Supervised Methods for Aspect-Based Sentiment Analysis

Proceedings of the 8th International Workshop on Semantic Evaluation (SemEval 2014), pages 596–600, Dublin, Ireland, August 23-24, 2014. Supervised Methods for Aspect-Based Sentiment Analysis Hussam Hamdan*,**,*** *LSIS Aix-Marseille Université CNRS Av. Esc. Normandie Niemen, 13397 Marseille Cedex 20, France hussam.hamdan@lsis.org Patrice Bellot*,** **OpenEdition Aix-Marseille Université CNRS 3 pl. V. Hugo, case n°86 13331 Marseille Cedex 3, France patrice.bellot@lsis.org Frederic Béchet*** ***LIF Aix-Marseille Université CNRS Avenue de Luminy 13288 Marseille Cedex 9, France frederic.bechet@lif.univ-mrs.fr Abstract In this paper, we present our contribution in SemEval2014 ABSA task, some supervised methods for Aspect-Based Sentiment Analysis of restaurant and laptop reviews are proposed, im- plemented and evaluated. We focus on determin- ing the aspect terms existing in each sentence, finding out their polarities, detecting the catego- ries of the sentence and the polarity of each cate- gory. The evaluation results of our proposed methods exhibit a significant improvement in terms of accuracy and f-measure over all four subtasks regarding to the baseline proposed by SemEval organisers. 1 Introduction The increasing amount of user-generated textual data has increased the need of efficient tech- niques for analysing it. Sentiment Analysis (SA) has become more and more interesting since the year 2000 (Liu 2012), many techniques in Natu- ral Language Processing have been used to un- derstand the expressed sentiment on an entity. Many levels of granularity have been also distin- guished: Document Level SA considers the whole document is about an entity and classifies whether the expressed sentiment is positive, neg- ative or neutral; Sentence Level SA determines the sentiment of each sentence, some works have been done on Clause Level SA but they are still not enough; Entity or Aspect-Based SA performs finer-grained analysis in which all entities and This work is licensed under a Creative Commons At- tribution 4.0 International Licence. Page numbers and proceedings footer are added by the organisers. Li- cence details: http://creativecommons.org/licenses/by/4.0/ their aspects should be extracted and the senti- ment on them should also be determined. Aspect-Based SA task consists of several sub- problems, the document is about many entities which could be for example a restaurant, a lap- top, a printer. Users may refer to an entity by different writings but normally there are not a lot of variations to indicate the same entity, each entity has many aspects which could be its parts or attributes, some aspects could be another enti- ty such as screen of laptop, but most works did not take this case into account. Therefore, we could define the opinion by the quintuple (Liu 2012) (ei, aij, sijkl, hk, tl) where ei is the entity i, aij are the aspects of the entity i, sijkl is the ex- pressed sentiment on the aspect at the time tl, hk the holder which created the document or the text. This definition does not take into account that the entity has aspects that could have also other as- pects which leads to an aspect hierarchy, in order to avoid this information loss, few works have handled this issue, …

Content truncated to 500 words