No abstract

This paper describes the NILC USP system that participated in SemEval-2014 Task 9: Sentiment Analysis in Twitter, a re-run of the SemEval 2013 task under the same name. Our system is an improved version of the system that participated in the 2013 task. This system adopts a hybrid classification process that uses three classification approaches: rule-based, lexiconbased and machine learning. We suggest a pipeline architecture that extracts the best characteristics from each classifier. In this work, we want to verify how this hybrid approach would improve with better classifiers. The improved system achieved an F-score of 65.39% in the Twitter message-level subtask for 2013 dataset (+ 9.08% of improvement) and 63.94% for 2014 dataset.

Abstract-This paper presents some results on lexicon-based classification of sentiment polarity in web reviews of products written in Brazilian Portuguese. They represent a first step towards a robust opinion miner from reviews of technology products. The evaluation shows the performance of 3 different sentiment lexicons combined with simple strategies. It is also discussed the risk of considering the rating provided by the writers for the purpose of evaluating the algorithms. The results show that the better combination is the version of the algorithm that deals also with negation and intensification and uses the sentiment lexicon Sentilex. The average F-measure achieved 0.73.

This paper describes the analysis of different kinds of noises in a corpus of products reviews in Brazilian Portuguese. Case folding, punctuation, spelling and the use of internet slang are the major kinds of noise we face. After noting the effect of these noises on the POS tagging task, we propose some procedures to minimize them.

User-generated contents (UGC) represent an important source of information for governments, companies, political candidates and consumers. However, most of the Natural Language Processing tools and techniques are developed from and for texts of standard language, and UGC is a type of text especially full of creativity and idiosyncrasies, which represents noise for NLP purposes. This paper presents UGCNormal, a lexicon-based tool for UGC normalization. It encompasses a tokenizer, a sentence segmentation tool, a phonetic-based speller and some lexicons, which were originated from a deep analysis of a corpus of product reviews in Brazilian Portuguese. The normalizer was evaluated in two different data sets and carried out from 31% to 89% of the appropriate corrections, depending on the type of text noise. The use of UGCNormal was also validated in a task of POS tagging, which improved from 91.35% to 93.15% in accuracy and in a task of opinion classification, which improved the average of F1-score measures (F1-score positive and F1-score negative) from 0.736 to 0.758.