Hatespeech Detection Using Neural Network – Naïve Bayes Classifier with Twitter Dataset

Ramadhan, Reza Wahyu (2024) Hatespeech Detection Using Neural Network – Naïve Bayes Classifier with Twitter Dataset. Masters thesis, Faculty of Intelligent Electrical and Informatics Technology.

Text RezaWahyuRamadhan_BukuTesis.pdf - Accepted Version Restricted to Repository staff only until 1 October 2026. Download (3MB)

Abstract

Indonesia is one of the largest social media users in the world, with Twitter/X being a particularly popular platform, ranking sixth in the world for the number of users. However, this massive use of social media also presents significant challenges related to hate speech. Hate speech on social media is a concerning issue because it can spread quickly and widely influence audiences, potentially leading to real-world violence. Despite this, there is still a lack of research aimed at developing better models for the Indonesian language.
Naive Bayes (NB) is one of the traditional models commonly used for text detection. NB is a probabilistic model based on the assumption of feature independence. However, in text data classification, the relationships between features are important. The Artificial Neural Network (ANN) model can be used to overcome the weaknesses of the NB model. ANN can capture and model non-linear relationships between features in the data. By using ANN for feature extraction, feature representation becomes more refined, allowing NB to work with more informative and relevant features, thereby enhancing the performance of the NB model.
Implementing ANN feature extraction on NB (ANN-NB) in this study has proven to improve the NB model's performance in both classical scenarios of splitting the dataset into 70:30 and in data stream mining scenarios. The highest accuracy achieved was 97.6% which measured by confusion matrix.

Item Type:	Thesis (Masters)
Subjects:	Q Science > Q Science (General) > Q325.5 Machine learning. Support vector machines.
Divisions:	Faculty of Intelligent Electrical and Informatics Technology (ELECTICS) > Informatics Engineering > 55101-(S2) Master Thesis
Depositing User:	Reza Wahyu Ramadhan
Date Deposited:	06 Aug 2024 03:23
Last Modified:	25 Sep 2024 02:42
URI:	http://repository.its.ac.id/id/eprint/112815

Actions (login required)

View Item