ABSTRACT
In recent years, hate speech on social media has become a common phenomenon in the Ethiopian online community particularly due to the substantial growth of users. As part of our country’s language Efik language Facebook users also increased in recent years. In line with this, hate speech in the Efik language is also increased. The reason could be due to, political instabilities. Hate speech on social media has the potential to quickly disseminate through online users that could escalate an act of violence and hate crime among people. To address this problem, this research proposed hate speech detection using machine learning and text-mining feature extraction techniques to build a detection model. Hate speech data written in the Efik language was collected from the Facebook public page and manually labeled into hate and hate-free classes to build binary class datasets. The research employed an experimental approach to determine the best combination of the machine learning algorithm and feature extraction for modeling. Support Vector Machine (SVM), Naïve Bayes (NB), and Random Forest (RF)classification algorithms are employed to construct a hate speech detection model using the whole dataset with the extracted features based on word unigram, bigram, trigram, as well as combined n-grams and TFIDF. An experimental result shows that the Naïve Bayes classification algorithm with TFDF feature extraction achieved slightly better performance than the SVM and RF models for hate speech detection with 79% accuracy. In this study, we achieved a promising result for designing hate speech detection for the Efik language. Since there is no data set available for experimentation, we used limited data for constructing an optimal hate speech detection model using a machine learning classification algorithm. Hence, we recommend the need to prepare a standard corpus for hate speech detection in local languages, including the Efik language.
The Hate Speech Detection from Facebook Social Media Posts and Comments in Efik Language, GET MORE COMPUTER SCIENCE PROJECT TOPICS AND MATERIALS
