Automatic Classification of Bulgarian Adjectives on Emotional Semantic Axes

Report published in the Proceedings of the National Conference on "Education and Research in the Information Society", Plovdiv, May, 2014

This study presents a method for automatic classification of Bulgarian adjectives as both positivity and positioning on pre-selected emotional axes like love - hate, generosity - greed, goodness - evil and others. In the basis of the study stands the frequency of occurrence of words in documents from the index of the popular search engine Bing, which provides information as to the number of documents containing a word and the number of documents where two words are found in a nearby. The survey results reflect the use of modern Bulgarian language on the Internet.

Association for the Development of the Information Society, Institute of Mathematics and Informatics Bulgarian Academy of Sciences, Plovdiv University "Paisii Hilendarski"