Evaluation of different extractors of features at the level of sentiment analysis

Abstract

Sentiment analysis is the process of recognizing and categorizing the emotions being expressed in a textual source. Tweets are commonly used to generate a large amount of sentiment data after they are analyzed. These feelings data help to learn about people's thoughts on a various range of topics. People are typically attracted for researching positive and negative reviews, which contain dislikes and likes, shared by the consumers concerning the features of a certain service or product. Therefore, the aspects or features of the product/ service play an important role in opinion mining. Furthermore to enough work being carried out in text mining, feature extraction in opinion mining is presently becoming a hot research field. In this paper, we focus on the study of feature extractors because of their importance in classification performance. The feature extraction is the most critical aspect of opinion classification since classification efficiency can be degraded if features are not properly chosen. A few scientific researchers have addressed the issue of feature extraction. And we found in the literature that almost every article deals with one or two feature extractors. For that, we decided in this paper to cover all the most popular feature extractors which are BOW, N-grams, TF-IDF, Word2vec, GloVe and FastText. In general, this paper will discuss the existing feature extractors in the opinion mining domain. Also, it will present the advantages and the inconveniences of each extractor. Moreover, a comparative study is performed for determining the most efficient combination CNN/extractor in terms of accuracy, precision, recall, and F1 measure.