Sentiment analysis on the hotel reviews in the Kazakh language

Banu Yergesh, Gulmira Bekmanova, Altynbek Sharipbay

2017

Closed access Metadata (CSL-JSON)
DOI 10.1109/ubmk.2017.8093531
Data confidence 70 medium
How this score is calculated

It is built from checkable properties of the record itself: whether the article has a DOI, how many independent sources confirmed its data, whether the required fields are filled in, and how recent the latest confirmation is. Disagreement between sources and a missing identifier lower it. A value of 80 or above means the record was published without further checking; 60 to 79 means it is published at reduced confidence, with a manual check advisable. A record verified by an editor by hand is never pushed below 90 by a recalculation. This scores our data about the article, not the article itself.

Abstract

We studied the texts in Kazakh and determined the parts of speech that define the text mood. Based on the conducted studies a lot of phrases were identified as determining the mood of the text. The technique of fuzzy inference associated with the estimation of the general level of the hotel state on the basis of the calculated criterion for each aspect is proposed. The criterion is measured in percent and is derived on the basis of fuzzy subjective estimates of the characteristics of the services of the hotel in the Kazakh language.