Building an expert-system based conversational agent to provide personalised resources about neurological disorders

• Author / Creator

  Sajed, Tanvir

• Researchers developing artificially intelligent conversational agents (aka, chat-
  bots) seek effective ways to provide personal assistance to users with various
  needs. We have implemented a web-based conversational agent that recom-
  mends resources to help clients (caregivers of patients suffering from various
  neurodevelopmental disorders — either family members or health-care pro-
  fessionals). Our agent first asks the client a conditional sequence of relevant
  questions about the patient’s medical symptoms to fill out a patient profile,
  then recommends an appropriate website from a curated knowledge base of
  resources, previously validated by experts. We implement this agent as an
  expert-system (ES), using an inference engine to make recommendations based
  on a knowledge base of information about resources and the information ac-
  quired about the patient. This ES technology means the designer can easily
  update information about the resources, without redesigning the question-
  answering process. We anticipate that our framework can be used in different
  applications that require a conversational agent to ask personalised questions
  to identify the best recommendations for users.

• Subjects / Keywords

  • expert-system
  • recommendation system
  • chatbot

• Graduation date

  Spring 2022

• Type of Item

  Thesis

• Degree

  Master of Science

• DOI

  https://doi.org/10.7939/r3-62at-r136

• License

  This thesis is made available by the University of Alberta Libraries with permission of the copyright owner solely for non-commercial purposes. This thesis, or any portion thereof, may not otherwise be copied or reproduced without the written consent of the copyright owner, except to the extent permitted by Canadian copyright law.