Features

XXIV.4 July-August 2017
Page: 34
Digital Citation

Avoiding pitfalls when using machine learning in HCI studies


Authors:
Vassilis Kostakos, Mirco Musolesi

  Machine learning (ML) has come of age and has revolutionized several fields in computing and beyond, including human-computer interaction (HCI). Human-subject studies have been adopting ML techniques for more than a decade, for example for activity recognition and wearable computing. There now also exists a plethora of application domains in which ML approaches are enriching interactive computing research. Here we wish to highlight some of the pitfalls that HCI researchers should avoid while using ML techniques in their research.   Insights A popular use of ML techniques in HCI is to model human behavior. One potential risk is that…




You must be a member of SIGCHI, a subscriber to ACMís Digital Library, or an interactions subscriber to read the full text of this article.

LOG IN TO READ THE FULL ARTICLE

Forgot Password?

GET ACCESS

Join ACM SIGCHI

In addition to all of the professional benefits of being a SIGCHI member, members get full access to interactionsí online content and receive the print version of the magazine bimonthly.


Subscribe to the ACM Digital Library

Get access to all interactions content online and the entire archive of ACM publications dating back to 1954. (Please check with your institution to see if it already has a subscription.)


Subscribe to interactions

Get full access to interactionsí online content and receive the print version of the magazine bimonthly.