Eni Purnama
a:1:{s:5:"en_US";s:24:"Institut Pertanian Bogor";}

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

PENERAPAN METODE NAÏVE BAYES CLASSIFIER TERHADAP SENTIMEN MASYARAKAT PADA TAGAR #KABURAJADULU DI MEDIA SOSIAL TWITTER Eni Purnama; Bayu Suriaatmaja Suwanda
JURNAL DAYA-MAS Vol. 10 No. 2 (2025): JURNAL DAYA-MAS
Publisher : Universitas Merdeka Madiun

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33319/dymas.v10i2.182

Abstract

Twitter is a social media platform that allows its users to communicate in short messages and has become a space for expressing public opinion, including through the popular hashtag #kaburajadulu, which reflects the concerns of the young generation about social conditions and their dreams of seeking a better life abroad. This study aims to analyze public sentiment towards the hashtag using two approaches. First, sentiment classification was performed using the Naïve Bayes Classifier algorithm to divide tweets into positive, neutral, and negative categories. The process involved data collection, preprocessing, labeling, word weighting, classification, evaluation, and visualization. The classification results showed an accuracy of 56%. Second, a multinomial logistic regression analysis was conducted to determine the effect of three independent variables on sentiment. The results showed that all three variables had a significant influence, with varying degrees of contribution. These findings suggest that a combined approach between machine learning and statistical analysis can provide in-depth insights into communication patterns and public opinion on social issues emerging on social media, particularly in the context of migration and youth anxiety.