Stefanos Petrakis

Learn More
In this paper, we describe MLSA, a publicly available multi-layered reference corpus for German-language sentiment analysis. The construction of the corpus is based on the manual annotation of 270 German-language sentences considering three different layers of granularity. The sentence-layer annotation, as the most coarse-grained annotation, focuses on(More)
In the past, we have succesfully used machine learning approaches for sentiment analysis. In the course of those experiments, we observed that our machine learning method, although able to cope well with figurative language could not always reach a certain decision about the polarity orientation of sentences, yielding erroneous evaluations. We support the(More)
We introduce an explorative tool for affect analysis from texts. Rather than the full range of emotions, feelings, and sentiment, our system is currently restricted to the positive or negative polarity of phrases and sentences. It analyses the input texts with the aid of a affect lexicon that specifies among others the prior polarity (positive or negative)(More)
The current endeavour focuses on the notion of positive versus negative polarity preference of verbs for their direct objects. This preference has to be distinguished from a verb’s own prior polarity for the same verb, these two properties might even be inverse. Polarity preferences of verbs are extracted on the basis of a large and dependencyparsed corpus(More)
In the past we have witnessed our machine learning method for sentiment analysis coping well with figurative language, but determining with uncertainty the polarity of mildly figurative cases. We have shown that for these uncertain cases, a rule-based system should be consulted. We evaluate this collaborative approach on the ”Rotten Tomatoes” movie reviews(More)
We introduce the task of word and phrase-level polarity annotation for German as part of an attempt to develop a compositional theory of clause-level polarity determination. Thus, annotations should give access to the nested building blocks, the structural strata of polarity composition. Therefore and in contrast to existing polarity-tagged corpora, we(More)
  • 1