About Contact Help us

HCI, User Experience, Information Architecture, Usability, and more

“I use free sources like Interaction-Design.org so often that I have an obligation to recognize its value and support its continued presence”

---Stephen J. Kidd

Last 3 Donors

1. Stephen J. Kidd

2. Maria Hull

3. Rosemary J. Bennett

...more generous donors

Support us

Funding progress for 2010:

References

Authors

Jonathan Herlocker

Printer-friendly

How to cite

Jonathan Herlocker

About the author:
No description available of Jonathan Herlocker...

ADD DESCRIPTION

← Button will not work: You have not enabled Javascript. How do I enable it?

ADD PUBLICATION

← Button will not work: You have not enabled Javascript. How do I enable it?

SHARE YOUR RESEARCH

← Button will not work: You have not enabled Javascript. How do I enable it?

Publications by Jonathan Herlocker (bibliography)

» 2007 «

Edit | Del

Stumpf, Simone, Rajaram, Vidya, Li, Lida, Burnett, Margaret, Dietterich, Thomas G., Sullivan, Erin, Drummond, Russell and Herlocker, Jonathan (2007): Toward harnessing user feedback for machine learning. In: Proceedings of the 2007 International Conference on Intelligent User Interfaces 2007. pp. 82-91. Available online

“There has been little research into how end users might be able to communicate advice to machine learning systems. If this resource -- the users themselves -- could somehow work hand-in-hand with machine learning systems, the accuracy of learning systems could be improved and the users' understanding and trust of the system could improve as well. We conducted a think-aloud study to see how willing users were to provide feedback and to understand what kinds of feedback users could give. Users were shown explanations of machine learning predictions and asked to provide feedback to improve the predictions. We found that users had no difficulty providing generous amounts of feedback. The kinds of feedback ranged from suggestions for reweighting of features to proposals for new features, feature combinations, relational features, and wholesale changes to the learning algorithm. The results show that user feedback has the potential to significantly improve machine learning systems, but that learning algorithms need to be extended in several ways to be able to assimilate this feedback.”

Copyrights may apply

ADD PUBLICATION