Data mining topic evolution in social media

OData support
Supervisor:
Gáspár Csaba
Department of Telecommunications and Media Informatics

My research is designed to be able to demonstrate the extraction of the popularity and development of different music genres with the help of data mining and to find established estimations for the future. My aim is to develop and use a method that is able to predict the popularity of a music genre based on the opinion of the public.

My project is related to several fields of science: social media, data mining, programming, process prediction and statistics. My topic is the extraction of data from Twitter and Last.fm with the help of data mining tools. After data transformation, I am analysing and making predictions by means of the selected methods. There have been several researches in this field so far, but mine is unique with regards to its topic and the combination of analytic methods.

In order to reach my goal, I used the services of the data sources to build my own programs, which can allow us to prepare automatic analysis based on preliminary instructions. My research shows that the results of this method may serve as an important source of information for example in the field of marketing research.

Downloads

Please sign in to download the files of this thesis.