ACM Home Page
Please provide us with feedback. Feedback
Learning users' interests by unobtrusively observing their normal behavior
Full text PdfPdf (558 KB)
Source International Conference on Intelligent User Interfaces archive
Proceedings of the 5th international conference on Intelligent user interfaces table of contents
New Orleans, Louisiana, United States
Pages: 129 - 132  
Year of Publication: 2000
ISBN:1-58113-134-8
Authors
Jeremy Goecks  Computer Sciences Dept., University of Wisconsin, 1210 W. Dayton Street, Madison, WI
Jude Shavlik  Computer Science Dept., University of Wisconsin, 1210 W. Dayton Street, Madison, WI
Sponsors
SIGCHI: ACM Special Interest Group on Computer-Human Interaction
SIGART: ACM Special Interest Group on Artificial Intelligence
Publisher
ACM  New York, NY, USA
Bibliometrics
Downloads (6 Weeks): 17,   Downloads (12 Months): 89,   Citation Count: 29
Additional Information:

abstract   references   cited by   index terms   collaborative colleagues  

Tools and Actions: Request Permissions Request Permissions    Review this Article  
DOI Bookmark: Use this link to bookmark this Article: http://doi.acm.org/10.1145/325737.325806
What is a DOI?

ABSTRACT

For intelligent interfaces attempting to learn a user's interests, the cost of obtaining labeled training instances is prohibitive because the user must directly label each training instance, and few users are willing to do so. We present an approach that circumvents the need for human-labeled pages. Instead, we learn “surrogate” tasks where the desired output is easily measured, such as the number of hyperlinks clicked on a page or the amount of scrolling performed. Our assumption is that these outputs will highly correlate with the user's interests. In other words, by unobtrusively “observing” the user's behavior we are able to learn functions of value. For example, an intelligent browser could silently observe the user's browsing behavior during the day, then use these training examples to learn such functions and gather, during the middle of the night, pages that are likely to be of interest to the user. Previous work has focused on learning a user profile by passively observing the hyperlinks clicked on and those passed over. We extend this approach by measuring user mouse and scrolling activity in addition to user browsing activity. We present empirical results that demonstrate our agent can accurately predict some easily measured aspects of one's use of his or her browser.


REFERENCES

Note: OCR errors may be found in this Reference List extracted from the full text article. ACM has opted to expose the complete List rather than only correct and linked references.

 
1
T. Joachims, D. Freitag, and T. Mitchell. WebWatcher: A Tour Guide for the World Wide Web, ZJCAI-97, pp. 770-775.
 
2
K. Lang. NewsWeeder: Learning to Filter News, ZCML-95, pp. 33 l-339.
 
3
Liberman, H. Letizia: An Agent that Assists Web Browsing. ZJCAZ-95, pp. 924-929.
 
4
Mladenic, D. Personal WebWatcher: Implementation and Design, Technical Report ZJS-DP-7472, Department for Intelligent Systems, J.Stefan Institute, October, 1996.
 
5
M. Pazzani, J. Muramatsu, and D. Billsus. Syskill & Webert: Identifying Interesting Web Sites, AAAZ-96, pp. 54-61.
 
6
G. Salton. Developments in Automatic Text Retrieval, Science 253~974-97

CITED BY  29

Collaborative Colleagues:
Jeremy Goecks: colleagues
Jude Shavlik: colleagues