Abusive Language Detection Research Articles

Abusive Language Detection in Khasi Social Media Comments

Abusive Language Detection in Khasi Social Media Comments

Multi-label text classification on unbalanced Twitter with monolingual model and hyperparameter optimization for hate speech and abusive language detection

The increase in hate speech and abusive language on social media leads to uncomfortable interactions among users. Many datasets available publicly that address hate speech and abusive language are not balanced, particularly those from Indonesian Twitter. To develop a more effective classification model that also considers minority classes, we needed to optimize the hyperparameters of a monolingual model, use four different data preprocessing scenarios, and improve the treatment of slang words. We assessed the model's effectiveness by its accuracy, achieving 81.38%. This result came from optimizing hyperparameters, processing data without stemming and removing stop words, and enhancing the slang word data. The optimal hyperparameters were a learning rate of 4e-5, a batch size of 16, and a dropout rate of 0.1. However, using too much dropout can decrease the model’s performance and its ability to predict less common categories, such as physical- and gender-related hate speech.

Enhancing abusive language detection: A domain-adapted approach leveraging BERT pre-training tasks

The widespread adoption of deep learning approaches in natural language processing is largely attributed to their exceptional performance across diverse tasks. Notably, Transformer-based models, such as BERT, have gained popularity for their remarkable efficacy and their ease of adaptation (via fine-tuning) across various domains. Despite their success, fine-tuning these models for informal language, particularly instances involving offensive expressions, presents a major challenge due to limitations in vocabulary coverage and contextual information for such tasks. To address these challenges, we propose the domain adaptation of the BERT language model for the task of detecting abusive language. Our approach involves constraining the language model with the adaptation and paradigm shift of two default pre-trained tasks, the design of two datasets specifically engineered to support the adapted pre-training tasks, and the proposal of a dynamic weighting loss function. The evaluation of these adapted configurations on six datasets dedicated to abusive language detection reveals promising outcomes, with a significant enhancement observed compared to the base model. Furthermore, our proposed methods yield competitive results when compared to state-of-the-art approaches, establishing a robust and easily trainable model for the effective identification of abusive language.

Survey Paper on Implementation of Abusive Language Detection in Chatting Application

Communication has become stronger due to exponential increase in the usage of social media in the last few years. People use them for communicating with friends, finding new friends, updating any important activities of their life, etc. Due to their growing popularity and deep reach, these mediums are infiltrated with huge Volume of spam messages. Spam message randomly sent to multiple addressees by all sorts of groups, but mostly lazy advertisers and criminals who wish to lead you to phishing sites. In this we are using various machine learning techniques for detecting spam in the short text messages and also Google vision API for detecting spam images. Key Words: Spam Filtration, Google Vision API, OWASP, Naive baise classifier, Dictionary Based Algorithm

Survey Paper on Implementation of Abusive Language Detection in Chatting Application

Communication has become stronger due to exponential increase in the usage of social media in the last few years. People use them for communicating with friends, finding new friends, updating any important activities of their life, etc. Due to their growing popularity and deep reach, these mediums are infiltrated with huge volume of spam messages. Spam message randomly sent to multiple addressees by all sorts of groups, but mostly lazy advertisers and criminals who wish to lead you to phishing sites. In this we are using various machine learning techniques for detecting spam in the short text messages and also Google vision API for detecting spam images. Key Words: Spam Filtration, Google Vision API, OWASP, Naive baise classifier, Dictionary Based Algorithm

Hate Speech and Abusive Language and Abusive Language Detection in Twitter using Machine Learning

Twitter's central goal is to enable everybody to make and share thoughts and data, and to communicate their suppositions and convictions without boundaries. Twitter's job is to serve the public discussion, which requires portrayal of a different scope of points of view. Yet, it does not advance viciousness against or straightforwardly assault or undermine others based on race, nationality, public cause, rank, sexual direction, age, inability, or genuine illness. Hate speech and abusive language can hurt a person or a community. So, it is not appropriate to use hate speech and abusive language. Now, due to increase in social media usage, hate speech and abusive language is very commonly used on these platforms. So, it is not possible to identify hate speech and abusive languagees manually. So, it is essential to develop an automated hate speech and abusive language detection model and this research work shows different approaches of Natural Language Processing for classification of Hate speech and abusive language through Machine Learning Algorithms.

GHA: a Gated Hierarchical Attention Mechanism for the Detection of Abusive Language in Social Media

GHA: a Gated Hierarchical Attention Mechanism for the Detection of Abusive Language in Social Media

Deep learning-based approaches for abusive content detection and classification for multi-class online user-generated data

With the rapid growth of social media culture, the use of offensive or hateful language has surged, which necessitates the development of effective abusive language detection models for online platforms. This paper focuses on developing a multi-class classification model to identify different types of offensive language. The input data is taken in the form of labeled tweets and is classified into offensive language detection, offensive language categorization, and offensive language target identification. The data undergoes pre-processing, which removes NaN value and punctuation, as well as performs tokenization followed by the generation of a word cloud to assess data quality. Further, the tf-idf technique is used for the selection of features. In the case of classifiers, multiple deep learning techniques, namely, bidirectional gated recurrent unit, multi-dense long short-term memory, bidirectional long short-term memory, gated recurrent unit, and long short-term memory, are applied where it has been found that all the models, except long short-term memory, achieved a high accuracy of 99.9 % for offensive language target identification. Bidirectional LSTM and multi-dense LSTM obtained the lowest loss and RMSE values of 0.01 and 0.1, respectively. This research provides valuable insights and contributes to the development of effective abusive language detection methods to promote a safe and respectful online environment. The insights gained can aid platform administrators in efficiently moderating content and taking appropriate actions against offensive language.

Enhancing Multi-Label Hate Speech and Abusive Language Detection on Indonesian Twitter Using Recurrent Neural Networks with Hyperparameter Tuning

This study investigates enhancing multi-label hate speech and abusive language detection on Indonesian Twitter using Recurrent Neural Networks (RNNs) with hyperparameter tuning. A dataset of Indonesian tweets labeled for various hate speech and abusive language categories was preprocessed through text cleaning, tokenization, and sequence padding. A baseline RNN model was initially constructed and evaluated. Hyperparameter tuning was then performed using Keras Tuner to optimize performance. The best hyperparameters identified were an embedding dimension of 32, 32 LSTM units, and a dropout rate of 0.2. The tuned model was trained and compared with the baseline. Results indicated improved precision for labels like Abusive, HS_Group, HS_Moderate, and HS_Strong, but a decline in recall and F1-scores for labels like HS_Religion and HS_Race. Overall performance metrics showed a slight decline, highlighting trade-offs in the tuning process. In conclusion, while hyperparameter tuning can enhance certain performance aspects, it also introduces complexities and trade-offs. It is recommended to use hyperparameter tuning in model optimization with careful consideration of application requirements. Further research will explore different model architectures and additional tuning strategies for better overall performance.

Preliminary Evaluation of Gaussian Naive Bayes for Multi-Label Hate Speech and Abusive Language Detection on Indonesian Twitter

Preliminary Evaluation of Gaussian Naive Bayes for Multi-Label Hate Speech and Abusive Language Detection on Indonesian Twitter

Abusive Language Detection in Speech Dataset

Abstract: In the topic, speech recognition there is a rapid increasing in it into area of engineering technology. Speech recognition delivers many different kinds of pros and it's been uses in a multiple field. Having a different type of language placed a restriction of talking between people. From this project we will going to create and develop to supports different systems that allows persons in that place or situation to change of data through interacting with end device users by voice or speech, after developing this project we will destroy the barriers of communication. This project takes that into consideration and makes an attempt to guarantee that it can identify speech and transform audio input into text. The speech is converted into text format. To overcome the offensive content in real-time every social media platform should implement an effectual hate speech detection system. There are many ways from that we can classify hate speech such as Machine Learning, Rule Based, Deep Learning Based and Hybrid

FALCoN: Detecting and classifying abusive language in social networks using context features and unlabeled data

Social networks have grown into a widespread form of communication that allows a large number of users to participate in conversations and consume information at any time. The casual nature of social media allows for nonstandard terminology, some of which may be considered rude and derogatory. As a result, a significant portion of social media users is found to express disrespectful language. This problem may intensify in certain developing countries where young children are granted unsupervised access to social media platforms. Furthermore, the sheer amount of social media data generated daily by millions of users makes it impractical for humans to monitor and regulate inappropriate content. If adolescents are exposed to these harmful language patterns without adequate supervision, they may feel obliged to adopt them. In addition, unrestricted aggression in online forums may result in cyberbullying and other dreadful occurrences. While computational linguistics research has addressed the difficulty of detecting abusive dialogues, issues remain unanswered for low-resource languages with little annotated data, leading the majority of supervised techniques to perform poorly. In addition, social media content is often presented in complex, context-rich formats that encourage creative user involvement. Therefore, we propose to improve the performance of abusive language detection and classification in a low-resource setting, using both the abundant unlabeled data and the context features via the co-training protocol that enables two machine learning models, each learning from an orthogonal set of features, to teach each other, resulting in an overall performance improvement. Empirical results reveal that our proposed framework achieves F1 values of 0.922 and 0.827, surpassing the state-of-the-art baselines by 3.32% and 45.85% for binary and fine-grained classification tasks, respectively. In addition to proving the efficacy of co-training in a low-resource situation for abusive language detection and classification tasks, the findings shed light on several opportunities to use unlabeled data and contextual characteristics of social networks in a variety of social computing applications.

The problem of varying annotations to identify abusive language in social media content

Abstract With the increase of user-generated content on social media, the detection of abusive language has become crucial and is therefore reflected in several shared tasks that have been performed in recent years. The development of automatic detection systems is desirable, and the classification of abusive social media content can be solved with the help of machine learning. The basis for successful development of machine learning models is the availability of consistently labeled training data. But a diversity of terms and definitions of abusive language is a crucial barrier. In this work, we analyze a total of nine datasets—five English and four German datasets—designed for detecting abusive online content. We provide a detailed description of the datasets, that is, for which tasks the dataset was created, how the data were collected, and its annotation guidelines. Our analysis shows that there is no standard definition of abusive language, which often leads to inconsistent annotations. As a consequence, it is difficult to draw cross-domain conclusions, share datasets, or use models for other abusive social media language tasks. Furthermore, our manual inspection of a random sample of each dataset revealed controversial examples. We highlight challenges in data annotation by discussing those examples, and present common problems in the annotation process, such as contradictory annotations and missing context information. Finally, to complement our theoretical work, we conduct generalization experiments on three German datasets.

Hope speech detection in Spanish

In recent years, systems have been developed to monitor online content and remove abusive, offensive or hateful content. Comments in online social media have been analyzed to find and stop the spread of negativity using methods such as hate speech detection, identification of offensive language or detection of abusive language. We define hope speech as the type of speech that is able to relax a hostile environment and that helps, gives suggestions and inspires for good to a number of people when they are in times of illness, stress, loneliness or depression. Detecting it automatically, in order to give greater diffusion to positive comments, can have a very significant effect when it comes to fighting against sexual or racial discrimination or when we intend to foster less bellicose environments. In this article we perform a complete study on hope speech, analyzing existing solutions and available resources. In addition, we have generated a quality resource, SpanishHopeEDI, a new Spanish Twitter dataset on LGBT community, and we have conducted some experiments that can serve as a baseline for further research.

Generalizability of Abusive Language Detection Models on Homogeneous German Datasets

Abusive language detection has become an integral part of the research, as reflected in numerous publications and several shared tasks conducted in recent years. It has been shown that the obtained models perform well on the datasets on which they were trained, but have difficulty generalizing to other datasets. This work also focuses on model generalization, but – in contrast to previous work – we use homogeneous datasets for our experiments, assuming that they have a higher generalizability. We want to find out how similar datasets have to be for trained models to generalize and whether generalizability depends on the method used to obtain a model. To this end, we selected four German datasets from popular shared tasks, three of which are from consecutive GermEval shared tasks. Furthermore, we evaluate two deep learning methods and three traditional machine learning methods to derive generalizability trends based on the results. Our experiments show that generalization is only partially given, although the annotation schemes for these datasets are almost identical. Our findings additionally show that generalizability depends solely on the (combinations of) training sets and is consistent no matter what the underlying method is.

Measuring and mitigating language model biases in abusive language detection

Warning: This paper contains abusive samples that may cause discomfort to readers.Abusive language on social media reinforces prejudice against an individual or a specific group of people, which greatly hampers freedom of expression. With the rise of large-scale pre-trained language models, classification based on pre-trained language models has gradually become a paradigm for automatic abusive language detection. However, the effect of stereotypes inherent in language models on the detection of abusive language remains unknown, although this may further reinforce biases against the minorities. To this end, in this paper, we use multiple metrics to measure the presence of bias in language models and analyze the impact of these inherent biases in automatic abusive language detection. On the basis of this quantitative analysis, we propose two different debiasing strategies, token debiasing and sentence debiasing, which are jointly applied to reduce the bias of language models in abusive language detection without degrading the classification performance. Specifically, for the token debiasing strategy, we reduce the discrimination of the language model against protected attribute terms of a certain group by random probability estimation. For the sentence debiasing strategy, we replace protected attribute terms and augment the original text by counterfactual augmentation to obtain debiased samples, and use the consistency regularization between the original data and the augmented samples to eliminate the bias at the sentence level of the language model. The experimental results confirm that our method can not only reduce the bias of the language model in the abusive language detection task, but also effectively improve the performance of abusive language detection.

Detection of Cyberbullying and Abusive Language on Social Media Using Supervised ML & NLP Techniques

Detection of Cyberbullying and Abusive Language on Social Media Using Supervised ML & NLP Techniques

Addressing religious hate online: from taxonomy creation to automated detection.

Abusive language in online social media is a pervasive and harmful phenomenon which calls for automatic computational approaches to be successfully contained. Previous studies have introduced corpora and natural language processing approaches for specific kinds of online abuse, mainly focusing on misogyny and racism. A current underexplored area in this context is religious hate, for which efforts in data and methods to date have been rather scattered. This is exacerbated by different annotation schemes that available datasets use, which inevitably lead to poor repurposing of data in wider contexts. Furthermore, religious hate is very much dependent on country-specific factors, including the presence and visibility of religious minorities, societal issues, historical background, and current political decisions. Motivated by the lack of annotated data specifically tailoring religion and the poor interoperability of current datasets, in this article we propose a fine-grained labeling scheme for religious hate speech detection. Such scheme lies on a wider and highly-interoperable taxonomy of abusive language, and covers the three main monotheistic religions: Judaism, Christianity and Islam. Moreover, we introduce a Twitter dataset in two languages-English and Italian-that has been annotated following the proposed annotation scheme. We experiment with several classification algorithms on the annotated dataset, from traditional machine learning classifiers to recent transformer-based language models, assessing the difficulty of two tasks: abusive language detection and religious hate speech detection. Finally, we investigate the cross-lingual transferability of multilingual models on the tasks, shedding light on the viability of repurposing our dataset for religious hate speech detection on low-resource languages. We release the annotated data and publicly distribute the code for our classification experiments at https://github.com/dhfbk/religious-hate-speech.

Guest Editorial: Sentiment Analysis as a Multidisciplinary Research Area

The papers in this special section focus on bringing multidisciplinary knowledge into sentiment analysis. The last two decades have witnessed an enormous amount of research works on sentiment analysis and significant progress has been made. In terms of depth, finer-grained semantic schemas are defined, such as aspect, target, and category. In terms of broadness, multimodal sentiment analysis touches audio and video channels. Conversational sentiment analysis considers contextual and time-dependent relations and domain-specific sentiment analysis settings tackles real-life challenges, including but not limited to user profiling, financial prediction, abusive language detection, and mental health.

Improving Abusive Language Detection with online interaction network

The rapid development of online social media makes Abusive Language Detection (ALD) a hot topic in the field of affective computing. However, most methods for ALD in social networks do not take into account the interactive relationships among user posts, which simply regard ALD as a task of text context representation learning. To solve this problem, we propose a pipeline approach that considers both the context of a post and the characteristics of interaction network in which it is posted. Specifically, our method is divided into pre-training and downstream tasks. First, to capture fine contextual features of the posts, we use Bidirectional Encoder Representation from Transformers (BERT) as Encoder to generate sentence representations. Later, we build a Relation-Special Network according to the semantic similarity between posts as well as the interaction network structural information. On this basis, we design a Relation-Special Graph Neural Network (RSGNN) to spread effective information in the interaction network and learn the classification of texts. The experiment proves that our method can effectively improve the detection effect of abusive posts over three public datasets. The results demonstrate that injecting interaction network structure into the abusive language detection task can significantly improve the detection results.