Peaks and persistence: modeling the shape of microblog conversations

A microblogged stream is delivered over time, providing an ongoing commentary of topics, trends, and issues. In this article, we present two methods of finding temporal topics within these Twitter streams. Using a normalized term frequency, we demonstrate how an effective table of contents can be extracted by finding localized “peaky topics”. Second, we find “persistent conversations” which have a lower general salience but sustain and persist over the tweet corpus, in effect the whispering conversation that lingers in the background. These methods are demonstrated on a Twitter corpus of 53,000 tweets and a second Twitter corpus of

• Type: Journal
• Year: 2011
• Where: CSCW
• Authors: David A. Shamma, Lyndon Kennedy, Elizabeth F. Churchill
• Keywords: CSCW 2011, Lower General Salience, Normalized Term Frequency, Social Sciences, Twitter Corpus