A Conversational Web-Based Chatbot to Disseminate COVID-19 Advisory Information.

Journal: Studies in health technology and informatics
Published Date:

Abstract

Chatbots are computer programs which integrate Artificial Intelligence (AI) and Natural Language Processing (NLP) technologies to simulate human conversation. The use of chatbots has significantly been increased during the COVID-19 pandemic to support healthcare procedures and systems. The purpose of this study is to present the design, implementation, and initial evaluation of a web-based conversational chatbot aiming at the immediate and reliable information regarding the COVID-19 disease. The implementation of the chatbot was built on IBM's Watson Assistant. The chatbot "Iris" that was created is highly developed with the ability to support dialogue, since it has a satisfactory understanding of the relevant subject matter. The system was pilot evaluated using the University of Ulster's Chatbot Usability Questionnaire (CUQ). The results confirmed its usability and that Chatbot "Iris" is a pleasant experience for users. Finally, the related study's limitations and future steps are discussed.

Authors

  • Fratzeska Moutsana Tapolin
    Health Informatics Laboratory, Faculty of Nursing, School of Health Sciences, National and Kapodistrian University of Athens, Athens, Greece.
  • Joseph Liaskos
    Health Informatics Laboratory, Faculty of Nursing, National and Kapodistrian University of Athens, Athens, Greece.
  • Emmanouil Zoulias
    Health Informatics Laboratory, Faculty of Nursing, National and Kapodistrian University of Athens, Athens, Greece.
  • John Mantas
    Health Informatics Laboratory, Faculty of Nursing, National and Kapodistrian University of Athens, Greece.