Search

Information and communication technology has evolved dramatically, and now the majority of people are using internet and sharing their opinion more openly, which has led to the creation, collection and circulation of hate speech over multiple platforms. The anonymity and movability given by these social media platforms allow people to hide themselves behind a screen and spread the hate effortlessly. Online hate speech (OHS) recognition can play a vital role in stopping such activities and can thus restore the position of public platforms as the open marketplace of ideas. To study hate speech detection in social media, we surveyed the related available datasets on the web-based platform. We further analyzed approximately 200 research papers indexed in the different journals from 2010 to 2022. The papers were divided into various sections and approaches used in OHS detection, i.e., feature selection, traditional machine learning (ML) and deep learning (DL). Based on the selected 111 papers, we found that 44 articles used traditional ML and 35 used DL-based approaches. We concluded that most authors used SVM, Naive Bayes, Decision Tree in ML and CNN, LSTM in the DL approach. This survey contributes by providing a systematic approach to help researchers identify a new research direction in online hate speech. [ABSTRACT FROM AUTHOR]

In today's digital landscape, organizations face significant challenges, including sensitive data leaks and the proliferation of hate speech, both of which can lead to severe consequences such as financial losses, reputational damage, and psychological impacts on employees. This work considers a comprehensive solution using a microservices architecture to monitor computer usage within organizations effectively. The approach incorporates spyware techniques to capture data from employee computers and a web application for alert management. The system detects data leaks, suspicious behaviors, and hate speech through efficient data capture and predictive modeling. Therefore, this paper presents a comparative performance analysis between Spring Boot and Quarkus, focusing on objective metrics and quantitative statistics. By utilizing recognized tools and benchmarks in the computer science community, the study provides an in-depth understanding of the performance differences between these two platforms. The implementation of Quarkus over Spring Boot demonstrated substantial improvements: memory usage was reduced by up to 80% and CPU usage by 95%, and system uptime decreased by 119%. This solution offers a robust framework for enhancing organizational security and mitigating potential threats through proactive monitoring and predictive analysis while also guiding developers and software architects in making informed technological choices. [ABSTRACT FROM AUTHOR]

In this paper, I argue that considerations of epistemic bubbles can give us reason to defend censorship of hate speech. Although censoring hate speech leads to epistemic bubbles ('censorship bubbles'), they tend to be less epistemically problematic than epistemic bubbles generated by the circulation of hate speech ('hate bubbles'). Because hate speech silences its target groups and creates the illusion that the dominant group identities are threatened, hate bubbles are likely more restrictive in structure than censorship bubbles and have a stronger tendency to turn into echo chambers where opposing views are actively discredited. Therefore, I argue that censorship bubbles might be a minor price we ought to pay to avoid hate bubbles. Additionally, my analysis shows that we cannot focus exclusively on the content or the structure of epistemic bubbles, since their content can partly determine their structure, as is in the case of hate bubbles. [ABSTRACT FROM AUTHOR]

In this paper, we will investigate whether or not the name 'Africa' can be seen as a slur. Since the name was given by European exploiters, slavers and colonists, it raises the question of whether such a name should continue to be accepted or abandoned. It may seem that just as the slavers renamed their victims and the colonists renamed the territories they conquered, the name Africa/ns similarly was an imposition on the continent and its peoples. It can also be argued that the naming of the continent by an external aggressor is a form of epistemic subordination that vitiates the dignity of the inhabitants. That is to say that European slavers took it upon themselves to give the inhabitants an identity that highlights climate and possibly skin colour because it was something they could not do for themselves. This presents the inhabitants as inferior to their namers and whose millennia-old civilisational achievements can comfortably be overlooked. We argue that the two preceding arguments constitute compelling reasons to abandon the name Africa as a compromised identity and offer an idea for the renaming of the continent. [ABSTRACT FROM AUTHOR]

In this paper, we investigate the issue of hate speech by presenting a novel task of translating hate speech into non-hate speech text while preserving its meaning. As a case study, we use Spanish texts. We provide a dataset and several baselines as a starting point for further research in the task. We evaluated our baseline results using multiple metrics, including BLEU scores. We used a cross-validation approach and an average of the metrics per fold for evaluation. We achieved a 0.236 sentenceBLEU score on four folds. This study aims to contribute to developing more effective methods for reducing the spread of hate speech in online communities. [ABSTRACT FROM AUTHOR]

Twitter has experienced a tremendous surge in popularity over recent years, establishing itself as a prominent social media platform with a large user base. However, with this increased usage, there has been a concerning rise in the number of individuals resorting to derogatory language and expressing their opinions in a demeaning manner toward others. This surge in hate speech has drawn significant attention to the field of sentiment analysis, which aims to develop algorithms capable of detecting and analyzing emotions expressed in social networks using intuitive approaches. This paper focuses on addressing the complex task of detecting hate speech and aggressive behavior while performing target classification. We explored various deep-learning approaches, including LSTM, BiLSTM, CNN, and GRU. Each offers unique capabilities for capturing different aspects of the input data. We proposed an ensemble approach that combines the top three performing models. This ensemble approach benefits from the diverse strengths of each individual model showing F1 score of 0.85 for English-HS, 0.94 for English-TR, 0.92 for English-AB, 0.84 for Spanish-HS, 0.86 for Spanish-TR, 0.97 for Spanish-AB, 0.74 for multilingual-HS, 0.94 for multilingual-TR, and 0.88 for multilingual-AB. [ABSTRACT FROM AUTHOR]

Social media platforms have surpassed cultural and linguistic boundaries, thus enabling online communication worldwide. However, the expanded use of various languages has intensified the challenge of online detection of hate speech content. Despite the release of multiple Natural Language Processing (NLP) solutions implementing cutting-edge machine learning techniques, the scarcity of data, especially labeled data, remains a considerable obstacle, which further requires the use of semisupervised approaches along with Generative Artificial Intelligence (Generative AI) techniques. This paper introduces an innovative approach, a multilingual semisupervised model combining Generative Adversarial Networks (GANs) and Pretrained Language Models (PLMs), more precisely mBERT and XLM-RoBERTa. Our approach proves its effectiveness in the detection of hate speech and offensive language in Indo-European languages (in English, German, and Hindi) when employing only 20% annotated data from the HASOC2019 dataset, thereby presenting significantly high performances in each of multilingual, zero-shot crosslingual, and monolingual training scenarios. Our study provides a robust mBERT-based semisupervised GAN model (SS-GAN-mBERT) that outperformed the XLM-RoBERTa-based model (SS-GAN-XLM) and reached an average F1 score boost of 9.23% and an accuracy increase of 5.75% over the baseline semisupervised mBERT model. [ABSTRACT FROM AUTHOR]

Social media platforms have emerged as fertile ground for the proliferation of hate speech, which can exacerbate the dissemination of hate crimes. The Federal Bureau of Investigation UCR Program gathers data on hate crimes and disseminates annual reports to identify national patterns and inform law enforcement agencies and policymakers, these reports often fail to keep pace with urgent demands. Real-time monitoring and predictive analysis of hate crime trends are imperative for more effective prevention and response efforts. This paper presents a framework that leverages information extraction techniques to extract incidents from articles published in The New York Times, enabling accurate prediction of hate crime trends at both the federal and state levels. Experimental findings demonstrate the superiority of our approach compared to other traditional methods. By expanding forecasting approaches for federal and state levels' hate crime trends, this framework offers valuable insights for law enforcement agencies and policymakers. [ABSTRACT FROM AUTHOR]

The paper presents a novel data augmentation-based approach to develop explainable, deep learning models for hate speech detection. Hate speech is widely prevalent on online social media but difficult to detect automatically due to challenges of natural language processing and complexity of hate speech. Further, the decisions of the existing solutions possess constrained explainability since limited annotated data are available for training and testing of models. Therefore, this work proposes the use of text-based data augmentation for improving the performance and explainability of deep learning models. Techniques based on easy data augmentation, bidirectional encoder representations from transformers and back translation have been utilized for data augmentation. Convolutional neural networks and long short-term memory models are trained with augmented data and evaluated on two publicly available datasets for hate speech detection. Methods of LIME and integrated gradients are used to retrieve explanations of the deep learning models. A diagnostic study is conducted on test samples to check for improvement in the models as a result of the data augmentation. The experimental results verify that the proposed approach improves the explainability as well as the accuracy of hate speech detection. [ABSTRACT FROM AUTHOR]

With an aim to eliminate or reduce the spread of hate content across social media platforms, the development of artificial intelligence supported computational predictors is an active area of research. However, diversity of languages hinders development of generic predictors that can precisely identify hate content. Several language-specific hate speech detection predictors have been developed for most common languages including English, Chinese and German. Specifically, for Urdu language a few predictors have been developed and these predictors lack in predictive performance. The paper in hand presents a precise and explainable deep learning predictor which makes use of advanced language modelling strategies for the extraction of semantic and discriminative patterns. Extracted patterns are utilized to train an attention-based novel classifier that is competent in precisely identifying hate content. Over coarse-grained benchmark dataset, the proposed predictor significantly outperforms state-of-the-art predictor by 8.7% in terms of accuracy, precision and F1-score. Similarly, over fine-grained dataset, in comparison with state-of-the-art predictor, it achieves performance gain of 10.6%, 17.6%, 18.6% and 17.6% in terms of accuracy, precision, recall and F1-score. [ABSTRACT FROM AUTHOR]

The amount of outrage language, hate speech and strong language in digital communication is steadily growing, but academic studies on how to deal linguistically with anger and outrage are still largely lacking. Social science studies focus mainly on behavioral actions, while only a few investigate situations in which aggression is successfully handled verbally. On the other hand, complaint handling via webcare has received considerable scholarly attention, but its focus was never on de-escalation techniques. This paper explores what verbal de-escalation techniques can be learned from webcare employees who succeeded in satisfying complainants. More specifically, it combines insights from the (im)politeness framework and conversational human voice approach (CHV) to show that webcare practitioners have developed a tacit consensus on how to use language to deal with complaints. In a study with a mixed methods approach, a Twitter (now X) sample of responses to complaints is explored to identify linguistic and rhetorical features that encourage de-escalation. Thirteen features, that can be grouped into three categories, contributed to mollify the initial complainant. They can be characterized as markers of empathy (1), authenticity (2) and verbal accommodation (3) and they may help to calm heated debates in domains other than webcare. This article extends previous research by merging both pragma-linguistic and corporate communication taxonomies of complaint handling routines, adding forms of stylistic internal modification as possibly successful de-escalation features. • Webcare policy on complaint handling serves to uncover de-escalation techniques for outrage language. • Linguistic and rhetorical features that create empathy, authenticity and accommodation help to defuse heated Twitter discussions. • The uptake of responses to complaints helps to distinguish between successful and unsuccessful complaint handling. [ABSTRACT FROM AUTHOR]

Exposure to hate speech (HS) leads to desensitization of listeners. Yet, most evidence of this process has been obtained using self‐report measures. In this paper, we examined desensitization to HS using an unobtrusive, psychophysiological measure. In an experimental electrocardiogram study (N = 56), we observed heart rate (HR) deceleration after reading comments that contained HS. This suggested a substantive psychophysiological reaction of participants to hateful comments. However, such HR deceleration was not observed among participants preexposed to HS. People exposed to hateful comments thus appeared to show different HR responses to HS compared to people who were not previously exposed to such comments. Consequently, not only does frequent exposure to HS influence an individual's beliefs as observed in earlier studies, but it also impacts psychophysiological reactions to derogatory language. [ABSTRACT FROM AUTHOR]

In the face of uncontrolled offensive content on social media, automated detection emerges as a critical need. This paper tackles this challenge by proposing a novel approach for identifying offensive language in multilingual, code-mixed, and script-mixed settings. The study presents a novel multilingual hybrid dataset constructed by merging diverse monolingual and bilingual resources. Further, we systematically evaluate the impact of input representations (Word2Vec, Global Vectors for Word Representation (or GloVe), Bidirectional Encoder Representations from Transformers (or BERT), and uniform initialization) and deep learning models (Convolutional Neural Network (or CNN), Bidirectional Long Short Term Memory (or Bi-LSTM), Bi-LSTM-Attention, and fine-tuned BERT) on detection accuracy. Our comprehensive experiments on a dataset of 42,560 social media comments from five languages (English, Hindi, German, Tamil, and Malayalam) reveal the superiority of fine-tuned BERT. Notably, it achieves a macro average F 1 -score of 0.79 for monolingual tasks and an impressive 0.86 for code-mixed and script-mixed tasks. These findings significantly advance offensive language detection methodologies and shed light on the complex dynamics of multilingual social media, paving the way for more inclusive and safer online communities. [ABSTRACT FROM AUTHOR]

In the face of uncontrolled offensive content on social media, automated detection emerges as a critical need. This paper tackles this challenge by proposing a novel approach for identifying offensive language in multilingual, code-mixed, and script-mixed settings. The study presents a novel multilingual hybrid dataset constructed by merging diverse monolingual and bilingual resources. Further, we systematically evaluate the impact of input representations (Word2Vec, Global Vectors for Word Representation (or GloVe), Bidirectional Encoder Representations from Transformers (or BERT), and uniform initialization) and deep learning models (Convolutional Neural Network (or CNN), Bidirectional Long Short Term Memory (or Bi-LSTM), Bi-LSTM-Attention, and fine-tuned BERT) on detection accuracy. Our comprehensive experiments on a dataset of 42,560 social media comments from five languages (English, Hindi, German, Tamil, and Malayalam) reveal the superiority of fine-tuned BERT. Notably, it achieves a macro average F 1 -score of 0.79 for monolingual tasks and an impressive 0.86 for code-mixed and script-mixed tasks. These findings significantly advance offensive language detection methodologies and shed light on the complex dynamics of multilingual social media, paving the way for more inclusive and safer online communities. [ABSTRACT FROM AUTHOR]

Nowadays, users across the globe interact with one another for information exchange, communication, and association on various online social media. However, some individuals exploit these venues for malicious practices like hate speech and cyberbully. In this paper, we present an improved multilingual hate speech and cyberbully detection model using bagging-stacking based hybrid ensemble deep learning techniques. The proposed model utilizes Bi-directional Long Short-Term Memory (BiLSTM), Bi-directional Gated Recurrent Unit (Bi-GRU), Convolutional Neural Network (CNN), and Long Short-Term Memory (LSTM) techniques to enhance the overall performance. We first preprocess the multilingual data streams followed by adoption of Global vectors for word Representation (GloVe) embeddings to convert words to a vector representation in parallel enabling the data streams for binary classification task. In order to construct an architecture for the detection of hate speech and cyberbully, we introduce a heterogeneous fusion of multiple effective models in a unique approach such that CNN-LSTM utilizes a stacking approach with stochastic gradient descent to achieve optimal weights, whereas all the base learners used bagging ensemble approach with cross-validation to reach optimal weights. The final output layer of the proposed ensemble deep learning architecture is achieved using a super learner approach on base learners. To show the efficacy of the proposed model, we conduct the simulation on a total of nine real-world social media datasets in different languages and compared the results with other contemporary hate speech and cyberbully detection methods. The collected findings show that the proposed model outperforms other models on considered datasets and shows an improvement of at least 4.44% in F1 scores. • Proposed an ensemble DL multilingual model for hate speech & cyberbully detection. • Model combines bagging, stacking, and super learning methods to improved results. • Model adopts a light weight heterogeneous fusion and bagging-stacking hybrid methods. • The experimental findings advocate the superiority of the proposed model. [ABSTRACT FROM AUTHOR]

Social media text can be classified in different ways, viz sentiment analysis, humour detection, hate speech detection and hope speech detection. Multitask learning (MTL) models built on Large Language Models (LLMs) eliminate the need to build separate models for each of these tasks. However, building MTL models by fully fine-tuning the LLM has limitations such as catastrophic forgetting and requiring complete retraining to add a new task. AdapterFusion was introduced to address these limitations. However, existing AdapterFusion techniques have not been experimented with code-mixed or code-switched text. Moreover, they only considered task-based AdapterFusion on monolingual LLMs. However, using monolingual LLMs is sub-optimal in classifying code-mixed or code-switched text. A better alternative is multilingual LLMs. In this paper, we present an MTL model that combines task AdapterFusion with language adapters on top of a multilingual LLM. We combine language adapters sequentially, in parallel, and as a fusion with task adapters to capture cross-lingual knowledge in code-mixed and code-switched text. We believe that this is the first research to introduce language-based AdapterFusion. [ABSTRACT FROM AUTHOR]