home › event - a comparison study of a social labeling technique and automatic keyword extraction for representing wikipedia contributions

EVENT:

A comparison study of a social labeling technique and automatic keyword extraction for representing wikipedia contributions

ICWSM-10

23 May 2010 - 26 May 2010
Washington, District of Columbia, USA

 

description

In many collaborative systems, researchers are interested in creating user profiles. There are many ways to create user profiles. In this paper, we are particularly interested in social labeling and automatic keyword extraction techniques for generating user profiles. Social labeling is a process in which users manually tag other users with keywords, which has become popular with the rise of Web2.0 systems and user-generated contents. Automatic keyword extraction technique selects the most salient words to represent the user contribution. In this paper, we apply these two profile-generation methods to highly active Wikipedia editors and their contributions, and compare the results. In our comparison, we found that profiles generated through social labeling matches the profiles extracted using automatic keyword extraction applied to Wikipedia revisions. The result suggests that user profiles generated from one method can be used as a seed for the other method.

 

upcoming events   view all 

The Cutting Edge of Artificial Intelligence
Tolga Kurtoglu, Margareta Ackerman, Andra Keay, Piero Scaruffi, Allen Saakyan
22 February 2018 | George E. Pake Auditorium, PARC
PARC Forum  

Printed Electronics: From Vision to Disruption
Markus Larsson
13 March 2018 | Munich, Germany
Conferences & Talks  

The Ghost in the Smart Machine (Panel)
Tolga Kurtoglu, Panelist
22 March 2018 | Chicago, IL
Conferences & Talks  

Robots, AI and the Future of Work (Plenary Session)
Tolga Kurtoglu
17 April 2018 | Miami, FL
Conferences & Talks  

Bringing Reliable (and Transparent) AI to Business (Keynote)
Tolga Kurtoglu, Keynote Speaker
26 April 2018 | Seattle, WA
Conferences & Talks