<![CDATA[Implementing machine learning in business has enabled producers and sellers to assess product quality by analyzing customer reviews through Sentiment Analysis (SA). This study investigates the impact of different stopword categories on the accuracy of the Multinomial Naïve Bayes (MNB) model for SA. This research considered ten stopword categories: general, conjunctions, slang, temporal terms, nouns, pronouns, interjections, adverbs, and single-letter words. A Friedman test conducted on commentary from three shoe products revealed that removing conjunction stopwords (MNB-conjunction) could potentially improve the predictive accuracy of the MNB model for SA by approximately 1%. A T-test further validated this result, showing that two out of three datasets provided evidence that MNB-conjunction outperformed the MNB model without removing stopwords.]]>
Copyrights © 2025
