TY - GEN

T1 - Automatic Generation of the Domain-Specific Sentiment Russian Dictionaries

AU - Dubatovka, A.

AU - Kurochkin, Yu.

AU - Mikhailova, E.

PY - 2016

Y1 - 2016

N2 - This paper presents an algorithm for generating the Domain-Speci c Senti- ment Russian dictionary using a graph model. It is important to emphasize that the described algorithm does not require any human-labeling, but just a su ciently large corpus of Russian texts from the subject area, which can be generated automatically for most domains. Our algorithm is not strictly con ned to the Russian language and, if necessary, can be generalized to develop dictionaries in other languages. Dictionaries of positive and negative words are created using the analy- sis of the graph constructed on unlabeled corpus of the Domain-Speci c Russian texts. The graph was built using the approach described in [6], pre-adapted to texts in Russian. The applicability of this method to create a graph for prediction of polarity of adjectives in reviews in Russian lan- guage is experimentally evaluated. The original method of graph processing for splitting the vertex set of this graph into subsets of positive and negative words was pr

AB - This paper presents an algorithm for generating the Domain-Speci c Senti- ment Russian dictionary using a graph model. It is important to emphasize that the described algorithm does not require any human-labeling, but just a su ciently large corpus of Russian texts from the subject area, which can be generated automatically for most domains. Our algorithm is not strictly con ned to the Russian language and, if necessary, can be generalized to develop dictionaries in other languages. Dictionaries of positive and negative words are created using the analy- sis of the graph constructed on unlabeled corpus of the Domain-Speci c Russian texts. The graph was built using the approach described in [6], pre-adapted to texts in Russian. The applicability of this method to create a graph for prediction of polarity of adjectives in reviews in Russian lan- guage is experimentally evaluated. The original method of graph processing for splitting the vertex set of this graph into subsets of positive and negative words was pr

KW - sentiment analysis

KW - sentiment lexicon

KW - opinion mining

M3 - Conference contribution

SP - 146

EP - 158

BT - Computational Linguistics and Intellectual Technologies

T2 - 2016 International Conference on Computational Linguistics and Intellectual Technologies, Dialogue 2016

Y2 - 1 June 2016 through 4 June 2016

ER -