Parametrical words in the sentiment lexicon

In this paper, the main features of parametrical words within a sentiment lexicon are determined. The data for the research are client reviews in the Russian language taken from the bank client rating; the domain under study is bank service quality. The sentiment lexicon structure is presented; it includes two primary classes (positive and negative words) and three secondary classes (increments, polarity modifiers, and polarity anti-modifiers). This lexicon is used as the main tool for the sentiment analysis carried out by two methods: the Naïve Bayes classifier and the REGEX algorithm. Parametrical words are referred to as the words denoting the value of some domain-specific parameter, e.g. the client’s time consuming. To distinguish the main features of parametrical words, the parameters relevant for the bank service quality domain are determined. The revised lexicon structure is proposed, with a new class (decrements) added. The results of the research demonstrate that parametrical words express implicit opinions, since parameters are not usually named directly in reviews. Only a small number of parametrical words can be ranged into the primary classes (positive or negative), but this ranging is domain-specific. It is the parameter that determines the domain specificity of such words. Most parametrical words are ranged into the secondary classes, and this ranging can be considered universal. The parametrical words denoting the increase of a parameter should be ranged into the increment class, as they intensify positive or negative emotions. The parametrical words denoting the decrease of a parameter should be ranged into the decrement class, as they reduce positive or negative emotions. The evident progress on the way to the sentiment lexicon universalization can be achieved by classifying parametrical words within the sentiment lexicon.