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 professionals and academicians specializing in HCI, who were asked to state level of ML use in HCI work. Responses were captured via a structured questionnaire. Analysis showed that about one-third of those who participated in the survey had used ML in conjunction with a variety of different HCI tasks. However, statistically significant differences could not be identified between those who have and those who have not used ML. Using statistics, contingency analysis, and clustering, we modeled interaction between representative HCI tasks and ML paradigms. We discovered that neural networks, rule induction, and statistical learning emerged as the most popular ML paradigms across HCI workers, although intensive learning, such as inductive logic programming, are gaining popularity among application developers. We also discovered that the leading causes for declining use of ML in HCI work are (1) misperceptions about ML, (2) lack of awareness of ML’s potential, and (3) scarcity of concrete case studies demonstrating the application of ML in HCI.