Assigning Connotation Values to Events

Abstract

Sentiment Analysis (SA) and Opinion Mining (OM) have become a popular task in recent years in NLP with the development of language resources, corpora and annotation schemes. The possibility to discriminate between objective and subjective expressions contributes to the identification of a document's semantic orientation and to the detection of the opinions and sentiments expressed by the authors or attributed to other participants in the document. Subjectivity word sense disambiguation helps in this task, automatically determining which word senses in a corpus are being used subjectively and which are being used objectively. This paper reports on a methodology to assign in a semi-automatic way connotative values to eventive nouns usually labelled as neutral through syntagmatic patterns that express cause-effect relations between emotion cause events and emotion words. We have applied our method to nouns and we have been able reduce the number of OBJ polarity values associated to event noun.

Resources

Details