A briefly overview about
Sentiment Analysis and Aspect Term Extraction
Sentiment Analysis(or Opinion Mining) is the task of identifying what the user thinks about a particular element. In particular, it often takes the form of an annotation task with the purpose of annotating a portion of text with a positive, negative, or neutral label. Aspect-based SentimentAnalysis(ABSA) is an evolution of Sentiment Analysis that aims at capturing the aspect-level opinions expressed in natural language texts [Liu07]. Very often, the ABSA task is performed on a set of aspects defined a priori, limiting its applicability in the real scenario.Aspect TermExtraction(ATE) is the task of identifying an "aspect" in a text without knowing a priori the list that contains it. According to the literature definition, a term/phrase is considered as an aspect when it co-occurs with some “opinion words” that indicate a sentiment polarity on it [Pea16a].At the international level, SemEval, the most prominent evaluation campaign in the Natural Language Processing field, in 2014 SE-ABSA14 [Pea14] provided a benchmark dataset of reviews in English language for the ABSA task. Given a set of sentences with pre-identified entities (e.g.,restaurants), the task was about identifying the aspect terms present in the sentences and returning a list containing all the distinct aspect terms. Then for the set of aspect terms within a sentence, it was asked to determine whether the polarity of each aspect term is positive, negative, neutral or conflict. The same task was replicated in 2015, 2016, consolidating the four subtasks of SE-ABSA14 [Pea14] within a unified framework. In addition, SE-ABSA15 [Pea16b] included an out-of-domain ABSA subtask, involving test data from a domain unknown to the participants.ABSA is not a novel task at EVALITA. A first edition was proposed at EVALITA 2018 by [Bea18]. The task was subdivided into two subtasks: Aspect Category Detection (ACD) and Aspect Cate-gory Polarity (ACP). The first was about the identification of categories mentioned into the review, knowing the categories a priori. The latter was about the detection of the polarity of the opinion of the user about the previous detected categories. However, it bears some similarities with at least other two tasks from the previous editions of the campaign. SENTIPOLC, featured in the2014 and 2016 editions of EVALITA, is a shared task on the polarity classification of social media content. The other is NEEL-it, held at EVALITA 2016. NEEL-it is the task of Named EntityRecognition and Linking, that is, the task of identifying the spans of an input text that refer to named entities, and linking them to entries in a knowledge base, e.g., pages of Wikipedia.
References
[Bea18] Pierpaolo Basile et al. Overview of the evalita 2018 aspect-based sentiment analysis task (absita). EVALITA Evaluation of NLP and Speech Tools for Italian, 2018.
[BN14] Pierpaolo Basile and Nicole Novielli. Uniba at evalita 2014-sentipolc task predicting tweet sentiment polarity combining micro-blogging, lexicon and semantic features. UNIBA at EVALITA 2014-SENTIPOLC Task Predicting tweet sentiment polarity combining micro-blogging, lexicon and semantic features., pages 58–63, 2014.
[FGM05]Jenny Rose Finkel, Trond Grenager, and Christopher Manning. Incorporating non- local information into information extraction systems by gibbs sampling. In Proceed- ings of the 43rd Annual Meeting of the Association for Computational Linguistics (ACL’05), page 363–370. Association for Computational Linguistics, Jun 2005.
[Liu07] Bing Liu. Web data mining. Springer, 2007.
[PBdG+19] Marco Polignano, Pierpaolo Basile, Marco de Gemmis, Giovanni Semeraro, and Valerio Basile. Alberto: Italian bert language understanding model for nlp challenging tasks based on tweets. In Proceedings of the Sixth Italian Conference on Computational Linguistics (CLiC-it 2019). CEUR, 2019.
[Pea14] Maria Pontiki et al. Semeval-2014 task 4: Aspect based sentiment analysis. In Pro- ceedings of the 8th International Workshop on Semantic Evaluation, 2014.
[Pea16b Maria Pontiki et al. SemEval-2016 task 5: Aspect based sentiment analysis. In Proceedings of the 10th International Workshop on Semantic Evaluation, SemEval ’16, San Diego, California, June 2016. Association for Computational Linguistics.
