawing attention to the chatbot area localized within the periphery area can be carried out with the use of various visual characteristics. The presented study analyzed the impact of changes in a chatbot's emotional expressions on user reaction. The aim of this study was to observe, based on user reaction times, whether changes in a chatbot's emotional expressions make it more noticeable. The results showed that users are more sensitive to positive emotions within chatbots, as positive facial expressions were noticed more quickly than negative ones.

Publication types

  • Research Support, Non-U.S. Gov't

MeSH terms

  • Communication
  • Facial Expression*
  • Language
  • Reaction Time
  • Software*

Grants and funding

This work was supported by the National Science Centre of Poland, Decision No. 2017/27/B/HS4/01216 (J.J., K.B.) and this research was supported by ZUT Highfliers School /Szkoła Orłów ZUT/ project co-ordinated by Dr. Piotr Sulikowski, within the framework of the program of the Minister of Education and Science /Grant No. MNiSW/2019/391/DIR/KH, POWR.03.01.00-00-P015/18/, co-financed by the European Social Fund, the amount of financing PLN 1,704,201,66 (K.F.). The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.