WHERE DO MACHINE LEARNING AND HUMAN-COMPUTER INTERACTION MEET

Implementation of machine learning (ML) in human-computer interaction (HCI) work is not trivial. This article reports on a survey of 112 pro fessionals and academicians specializing in HCI, who were asked to sta te level of ML use in HCI work. Responses were captured via a structur ed questionnaire. Analysis showed that about one-third of those who pa rticipated in the survey had used ML in conjunction with a variety of different HCI tasks. However, statistically significant differences co uld not be identified between those who have and those who have not us ed ML. Using statistics, contingency analysis, and clustering, we mode led interaction between representative HCI tasks and ML paradigms. We discovered that neural networks, rule induction, and statistical learn ing emerged as the most popular ML paradigms across HCI workers, altho ugh intensive learning, such as inductive logic programming, are gaini ng popularity among application developers. We also discovered that th e leading causes for declining use of ML in HCI work are (I) mispercep tions about ML, (2) lack of awareness of ML's potential, and (3) scarc ity of concrete case studies demonstrating the application of ML in HC I.