Abstract

The automatic analysis of complex text collections is of high interest for many companies and institutions. Analyzing the sentiments of documents is a current research topic. This paper presents and evaluates a classification approach we developed for the public relations department of the "Technische Universitaet Berlin". The system is designed to predict the sentiment class of news articles. In the paper we discuss the creation of a training corpus, the approach for learning a classifier with different preprocessing steps as well as the evaluation of our system. The analysis of the baseline comparison with a 10-fold cross-validation shows that it predicts sentiment classes with a satisfying accuracy.

@TechReport{SemSearchSentimentAnalysis2015,
  author = 	 {Florian B"utow and Florian Schultze and Leopold Strauch and Danuta Ploch and Andreas Lommatzsch},
  title = 	 {Sentiment Analysis with Machine Learning Algorithms on German News Articles},
  institution =  {Berlin Institute of Technology, AOT},
  year = 	 {2015},
  note = 	 {http://www.dai-labor.de/publikationen/1052},
  type =  {project report},
}