Paper Info
Title
Topical semantics of twitter links
Abstract
Twitter, a micro-blogging platform with an estimated 20 million unique monthly visitors and over 100 million registered users, offers an abundance of rich, structured data at a rate exceeding 600 tweets per second. Recent efforts to leverage this social data to rank users by quality and topical relevance have largely focused on the "follow" relationship. Twitter's data offers additional implicit relationships between users, however, such as "retweets" and "mentions". In this paper we investigate the semantics of the follow and retweet relationships. Specifically, we show that the transitivity of topical relevance is better preserved over retweet links, and that retweeting a user is a significantly stronger indicator of topical interest than following him. We demonstrate these properties by ranking users with two variants of the PageRank algorithm; one based on the follows sub-graph and one based on the implicit retweet sub-graph. We perform a user study to assess the topical relevance of the resulting top-ranked users.
Year
DOI
Venue
2011
10.1145/1935826.1935882
Web Search and Data Mining
Keywords
Field
DocType
social data,link semantics,topical semantics,topical relevance,twitter link,retweet link,structured data,implicit retweet sub-graph,twitter,million registered user,web graph,modeling,million unique monthly visitor,topical interest,ranking,retweet relationship,additional implicit relationship,semantic model
Data mining,World Wide Web,Leverage (finance),Information retrieval,Ranking,Computer science,Pagerank algorithm,Data model,Semantics,Transitive relation
Conference
Citations 
PageRank 
References 
33
1.79
17
Authors
4
Name
Order
Citations
PageRank
Michael J. Welch1874.84
Uri Schonfeld21065.85
Dan He312420.07
Junghoo Cho43088584.54