Hoax classification and sentiment analysis of Indonesian news using Naive Bayes optimization

Abstract

Currently, the spread of hoax news has increased significantly, especially on social media networks. Hoax news is very dangerous and can provoke readers. So, this requires special handling. This research proposed a hoax news detection system using searching, snippet and cosine similarity methods to classify hoax news. This method is proposed because the searching method does not require training data, so it is practical to use and always up to date. In addition, one of the drawbacks of the existing approaches is they are not equipped with a sentiment analysis feature. In our system, sentiment analysis is carried out after hoax news is detected. The goal is to extract the true hidden sentiment inside hoax whether positive sentiment or negative sentiment. In the process of sentiment analysis, the Naïve Bayes (NB) method was used which was optimized using the Particle Swarm Optimization (PSO) method. Based on the results of experiment on 30 hoax news samples that are widely spread on social media networks, the average of hoax news detection reaches 77% of accuracy, where each news is correctly identified as a hoax in the range between 66% and 91% of accuracy. In addition, the proposed sentiment analysis method proved to has a better performance than the previous analysis sentiment method.

Hoax Distribution in Social Media After Ratification of Omnibus Law

“…Social media is the channel in which the most hoax content is spread (Santoso et al, 2020). This can happen because one of the distinctive characteristics of social media is that every social media user is not only a consumer of information, but every user is also a producer and distributor of information circulating on social media (Weeks & Holbert, 2013).…”

Analysis of spammers’ behavior on a live streaming chat

“…The similarity of chat message (Sim) is an estimate of the degree of similarity between two chat messages from the same user. In this study, we used the result of the calculation of cosine similarity [17] to represent the degree of message similarity. Cosine similarity [18][19] is the traditional method used to measure the degree of similarity between two vectors, obtained from the cosine angle multiplication.…”

“…SentiStrength [20], SentiWordNet and AFINN are sentiment lexicon classification tools that are often used to estimate the strength of positive and negative sentiment of words. These methods can be applied to identify the polarity of the comments as being positive, negative, or neutral [17,21].…”

Klasifikasi Rating Otomatis pada Dokumen Teks Ulasan Produk Elektronik Menggunakan Metode N-gram dan Naïve Bayes

“…Untuk mendapatkan bobot term dapat dilihat pada persamaan 1. (Santoso et al, 2020). Naïve Bayes dapat memperkirakan peluang yang mungkin terjadi di masa depan dengan melihat data-data sebelumnya dengan ciri khas berupa independensi dari masingmasing kondisi.…”