TRCM: a methodology for temporal analysis of evolving concepts in Twitter

Mariam Adedoyin-Olowe, M. Gaber, F. Stahl

Research output: Contribution to conferencePaperpeer-review

140 Downloads (Pure)

Abstract

The Twitter network has been labelled the most commonly used microblogging application around today. With about 500 million estimated registered users as of June, 2012, Twitter has become a credible medium of sentiment/opinion expression. It is also a notable medium for information dissemination; including breaking news on diverse issues since it was launched in 2007. Many organisations, individuals and even government bodies follow activities on the network in order to obtain knowledge on how their audience reacts to tweets that affect them. We can use postings on Twitter (known as tweets) to analyse patterns associated with events by detecting the dynamics of the tweets. A common way of labelling a tweet is by including a number of hashtags that describe its contents. Association Rule Mining can find the likelihood of co-occurrence of hashtags. In this paper, we propose the use of temporal Association Rule Mining to detect rule dynamics, and consequently dynamics of tweets. We coined our methodology Transaction-based Rule Change Mining (TRCM). A number of patterns are identifiable in these rule dynamics including, new rules, emerging rules, unexpected rules and `dead' rules. Also the linkage between the different types of rule dynamics is investigated experimentally in this paper.
Original languageEnglish
Publication statusPublished - 9 Jun 2013
EventThe 12th International Conference on Artificial Intelligence and Soft Computing ICAISC 2013 - Zakopane, Poland
Duration: 9 Jun 201313 Jun 2013

Conference

ConferenceThe 12th International Conference on Artificial Intelligence and Soft Computing ICAISC 2013
Country/TerritoryPoland
CityZakopane
Period9/06/1313/06/13

Fingerprint

Dive into the research topics of 'TRCM: a methodology for temporal analysis of evolving concepts in Twitter'. Together they form a unique fingerprint.

Cite this