Sentiment analysis for media reputation research

Samuel Läubli, Mario Schranz, Urs Christen, Manfred Klenner; Proceedings of KONVENS 2012 (PATHOS 2012 workshop), pp. 274-281, September 2012.


As a subtask of qualitative media reputation research, human annotators manually encode the polarity of actors in media products. Seeking to automate this process, we have implemented two baseline classifiers that categorize actors in newspaper articles under six and four polarity classes. Experiments have shown that our approach is not suitable for distinguishing between six finegrained classes, which has turned out to be difficult for humans also. In contrast, we have obtained promising results for the four class model, through which we argue that automated sentiment analysis has a considerable potential in qualitative reputation research.

[pdf] [bibtex]