From data to knowledge: a text mining approach

I recently gained some press coverage with an article that I wrote on the media coverage of political parties/figures. As with all politics related articles, it got quite a few reactions from the general public (positive and negative ones). I feel that most negative comments were due to not knowing/understanding the methodology used. For those interested in the full reasoning behind our conclusions, please refer to the publication in Expert Systems with Applications.

I presented my work at the MTT research seminar as well, slides of the talk, entitle “From data to knowledge: a text mining approach.” are available here. The support vector machine kernalization demonstration is available below (click to get through the next step in theĀ visualization).


The visualization was inspired by Udi’s video located here.

The working life

Goodbye student life. Hello working life!

fig. four hours of stock information crawling went into this picture

Thesis

So here we are, I finally finished my masters thesis. I wasn’t allowed to publish some of these details before due to possible copy behavior. Please be sure to read the disclaimer before using any material included in this post.

Thesisbook

Disclaimer:

“The author gives permission to make this master dissertation available for consultation and to copy parts of this master dissertation for personal use. In the case of any otherĀ use, the limitations of the copyright have to be respected, in particular with regard to the obligation to state expressly the source when quoting results from this master dissertation.”

(in case of reusage or doubt, please contact me first)


video: scapula usage in animals and the robot


video: vertebra usage in animals and the robot


video: trajectory as used in the learning proces