Popularity Prediction of Online Messages

From Master Projects
Revision as of 08:50, 21 June 2011 by Swr500 (talk | contribs)

(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)
Jump to: navigation, search

has title::Popularity Prediction of Online Messages
status: ongoing
Master: project within::Knowledge Technology and Intelligent Internet Applications
Student name: student name::S.U. Weller
Start start date:=2011/02/01
End end date:=2011/07/31
Supervisor: Stefan Schlobach
Second reader: has second reader::Zoltan Szlavik
Company: has company::Buzzcapture
Poster: has poster::Media:Swr500_poster.pdf

Signature supervisor



Vast numbers of people post messages about their lives and opinions using online media platforms (blogs, forums, microblogs, social-networks, etc). Some of the messages posted are very popular, i.e. get large number of responses, extreme ratings, a lot of views, or make it to official news sites. It would be interesting to be able to predict the popularity of messages at a relatively early stage, which is possible if we have a way of expressing popularity. In order to find a way to express this, the data from the message platforms needs to be normalized. In this presentation, I will outline the methods that will be used in this research to obtain message data from online platforms, and the structure of an ontology in which this data can be uniformly stored (the SIOC ontology, sioc-project.org).