Tuning Hyperparameters of Machine Learning Methods for Afan Oromo Hate Speech Text Detection for Social Media

Hate speech towards a group or an individual based on their perceived identity, such as ethnicity, religion, or nationality, is widely and rapidly spreading on social media platforms. This causes harmful impacts on users of these platforms and the quality of online shared content. Fortunately, researchers have developed different machine learning algorithms to automatically detect hate speech on social media platforms. However, most of these algorithms focus on the detection of hate speech that appears in English. There is a lack of studies on the detection of hate speech in Arabic due to the language’s complex nature. This paper aims to address this issue by proposing an effective approach for detecting Arabic hate speech on social media platforms, namely Twitter. Therefore, this paper introduces the Arabic BERT-Mini Model (ABMM) to identify hate speech on social media. More specifically, the bidirectional encoder representations from transformers (BERT) model was employed to analyze data collected from Twitter and classify the results into three categories: normal, abuse, and hate speech. In order to evaluate our model and state-of-the-art approaches, we conducted a series of experiments on Twitter data. In comparison with previous works on Arabic hate-speech detection, the ABMM model shows very promising results with an accuracy score of 0.986 compared to the other models.

Hate speech is a form of negative communication intended to harm people and communities. Hate speech is quite common in the real world, and it has reached alarming proportions on social media as well. These days our lives have become increasingly reliant on social media platforms, such as Facebook. This is due to the rapid advancement of technology and communication. In Bangladesh, the number of people using social media platforms is also rapidly increasing. In English, detecting hate speech on social media is a difficult task. Comparatively, Bengali is a complicated language with few datasets available. As a result, detection of Bengali hate speech becomes even more challenging. In this paper, we present a new dataset of 10,133 user comments. We have collected them from the comment section of various public Facebook pages. We explore the performance of various machine learning and deep learning models in detecting hate speech. Bengali pre-trained word embeddings from fastText are used to train the models. We are especially interested in Convolutional Neural Network (CNN). To our knowledge it was never used for hate speech detection in binary classification. Another goal of this research is to create a new and large dataset, which will facilitate further research of Bengali Hate Speech Detection. All machine learning and deep learning models performed very well from our experiments. But, Support Vector Machine (SVM) is the one that performed the best among them.

Social media has changed the world and play an important role in people lives. Social media platforms like Twitter, Facebook and YouTube create a new dimension of communication by providing channels to express and exchange ideas freely. Although the evolution brings numerous benefits, the dynamic environment and the allowable of anonymous posts could expose the uglier side of humanity. Irresponsible people would abuse the freedom of speech by aggressively express opinion or idea that incites hatred. This study performs hate speech and offensive language detection. The problem of this task is there is no clear boundary between hate speech and offensive language. In this study, a selected new features set is proposed for detecting hate speech and offensive language. Using Twitter dataset, the experiments are performed by considering the combination of word n-gram and enhanced syntactic n-gram. To reduce the feature set, filter-embedded combining feature selection is used. The experimental results indicate that the combination of word n-gram and enhanced syntactic n-gram with feature selection to classify the data into three classes: hate speech, offensive language or neither could give good performance. The result reaches 91% for accuracy and the averages of precision, recall and F1.

Hate speech has long been a prevalent issue offline, but with the rise of the internet and social media, its spread has accelerated. The anonymity afforded by these platforms enables individuals to engage in hate speech often without facing substantial consequences. As technology continues to evolve, new opportunities arise to tackle this problem, particularly through the use of natural language processing (NLP). NLP technology can help automate processes that have traditionally been done manually, such as flagging hate speech in online content. Yet, many issues remain unresolved before we can achieve efficient hate speech detection systems. These include foundational challenges, such as defining hate speech, as well as issues that arise at the end of an NLP pipeline, such as evaluating whether a model can generalize. Additionally, the issue of bias in models poses a significant challenge, as biased training data can lead to inaccurate or unfair results. In this thesis, I will focus on addressing these issues. First, I examine the definitions of hate speech and related concepts like toxicity and abusive language, and their impact on re-annotated datasets. I then compare the original and re-annotated labels in terms of robustness and generalization using a BERT-based classifier. Next, I explore the use of hate speech legislation from three countries for annotation, expanding the task of hate speech detection to prosecutable hate speech detection. The results show even law interpretation can be subjective, which has a consequent effect on model training and evaluation. To address this issue, I introduce a semantic componential analysis of hate speech definitions, leading to the creation of the HateDefCon corpus. Moreover, I present a pipeline for generating parallel multilingual hate speech corpora and discuss the associated challenges. The thesis concludes with an examination of textual biases based on the psycholinguistic aspects of harmful language.

Online hate has emerged as a rapidly growing issue worldwide, often stemming from differences in opinion. It is crucial to use appropriate language and words on social media platforms, as inappropriate communication can negatively impact others. Consequently, detecting hate speech is of significant importance. While manual methods are commonly employed to identify hate and offensive content on social media, they are time-consuming, labor-intensive, and prone to errors. Therefore, AI-based approaches are increasingly being adopted for the effective classification of hate and offensive speech. The proposed model incorporates various text preprocessing techniques, such as removing extraneous elements like URLs, emojis, and blank spaces. Following preprocessing, tokenization is applied to break down the text into smaller components or tokens. The tokenization technique utilized in this study is TF-IDF (Term Frequency–Inverse Document Frequency). After tokenization, the model performs the classification of hate and offensive speech using the proposed BiLSTM-based SM-CJ (Scalable Multi-Channel Joint) framework. The BiLSTM-based SM-CJ model is particularly effective in detecting hate, offensive, and neutral tweets due to its ability to capture both forward and backward contexts within a given text. Detecting hate speech requires a comprehensive understanding of the text and the identification of patterns spanning across multiple words or phrases. To achieve this, the LSTM component of the BiLSTM model is designed to capture long-term dependencies by utilizing information from earlier parts of the text. The proposed SM-CJ framework further aligns the input sequence lengths fetched from the input layer, enabling the model to focus on specific segments of the input sequence that are most relevant for hate speech detection. This approach allows the model to accurately capture derogatory language, and subtle nuances present in hate speech. Finally, the performance of the proposed framework is evaluated using various metrics, including accuracy, recall, F1-score, and precision. The results are compared with state-of-the-art approaches, demonstrating the effectiveness of the proposed model. Doi: 10.28991/ESJ-2025-09-01-03 Full Text: PDF

In recent times, the Internet and social media are very well-known and popular among people. Usage of social media is increased exponentially during the last few years globally, and it allows people to engage with one another and share ideas, thoughts, opinions, etc. Every day, massive amounts of data are disseminated at breakneck speed via social media platforms, reaching a massive audience. Furthermore, the ability to write anonymous posts and comments makes expressing and spreading hate speech even easier. To improve the users’ experience, social media sites are attempting to remove hateful remarks. In this research work, the main focus is on developing automated hate speech and offensive language detection models. Started with traditional hate speech and offensive language identification approaches, than reaches to advanced hate speech recognition methods for social media. This brings a need for integrated datasets and the hate speech prediction method. This paper describes the study on hate speech and offensive content identification in English language by using the various approaches based on machine learning algorithms (Support vector machine, decision tree, and so on) and NLP, along with the features used for the classification problem. The models were tested on the HASOC (2021) datasets and concluded that the ensemble model perform better than other algorithms with the test dataset for different tasks. Results and analysis part of this paper offers researchers a comprehensive picture of approaches.

The aim of this paper is to review machine learning (ML) algorithms and techniques for hate speech detection in social media (SM). Hate speech problem is normally model as a text classification task. In this study, we examined the basic baseline components of hate speech classification using ML algorithms. There are five basic baseline components – data collection and exploration, feature extraction, dimensionality reduction, classifier selection and training, and model evaluation, were reviewed. There have been improvements in ML algorithms that were employed for hate speech detection over time. New datasets and different performance metrics have been proposed in the literature. To keep the researchers informed regarding these trends in the automatic detection of hate speech, it calls for a comprehensive and an updated state-of-the-art. The contributions of this study are three-fold. First to equip the readers with the necessary information on the critical steps involved in hate speech detection using ML algorithms. Secondly, the weaknesses and strengths of each method is critically evaluated to guide researchers in the algorithm choice dilemma. Lastly, some research gaps and open challenges were identified. The different variants of ML techniques were reviewed which include classical ML, ensemble approach and deep learning methods. Researchers and professionals alike will benefit immensely from this study.

This article investigates the identification of hate speech on social media using machine learning and deep learning techniques. The research uses metrics such as F-measure, AUC-ROC, precision, accuracy, and recall assessing the effectiveness of various tactics. The findings indicate that deep learning models, particularly the bidirectional long short-term memory (BiLSTM) architecture, consistently outperform other methods in categorization tasks. The research emphasizes the importance of sophisticated neural network designs in identifying the intricacies of hostile and offensive content online. The study offers insights for promoting early identification and prevention of cyberbullying, improving secure and inclusive online environments. Future research may explore real-time detection systems, hybrid approaches, or the integration of complementary components to enhance and improve innovative technology in tackling this significant social issue. A sample tweet was annotated by specialists who categorize tweets as hate speech, offensive language, or neutral. The researchers applied shallow learning methodologies and integrated word embeddings like Word2Vec and GloVe to enhance the efficacy of deep learning models. The results indicate that BiLSTM surpasses shallow learning methods in detecting hate speech on Twitter, highlighting the efficacy of deep learning approaches in recognizing and tracking hate speech on social media platforms. When comparing different deep learning and machine learning models on different datasets, the results reveal that deep learning techniques are usually more effective. A reasonably high level of accuracy is achieved by KNN and SVM among classical algorithms, whereas Naïve Bayes performs the poorest. While deep learning approaches provide better results, tree-based models such as Random Forest and Decision Trees offer more consistent accuracy. Models based on neural networks, such as LSTM, CNN, and BI-LSTM, perform well, with LSTM-based methods excelling in particular. The most successful strategy for classification problems is the model presented, which obtains the greatest accuracy, precision, recall, F1-score of 95%. The research aids in the development of advanced tools and methodologies to mitigate hate speech on social media and foster positive online interactions. Future research may investigate alternative deep learning architectures, such as transformers, to enhance hate speech detection efficacy. The advancement of interpretable AI methodologies for identifying hate speech and delivering transparent forecasts might enhance user confidence and facilitate better content moderation decisions.

Technological developments over the past few decades have changed the way people communicate, with platforms like social media and blogs becoming vital channels for international conversation. Even though hate speech is vigorously suppressed on social media, it is still a concern that needs to be constantly recognized and observed. The Arabic language poses particular difficulties in the detection of hate speech, despite the considerable efforts made in this area for English-language social media content. Arabic calls for particular consideration when it comes to hate speech detection because of its many dialects and linguistic nuances. Another degree of complication is added by the widespread practice of "code-mixing," in which users merge various languages smoothly. Recognizing this research vacuum, the study aims to close it by examining how well machine learning models containing variation features can detect hate speech, especially when it comes to Arabic tweets featuring code-mixing. Therefore, the objective of this study is to assess and compare the effectiveness of different features and machine learning models for hate speech detection on Arabic hate speech and code-mixing hate speech datasets. To achieve the objectives, the methodology used includes data collection, data pre-processing, feature extraction, the construction of classification models, and the evaluation of the constructed classification models. The findings from the analysis revealed that the TF-IDF feature, when employed with the SGD model, attained the highest accuracy, reaching 98.21%. Subsequently, these results were contrasted with outcomes from three existing studies, and the proposed method outperformed them, underscoring the significance of the proposed method. Consequently, our study carries practical implications and serves as a foundational exploration in the realm of automated hate speech detection in text.

Over the last two decades, social media platforms have grown dramatically. Twitter and Facebook are the two most popular social media platforms, with millions of active users posting billions of messages daily. These platforms allow users to have freedom of expression. However, some users exploit this facility by disseminating hate speeches. Manual detection and censorship of such hate speeches are impractical; thus, an automatic detection mechanism is required to detect and counter hate speeches in a real-time environment. Most research in hate speech detection has been carried out in the English language. Still, minimal work has been explored in other languages, mainly Urdu written in Roman Urdu script. A few research have attempted machine learning, and deep learning models for Roman Urdu hate speech detection; however, due to a scarcity of Roman Urdu resources, and a large corpus with defined annotation rules, a robust hate speech detection model is still required. With this motivation, this study contributes in the following manner: we developed annotation guidelines for Roman Urdu Hate Speech. Second, we constructed a new Roman Urdu Hate Speech Dataset (RU-HSD-30K) that was annotated by a team of experts using the annotation rules. To the best of our knowledge, the Bi-LSTM model with an attention layer for Roman-Urdu Hate Speech Detection has not been explored. Therefore, we developed a context-aware Roman Urdu Hate Speech detection model based on Bi-LSTM with an attention layer and used custom word2vec for word embeddings. Finally, we examined the effect of lexical normalization of Roman Urdu words on the performance of the proposed model. Different traditional as well as deep learning models, including LSTM and CNN models, were used as baseline models. The performance of the models was assessed in terms of evaluation matrices like accuracy, precision, recall, and F1-score. The generalization of each model is also evaluated on a cross-domain dataset. Experimental results revealed that Bi-LSTM with attention outperformed the traditional machine learning models and other deep learning models with an accuracy score of 0.875 and an F-Score of 0.885. In addition, the results demonstrated that our suggested model (Bi-LSTM with Attention Layer) is more general than previous models when applied to unseen data. The results confirmed that lexical normalization of Roman Urdu words enhanced the performance of the suggested model.

As the use of internet and social media increases, hate speech has emerged as a significant issue. Hateful remarks are made anonymously by most users, and the incidence of harmful conversations, particularly on controversial subjects, increases. These kinds of content make readers feel upset and help create an unhealthy online environment. This study aims to address this problem by exploring the use of transformer models in hate speech identification and moderation of Malayalam social media posts. Based on a dataset from the DravidianLangTech competition, we train and test various transformer models for hate speech classification. This study aims to improve automated hate speech detection and removal tools for social media to provide a cleaner digital environment.

The CASE@EACL2024 Shared Task addresses Climate Activism online through three subtasks that focus on hate speech detection (Subtask A), hate speech target classification (Subtask B), and stance detection (Subtask C) respectively.Our contribution examines the effect of finetuning on external data for each of these subtasks.For the two subtasks that focus on hate speech, we augment the training data with the OLID (Zampieri et al., 2019a) dataset, whereas for the stance subtask we harness the SemEval-2016 Stance dataset (Mohammad et al., 2016b).We fine-tune RoBERTa and DeBERTa models for each of the subtasks, with and without external training data.For the hate speech detection and stance detection subtasks, our RoBERTa models came up third and first on the leaderboard, respectively.While the use of external data was not relevant on those tasks, we found that it greatly improved the performance on the hate speech target categorization.

This study focuses on the detection and analysis of Islamophobic hate speech on the TikTok platform. Social media platforms have a great impact in terms of reaching masses and sharing information. However, these platforms can also pave the way for the spread of negative content such as hate speech and discrimination. TikTok draws attention with its short video format, which is especially popular among young people. For this reason, it offers an important area of investigation in terms of the spread of hate speech and discrimination content. In this study, posts containing Islamophobic hate speech on TikTok were identified through the keywords ‘Islam’, ‘Muslim’, ‘Terrorist’, ‘Jihad’, ‘Sharia’, ‘Radical Islam’ and ‘Islamist’. These keywords were chosen from the terms that commonly define Islamophobic discourse in the literature. The 10 TikTok posts selected using simple random sampling technique were analysed by critical discourse analysis method. Critical discourse analysis is a method that analyses how texts and speeches gain meaning in the social context and how these meanings reflect social power relations. In the study, linguistic and visual analyses of Islamophobic content on TikTok were conducted. The research was conducted in the first six months of 2024. The data collection process carried out during this period was obtained as a result of the scans carried out on TikTok using the keywords mentioned above. The results of the study show that Islamophobic hate speech is spread linguistically and discursively through posts on TikTok. Islamophobic content reinforces negative stereotypes against Muslims and damages social cohesion. Such content leads to marginalisation, exclusion and violence against Muslims. Islamophobia and hate speech increase social polarisation and create distrust and hostility in society.

PurposeHate speech in recent times has become a troubling development. It has different meanings to different people in different cultures. The anonymity and ubiquity of the social media provides a breeding ground for hate speech and makes combating it seems like a lost battle. However, what may constitute a hate speech in a cultural or religious neutral society may not be perceived as such in a polarized multi-cultural and multi-religious society like Nigeria. Defining hate speech, therefore, may be contextual. Hate speech in Nigeria may be perceived along ethnic, religious and political boundaries. The purpose of this paper is to check for the presence of hate speech in social media platforms like Twitter, and to what degree is hate speech permissible, if available? It also intends to find out what monitoring mechanisms the social media platforms like Facebook and Twitter have put in place to combat hate speech. Lexalytics is a term coined by the authors from the words lexical analytics for the purpose of opinion mining unstructured texts like tweets.Design/methodology/approachThis research developed a Python software called polarized opinions sentiment analyzer (POSA), adopting an ego social network analytics technique in which an individual’s behavior is mined and described. POSA uses a customized Python N-Gram dictionary of local context-based terms that may be considered as hate terms. It then applied the Twitter API to stream tweets from popular and trending Nigerian Twitter handles in politics, ethnicity, religion, social activism, racism, etc., and filtered the tweets against the custom dictionary using unsupervised classification of the texts as either positive or negative sentiments. The outcome is visualized using tables, pie charts and word clouds. A similar implementation was also carried out using R-Studio codes and both results are compared and a t-test was applied to determine if there was a significant difference in the results. The research methodology can be classified as both qualitative and quantitative. Qualitative in terms of data classification, and quantitative in terms of being able to identify the results as either negative or positive from the computation of text to vector.FindingsThe findings from two sets of experiments on POSA and R are as follows: in the first experiment, the POSA software found that the Twitter handles analyzed contained between 33 and 55 percent hate contents, while the R results show hate contents ranging from 38 to 62 percent. Performing a t-test on both positive and negative scores for both POSA and R-studio, results reveal p-values of 0.389 and 0.289, respectively, on an α value of 0.05, implying that there is no significant difference in the results from POSA and R. During the second experiment performed on 11 local handles with 1,207 tweets, the authors deduce as follows: that the percentage of hate contents classified by POSA is 40 percent, while the percentage of hate contents classified by R is 51 percent. That the accuracy of hate speech classification predicted by POSA is 87 percent, while free speech is 86 percent. And the accuracy of hate speech classification predicted by R is 65 percent, while free speech is 74 percent. This study reveals that neither Twitter nor Facebook has an automated monitoring system for hate speech, and no benchmark is set to decide the level of hate contents allowed in a text. The monitoring is rather done by humans whose assessment is usually subjective and sometimes inconsistent.Research limitations/implicationsThis study establishes the fact that hate speech is on the increase on social media. It also shows that hate mongers can actually be pinned down, with the contents of their messages. The POSA system can be used as a plug-in by Twitter to detect and stop hate speech on its platform. The study was limited to public Twitter handles only. N-grams are effective features for word-sense disambiguation, but when using N-grams, the feature vector could take on enormous proportions and in turn increasing sparsity of the feature vectors.Practical implicationsThe findings of this study show that if urgent measures are not taken to combat hate speech there could be dare consequences, especially in highly polarized societies that are always heated up along religious and ethnic sentiments. On daily basis tempers are flaring in the social media over comments made by participants. This study has also demonstrated that it is possible to implement a technology that can track and terminate hate speech in a micro-blog like Twitter. This can also be extended to other social media platforms.Social implicationsThis study will help to promote a more positive society, ensuring the social media is positively utilized to the benefit of mankind.Originality/valueThe findings can be used by social media companies to monitor user behaviors, and pin hate crimes to specific persons. Governments and law enforcement bodies can also use the POSA application to track down hate peddlers.

Along with the increasing activity on social media, hate speech is getting out of control. Hate speech detection can be done by utilizing text mining technology. There have been many hate speech detection studies conducted. To identify and analyze research trends, data sources, methods and features used in hate speech detection, this systematic literature review was created. Until early 2020, the topics of hate speech were found, including hate speech against minorities, religion, women, the general election agenda, and politics. Sources of data that are widely used to be used as datasets come from twitter. Hate speech is not only classified into HS (hate speech) and Non-HS (non-hate speech) but can be further classified into racism, sexism, offensive, abusive, threats of violence and others. Of the 38 studies that meet inclusion and exclusion, there are 26 algorithms and 28 features that have been used to detect hate speech. However, these methods and features do not necessarily guarantee a good hate detection performance. Hate speech classification performance is also influenced by the dataset, the features chosen, the number of classes and mutually exclusive classes.