Abstract:
The paper presents a survey of methods solving the actual task of aspect-based sentiment analysis. Solutions for this task were proposed at multiple natural language processing conferences. Organizers of these conferences proposed evaluation platforms for methods for aspect-based sentiment analysis. This paper describes methods proposed by participants of two international evaluation platforms: SemEval-2015 focusing on English texts and SentiRuEval-2015 focusing on Russian texts.
SemEval-2015 organizers provided participants with the task 12.2 for English language and two domains: restaurants and laptops. The task was split to multiple subtasks two of which are described in this paper: opinion target expression (both explicit and implicit ones) extraction and sentiment polarity detection. Described methods for opinion target expression can be split to the following categories: sequence labeling, domain-specific terminology extraction and unsupervised learning. Methods for sentiment polarity detection varied from classification-based to unsupervised learning.
SentiRuEval-2015 organizers provided participants with the tasks A, B and C for Russian language and two domains: restaurants and automobiles. Task A was devoted to explicit aspect term extraction, task B – to explicit, implicit and factual aspect term extraction. Sentiment polarity detection was subject of the Task C. Described methods for aspect term extraction can be classified as following: sequence labeling, word2vec-based and neural network-based. Methods for sentiment polarity detection varied from word2vec-based to neural network-based.
Keywords:
sentiment analysis, aspect extraction, text processing, machine learning.
\Bibitem{AndMayTur15}
\by I.~Andrianov, V.~Mayorov, D.~Turdakov
\paper Modern approaches to aspect-based sentiment analysis
\jour Proceedings of ISP RAS
\yr 2015
\vol 27
\issue 5
\pages 5--22
\mathnet{http://mi.mathnet.ru/tisp169}
\crossref{https://doi.org/10.15514/ISPRAS-2015-27(5)-1}
\elib{https://elibrary.ru/item.asp?id=25141691}
Linking options:
https://www.mathnet.ru/eng/tisp169
https://www.mathnet.ru/eng/tisp/v27/i5/p5
This publication is cited in the following 5 articles:
Tsolak Ghukasyan, Yeva Yeshilbashyan, Karen Avetisyan, “Subwords-Only Alternatives to fastText for Morphologically Rich Languages”, Program Comput Soft, 47:1 (2021), 56
Ts. G. Gukasyan, “Vektornye modeli na osnove simvolnykh n-gramm dlya morfologicheskogo analiza tekstov”, Trudy ISP RAN, 32:2 (2020), 7–14
A. V. Glazkova, “Avtomaticheskii poisk fragmentov, soderzhaschikh biograficheskuyu informatsiyu, v tekste na estestvennom yazyke”, Trudy ISP RAN, 30:6 (2018), 221–236
Ksenia Lagutina, Vladislav Larionov, Vladislav Petryakov, Nadezhda Lagutina, Ilya Paramonov, 2018 23rd Conference of Open Innovations Association (FRUCT), 2018, 217
D. O. Mashkin, E. V. Kotelnikov, “Izvlechenie aspektnykh terminov na osnove uslovnykh sluchainykh polei i vektornykh predstavlenii slov”, Trudy ISP RAN, 28:6 (2016), 223–240
Citation in format AMSBIB
Contact us: