Skip to main content

University of Michigan School of Information


Licia He awarded Best Paper at ICWSM18

Friday, 06/29/2018

A study of how images vary on Wikipedia sites wins top honor for UMSI PhD student

Licia He, a UMSI doctoral student, has received a Best Paper award at the 12th International AAAI Conference on Web and Social Media, held this week in Palo Alto, Calif.

She is lead author of the study, "The_Tower_of_Babel.jpg: Diversity of Visual Encyclopedic Knowledge Across Wikipedia Language Editions.” 

The paper is a large-scale analysis of how images are used across multi-lingual Wikipedias. The researchers surveyed 25 languages and 10 million images. A primary finding of the study was that images are more diverse than text across different languages on Wikipedia. 

Images often are unique to one language, thus offering “substantially different visual representations for the same concept,” according to the study. 

Eytan Adar, UMSI associate professor, is He’s advisor and co-principal investigator of the study, along with Brent Hecht from Northwestern University; Northwestern student Allen Yilun also contributed to the research.

"Licia led an incredibly complex and exciting study,” Adar says. “The results have significance for the many people who use Wikipedia as readers, editors, or for machine learning applications. We're very honored that the work was recognized with a best paper award."

Link to study:

AAAI stands for the Association for the Advancement of Artificial Intelligence.

Eytan Adar is associate professor of information, School of Information and associate professor of electrical engineering and computer science, College of Engineering.

- UMSI News Service