ÚFAL: Using Hand-crafted Rules in Aspect Based Sentiment Analysis on Parsed Data

Proceedings of the 8th International Workshop on Semantic Evaluation (SemEval 2014), pages 694–698, Dublin, Ireland, August 23-24, 2014. ´UFAL: Using Hand-crafted Rules in Aspect Based Sentiment Analysis on Parsed Data Kateˇrina Veselovsk´a, Aleˇs Tamchyna Charles University in Prague, Faculty of Mathematics and Physics Institute of Formal and Applied Linguistics Malostransk´e n´amˇest´ı 25, Prague, Czech Republic {veselovska,tamchyna}@ufal.mff.cuni.cz Abstract This paper describes our submission to Se- mEval 2014 Task 41 (aspect based senti- ment analysis). The current work is based on the assumption that it could be advan- tageous to connect the subtasks into one workflow, not necessarily following their given order. We took part in all four sub- tasks (aspect term extraction, aspect term polarity, aspect category detection, aspect category polarity), using polarity items de- tection via various subjectivity lexicons and employing a rule-based system ap- plied on dependency data. To determine aspect categories, we simply look up their WordNet hypernyms. For such a basic method using no machine learning tech- niques, we consider the results rather sat- isfactory. 1 Introduction In a real-life scenario, we usually do not have any golden aspects at our disposal. Therefore, it could be practical to be able to extract both aspects and their polarities at once. So we first parse the data, bearing in mind that it is very difficult to detect both sources/targets and their aspects on plain text corpora. This holds especially for pro-drop lan- guages, e.g. Czech (Veselovsk´a et al., 2014) but the proposed method is still language independent to some extent. Secondly, we detect the polar- ity items in the parsed text using a union of two different existing subjectivity lexicons (see Sec- tion 2). Afterwards, we extract the aspect terms in the dependency structures containing polarity ex- 1http://alt.qcri.org/semeval2014/ task4/ This work is licensed under a Creative Commons At- tribution 4.0 International Licence. Page numbers and pro- ceedings footer are added by the organisers. Licence details: http://creativecommons.org/licenses/by/4.0/ pressions. In this task, we employ several hand- crafted rules detecting aspects based on syntactic features of the evaluative sentences, inspired by the method by Qiu et al. (2011). Finally, we iden- tify aspect term categories with the help of the En- glish WordNet and derive their polarities based on the polarities of individual aspects. The obtained results are discussed in Section 4. 2 Related Work This work is related to polarity detection based on a list of evaluative items, i.e. subjectivity lexi- cons, generally described e.g. in Taboada et al. (2011). The English ones we use are minutely de- scribed in Wiebe et al. (2005) and several papers by Bing Liu, starting with Hu and Liu (2004). In- spired by Kobayashi et al. (2007), who make use of evaluative expressions when learning syntac- tic patterns obtained via pattern mining to extract aspect-evaluation pairs, we use the opinion words to detect evaluative structures in parsed data. The issue of target extraction in sentiment analysis is discussed in articles proposing different methods, mainly tested on product review datasets (Popescu and Etzioni, 2005; Mei et …

Content truncated to 500 words