<![CDATA[The rapid growth of social media in Indonesia has intensified the spread of fake news, posing serious threats to public opinion, social stability, and democratic processes. This research proposes a fake news detection model based on sentiment analysis of Indonesian public opinion using Naïve Bayes and Deep Neural Network (DNN) classification methods. Textual data were collected from 4,990 records across Instagram (1,298), Twitter/X (2,004), and Facebook (1,690), with fact-checking verification conducted using TurnBackHoax (MAFINDO). After preprocessing — including normalization, tokenization, stopword removal, and stemming — 4,548 records were retained. Sentiment analysis was applied to capture public emotional tendencies, followed by TF-IDF feature extraction. The Naïve Bayes classifier achieved 87.25% accuracy, with macro recall of 0.5633 and macro F1-score of 0.6382. The DNN model achieved higher accuracy at 90.99%, with macro recall of 0.7204 and macro F1-score of 0.7951, demonstrating better performance across minority sentiment classes. These findings confirm that integrating sentiment analysis with machine learning and deep learning approaches significantly enhances fake news detection on Indonesian social media, with DNN models showing strong potential for deployment in automated detection systems driven by public opinion, thereby supporting more effective misinformation mitigation and national digital literacy initiatives in Indonesia.]]>
Copyrights © 2026
