INDECS 21(6), 607-622, 2023 DOI 10.7906/indecs.21.6.6 Full text available in pdf format.

Received: 10th July 2023. Accepted: 7th December 2023. Regular article

ABSTRACT

Sentiment analysis is a particular form of content analysis, and its application has become popular with the growth of Internet platforms where a wide range of content is generated. Today, various classifiers use for sentiment analysis, and in this article, we show an example of using a Naïve Bayesian classifier. The aim is to examine the consistency of classifying textual materials into a positive, negative or neutral tone by analysts and the Bayesian algorithm. The hypotheses are that there is an increase in the agreement between the two ways of classifying textual materials as (1) the complexity of the formulations and (2) the size of the learning datasets increases. Based on the results, both hypotheses were accepted, but only on certain groups of messages. Increasing the size of the learning datasets and increasing the complexity of the formulations helped the classification accuracy for messages in a positive tone, while the classification accuracy for messages in other tones was high and equal regardless of varying the parameters. Correlation analysis showed a high positive correlation between the outcomes the Bayesian algorithm classified and the tones the analyst determined (r = 0,816).

KEY WORDS
content analysis, sentiment analysis, naïve Bayes classifier

CLASSIFICATION

APA:	2240, 2260
JEL:	C38