АНАЛИЗ ТОНАЛЬНОСТИ ТЕКСТОВЫХ ОТЗЫВОВ С ПРИМЕНЕНИЕМ ТОНАЛЬНЫХ СЛОВАРЕЙ И КАРДИНАЛЬНОСТИ НЕЧЕТКОГО МНОЖЕСТВА

Abstract

Sentiment or opinion analysis aims to determine the polarity of people's opinions in relationto any product, service, event or any person. One of the most common methods used in sentimentanalysis of text content is natural language processing. Sentiment analysis of natural languagetext can be assessed using numerous methodologies such as machine learning algorithms andstatistical tools, while the application of fuzzy logic is not common. The use of fuzzy logic waschosen for the following reasons. First, fuzzy logic handles linguistic uncertainty well. This way ofdefining the problem leads to a reduction in bias, both positively and negatively. Secondly, learning approaches based on fuzzy rules are fundamentally different from those learning approachesthat are widely used in sentiment classification, such as support vector machines, naive Bayes,etc., as they relate to generative learning, i.e. i.e. the goal of learning is to assess the degree towhich an instance belongs to each individual class. The proposed model for sentiment analysis oftext reviews is based on the use of tone lexicons using fuzzy logic and consists of four main stages.The steps include tokenization, word bag model formulation, sentiment fuzzy score formulation,and polarity assignment. In the proposed model, the power of the fuzzy set is used as a measure ofthe evaluation of the indicators of the polarity of words. Word polarity values are obtained byapplying two sentiment lexicons: SentiWordNet and AFINN. Two versions of the model were createddepending on the type of vocabulary used: based on SentiWordNet and AFINN. Comparisonof the presented approach based on fuzzy logic with other dictionary-based methods demonstratesthe superiority of the developed models based on the application of fuzzy logic.