Good News or Bad News? Conducting sentiment analysis on Dutch text to dinstinguish between positive and negative relations

Many research questions in political communication can be answered by representing text as a network of positive or negative relations between actors and issues. This paper presents a system for automatically determining whether these relations are positive or negative by using techniques from Sentiment Analysis. We used a Machine Learning approach trained on the manually annotated news coverage of the Dutch 2006 elections, collecting lexical, syntactic, and word-similarity based features and using the syntactic analysis to focus on the relevant part of the sentence. The performance of the full system is significantly better than the baseline with an F-score of 0.63. Additionally, we replicate four studies from an earlier analysis of these elections, attaining correlations of >0.8 in three out of four cases. This shows that the presented system can be immediately used for a number of analyses. keywords: sentiment analysis, semantic network analysis, content analysis, political communication