日時： 2014年7月16日 18：00～
場所： 東京大学生産技術研究所 E棟5階 Ew-501室
Analyzing the “LIKE” Activities in Social Media
As one of popular activities in social media, pressing the LIKE button
toward published contents can be interpreted as an indication of one's
shared interests to the contents or the original posters. Therefore,
such LIKE activities form relationships and networks among people,
raising interesting questions about their unique characteristics and
implications. However, there has been very little research that solely
explored the LIKE information in social media.
To address this lack of understanding, we present our recent study:
(1) an analysis on the LIKE activities, especially focusing on their
structural, influential, and contextual aspects, built from 2.3
billion Likes between 130K posters and 44.6 million photos, in
Instagram; (2) unique characteristics of “teens” in their LIKE
activities in Instagram, indicating the so-called “generation LIKE”;
and (3) a preliminary study on accurately predicting user attributes
using their LIKE activities in Flickr.
Bio:
Dongwon Lee is currently an associate professor in the College of
Information Sciences and Technology (a.k.a. iSchool) of the
Pennsylvania State University, USA. He obtained his Ph.D. in Computer
Science from UCLA in 2002. From 1995 to 1997, he has also worked at
AT&T Bell Labs. Working mostly on the issues arising in the
management and mining of diverse forms of data (e.g., relational
records, documents, XML, and social media), he has (co-)authored over
130+ scholarly articles in selective publication outlets in Databases
and Data Mining. Further details of his research can be found at:
http://pike.psu.edu/ |