Publication Type

Conference Paper

Publication Date

2-2010

Abstract

Millions of users are posting their status updates, interesting findings, news, ideas and observations in real-time on microblogging services such as Twitter, Jaiku and Plurk. This real-time Web can be a great resource of valuable timely information. Since the real-time Web is completely open and decentralized and anyone may post information at whim, distinguishing interesting and popular postings from the mundane ones is a challenging task. In this paper we study the problem of estimating the quality (or “interestingness”) of postings in the real-time Web. We identify several important factors that are indicative of the quality of postings, and present metrics that capture these factors. To showcase the promise of our approach, we present early experimental results on Twitter.

Discipline

Databases and Information Systems | Numerical Analysis and Scientific Computing

Research Areas

Data Management and Analytics

Publication

WSDM 2010 Workshop on Search in Social Media (SSM)

City or Country

New York, USA

Additional URL

http://www.ntoulas.x10.mx/pubs/ntoulas_posting_quality.pdf

Share

COinS