UNIV. NEWS. NORTH-CAUCAS. REG. TECHNICAL SCIENCES SERIES. 2016; 2: 36-41
http://dx.doi.org/10.17213/0321-2653-2016-2-36-41
SYSTEMS ANALYSIS OF APPROACHES FOR SOLVING THE PROBLEM OF IDENTIFYING SENTIMENT IN TEXT
Gorbushin Daniil Andreevich – engineer of «NovoCNIT», Platov South-Russian State Polytechnic University (NPI), Novocherkassk, Russia. E-mail: gorinwww@gmail.com
Grinchenkov Dmitriy Valerievich – Candidate of Technical Sciences, assistant professor, head of department «Software Computer Engineering», Platov South-Russian State Polytechnic University (NPI), Novocherkassk, Russia. E-mail: grindv@yandex.ru
Mokhov Vasily Alexavdrovich – Candidate of Technical Sciences, assistant professor, department «Software Computer Engineering», Platov South-Russian State Polytechnic University (NPI), Novocherkassk, Russia. E-mail: mokhov_v@mail.ru
Nguyen Phuc Hau – post-graduate student, department «Software Computer Engineering», Platov South-Russian State Polytechnic University (NPI), Novocherkassk, Russia. E-mail: phuchauptit@gmail.com
Abstract
The article is reviewed the sentiment identification in the text and the area of science researches of that subject. There are described a definition of the concept of linguistic processor and the functionality of linguistic processor as the text processing system and sentiment analysis tool. The article also reviewed four approaches (lexicon-based, probabilistic, aspect-based and hybrid) for the creation of the linguistic processor. Also, it has been performed comparative analysis of the approaches. At the end, it has been identified the factors which is affected on the quality and the accuracy of the sentiment classification.
Keywords: sentiment analysis; computational linguistics; computer science; linguistic processor; machine learning
Full text: [in elibrary.ru]
References
References
1. Gorbushin D.A. [The analysis of methods of automatic classification of a tonality of the text]. Nauchno-tekhnicheskaya konferentsiya i vystavka innovatsionnykh proektov, vypolnennykh vuzami i nauchnymi organizatsiyami YuFO v ramkakh uchastiya v realizatsii federal'nykh tselevykh programm i vneprogrammnykh meropriyatii, zakazchikom kotorykh yavlyaetsya Minobrnauki Rossii: sbornik materialov konferentsii [Scientific and technical conference and an exhibition of the innovative projects executed by higher education institutions and the scientific organizations of the Southern Federal District within participation in implementation of federal target programs and extra program actions which customer is the Ministry of Education and Science of the Russian Federation: collection of materials of conference]. Novocherkassk, Lik Publ., 2014, pp. 123-125. [In Russ.]
2. Bol'shakova E.I., Klyshinskii E.S., Lande D.V., Noskov A.A., Peskova O.V., Yagunova E.V. Avtomaticheskaya obrabotka tekstov na estestvennom yazyke i komp'yuternaya lingvistika [Automatic processing of texts in a natural language and computational linguistics]. Moscow, MIEM Publ., 2011, 272 p.
3. Collomb A., Costea C., Joyeux D., Hasan O., Brunie L. A Study and Comparison of Sentiment Analysis Methods for Reputation Evaluation. Available at: http://liris.cnrs.fr/Documents/Liris-6508.pdf. (accessed: 07.03.2016).
4. Lukashevich N.V., Chetverkin I.I., Braslavskii P.I. [Sentiment Analysis Track at ROMIP 2011]. Komp'yuternaya lingvistika i intellektual'nye tekhnologii: Po materialam ezhegodnoi Mezhdunarodnoi konferentsii «Dialog» [Computational linguistics and intellectual technologies: On materials of the annual International Dialogue conference]. Moscow, Izd-vo RGGU, 2012, vol. 2, pp. 1-14. [In Russ.]
5. Awadallah R., Ramanath M., Weikum G. PolariCQ: Polarity Classification of Political Quotations In Proceedings of CIKM-2012 // Conference on Information and Knowledge Management.- 2012. pp. 1945-1949.
6. Gorbushin D.A., Grinchenkov D.V. Metody otsenki kachestva analiza tonal'nosti teksta [Methods of an assessment of quality of a sentiment analysis]. Traditsii russkoi inzhenernoi shkoly: vchera, segodnya, zavtra, Novocherkassk, YuRGPU Publ., 2015. [In Russ.]
7. Sokolova M., Lapalme G. A systematic analysis of performance measures for classification tasks // Inf. Process. Manage. 2009. vol 4. pp. 427–437.
8. Gorbushin D.A., Grinchenkov D.V. Osobennosti primeneniya algoritmov stemminga pri analize tonal'nosti teksta [Features of application of algorithms of a stemming at a sentiment analysis]. Teoriya, metody proektirovaniya, programmno-tekhnicheskaya platforma korporativnykh informatsionnykh system, Novocherkassk, YuRGPU Publ., 2014, pp. 22-24. [In Russ.]
9. Pang B., Lee L. Opinion Mining and Sentiment Analysis // Foundations and Trends in Information Retrieval, 2008. vol. 2 n.1-2, January, pp.1-135.
10. Chetverkin I.I. Avtomatizirovannoe formirovanie bazy znanii dlya zadachi analiza mnenii. Diss. kand. fiz-mat. nauk [The automated formation of the knowledge base for a task of the analysis of opinions. Cand. phys. and math. sci. dis.]. Moscow, MGU imeni M.V. Lomonosova, 2013.