During the COVID-19 pandemic, community tensions intensified, fuelling Hinduphobic sentiments and discrimination against individuals of Hindu descent within India and worldwide. Large language models (LLMs) have become prominent in natural language processing (NLP) tasks and social media analysis, enabling longitudinal studies of platforms like X (formerly Twitter) for specific issues during COVID-19. We present an abuse detection and sentiment analysis framework that offers a longitudinal analysis of Hinduphobia on X (Twitter) during and after the COVID-19 pandemic. This framework assesses the prevalence and intensity of Hinduphobic discourse, capturing elements such as derogatory jokes and racist remarks through sentiment analysis and abuse detection from pre-trained and fine-tuned LLMs. Additionally, we curate and publish a "Hinduphobic COVID-19 X (Twitter) Dataset" of 8,000 tweets annotated for Hinduphobic abuse detection, which is used to fine-tune a BERT model, resulting in the development of the Hinduphobic BERT (HP-BERT) model. We then further fine-tune HP-BERT using the SenWave dataset for multi-label sentiment analysis. Our study encompasses approximately 27.4 million tweets from six countries, including Australia, Brazil, India, Indonesia, Japan, and the United Kingdom. Our findings reveal a strong correlation between spikes in COVID-19 cases and surges in Hinduphobic rhetoric, highlighting how political narratives, misinformation, and targeted jokes contributed to communal polarisation. These insights provide valuable guidance for developing strategies to mitigate communal tensions in future crises, both locally and globally. We advocate implementing automated monitoring and removal of such content on social media to curb divisive discourse.
Online abusive content detection, particularly in low-resource settings and within the audio modality, remains underexplored. We investigate the potential of pre-trained audio representations for detecting abusive language in low-resource languages, in this case, in Indian languages using Few Shot Learning (FSL). Leveraging powerful representations from models such as Wav2Vec and Whisper, we explore cross-lingual abuse detection using the ADIMA dataset with FSL. Our approach integrates these representations within the Model-Agnostic Meta-Learning (MAML) framework to classify abusive language in 10 languages. We experiment with various shot sizes (50-200) evaluating the impact of limited data on performance. Additionally, a feature visualization study was conducted to better understand model behaviour. This study highlights the generalization ability of pre-trained models in low-resource scenarios and offers valuable insights into detecting abusive language in multilingual contexts.
Online gender-based harassment is a widespread issue limiting the free expression and participation of women and marginalized genders in digital spaces. Detecting such abusive content can enable platforms to curb this menace. We participated in the Gendered Abuse Detection in Indic Languages shared task at ICON2023 that provided datasets of annotated Twitter posts in English, Hindi and Tamil for building classifiers to identify gendered abuse. Our team CNLP-NITS-PP developed an ensemble approach combining CNN and BiLSTM networks that can effectively model semantic and sequential patterns in textual data. The CNN captures localized features indicative of abusive language through its convolution filters applied on embedded input text. To determine context-based offensiveness, the BiLSTM analyzes this sequence for dependencies among words and phrases. Multiple variations were trained using FastText and GloVe word embeddings for each language dataset comprising over 7,600 crowdsourced annotations across labels for explicit abuse, targeted minority attacks and general offences. The validation scores showed strong performance across f1-measures, especially for English 0.84. Our experiments reveal how customizing embeddings and model hyperparameters can improve detection capability. The proposed architecture ranked 1st in the competition, proving its ability to handle real-world noisy text with code-switching. This technique has a promising scope as platforms aim to combat cyber harassment facing Indic language internet users. Our Code is at https://github.com/advaithavetagiri/CNLP-NITS-PP
We introduce the Text Classification Attack Benchmark (TCAB), a dataset for analyzing, understanding, detecting, and labeling adversarial attacks against text classifiers. TCAB includes 1.5 million attack instances, generated by twelve adversarial attacks targeting three classifiers trained on six source datasets for sentiment analysis and abuse detection in English. Unlike standard text classification, text attacks must be understood in the context of the target classifier that is being attacked, and thus features of the target classifier are important as well. TCAB includes all attack instances that are successful in flipping the predicted label; a subset of the attacks are also labeled by human annotators to determine how frequently the primary semantics are preserved. The process of generating attacks is automated, so that TCAB can easily be extended to incorporate new text attacks and better classifiers as they are developed. In addition to the primary tasks of detecting and labeling attacks, TCAB can also be used for attack localization, attack target labeling, and attack characterization. TCAB code and dataset are available at https://react-nlp.github.io/tcab/.
To proactively offer social media users a safe online experience, there is a need for systems that can detect harmful posts and promptly alert platform moderators. In order to guarantee the enforcement of a consistent policy, moderators are provided with detailed guidelines. In contrast, most state-of-the-art models learn what abuse is from labelled examples and as a result base their predictions on spurious cues, such as the presence of group identifiers, which can be unreliable. In this work we introduce the concept of policy-aware abuse detection, abandoning the unrealistic expectation that systems can reliably learn which phenomena constitute abuse from inspecting the data alone. We propose a machine-friendly representation of the policy that moderators wish to enforce, by breaking it down into a collection of intents and slots. We collect and annotate a dataset of 3,535 English posts with such slots, and show how architectures for intent classification and slot filling can be used for abuse detection, while providing a rationale for model decisions.
Robustness of machine learning models on ever-changing real-world data is critical, especially for applications affecting human well-being such as content moderation. New kinds of abusive language continually emerge in online discussions in response to current events (e.g., COVID-19), and the deployed abuse detection systems should be updated regularly to remain accurate. In this paper, we show that general abusive language classifiers tend to be fairly reliable in detecting out-of-domain explicitly abusive utterances but fail to detect new types of more subtle, implicit abuse. Next, we propose an interpretability technique, based on the Testing Concept Activation Vector (TCAV) method from computer vision, to quantify the sensitivity of a trained model to the human-defined concepts of explicit and implicit abusive language, and use that to explain the generalizability of the model on new data, in this case, COVID-related anti-Asian hate speech. Extending this technique, we introduce a novel metric, Degree of Explicitness, for a single instance and show that the new metric is beneficial in suggesting out-of-domain unlabeled examples to effectively enrich the training data with informative, implicitly abusive texts.
Natural Language Processing (NLP) models risk overfitting to specific terms in the training data, thereby reducing their performance, fairness, and generalizability. E.g., neural hate speech detection models are strongly influenced by identity terms like gay, or women, resulting in false positives, severe unintended bias, and lower performance. Most mitigation techniques use lists of identity terms or samples from the target domain during training. However, this approach requires a-priori knowledge and introduces further bias if important terms are neglected. Instead, we propose a knowledge-free Entropy-based Attention Regularization (EAR) to discourage overfitting to training-specific terms. An additional objective function penalizes tokens with low self-attention entropy. We fine-tune BERT via EAR: the resulting model matches or exceeds state-of-the-art performance for hate speech classification and bias metrics on three benchmark corpora in English and Italian. EAR also reveals overfitting terms, i.e., terms most likely to induce bias, to help identify their effect on the model, task, and predictions.
Abusive content detection in spoken text can be addressed by performing Automatic Speech Recognition (ASR) and leveraging advancements in natural language processing. However, ASR models introduce latency and often perform sub-optimally for profane words as they are underrepresented in training corpora and not spoken clearly or completely. Exploration of this problem entirely in the audio domain has largely been limited by the lack of audio datasets. Building on these challenges, we propose ADIMA, a novel, linguistically diverse, ethically sourced, expert annotated and well-balanced multilingual profanity detection audio dataset comprising of 11,775 audio samples in 10 Indic languages spanning 65 hours and spoken by 6,446 unique users. Through quantitative experiments across monolingual and cross-lingual zero-shot settings, we take the first step in democratizing audio based content moderation in Indic languages and set forth our dataset to pave future work.
We present the first English corpus study on abusive language towards three conversational AI systems gathered "in the wild": an open-domain social bot, a rule-based chatbot, and a task-based system. To account for the complexity of the task, we take a more `nuanced' approach where our ConvAI dataset reflects fine-grained notions of abuse, as well as views from multiple expert annotators. We find that the distribution of abuse is vastly different compared to other commonly used datasets, with more sexually tinted aggression towards the virtual persona of these systems. Finally, we report results from bench-marking existing models against this data. Unsurprisingly, we find that there is substantial room for improvement with F1 scores below 90%.
While extensive popularity of online social media platforms has made information dissemination faster, it has also resulted in widespread online abuse of different types like hate speech, offensive language, sexist and racist opinions, etc. Detection and curtailment of such abusive content is critical for avoiding its psychological impact on victim communities, and thereby preventing hate crimes. Previous works have focused on classifying user posts into various forms of abusive behavior. But there has hardly been any focus on estimating the severity of abuse and the target. In this paper, we present a first of the kind dataset with 7601 posts from Gab which looks at online abuse from the perspective of presence of abuse, severity and target of abusive behavior. We also propose a system to address these tasks, obtaining an accuracy of ~80% for abuse presence, ~82% for abuse target prediction, and ~65% for abuse severity prediction.
In this paper, we describe our approach to utilize pre-trained BERT models with Convolutional Neural Networks for sub-task A of the Multilingual Offensive Language Identification shared task (OffensEval 2020), which is a part of the SemEval 2020. We show that combining CNN with BERT is better than using BERT on its own, and we emphasize the importance of utilizing pre-trained language models for downstream tasks. Our system, ranked 4th with macro averaged F1-Score of 0.897 in Arabic, 4th with score of 0.843 in Greek, and 3rd with score of 0.814 in Turkish. Additionally, we present ArabicBERT, a set of pre-trained transformer language models for Arabic that we share with the community.
Algorithms are widely applied to detect hate speech and abusive language in social media. We investigated whether the human-annotated data used to train these algorithms are biased. We utilized a publicly available annotated Twitter dataset (Founta et al. 2018) and classified the racial, gender, and party identification dimensions of 99,996 tweets. The results showed that African American tweets were up to 3.7 times more likely to be labeled as abusive, and African American male tweets were up to 77% more likely to be labeled as hateful compared to the others. These patterns were statistically significant and robust even when party identification was added as a control variable. This study provides the first systematic evidence on intersectional bias in datasets of hate speech and abusive language.
Nowadays, offensive content in social media has become a serious problem, and automatically detecting offensive language is an essential task. In this paper, we build an offensive language detection system, which combines multi-task learning with BERT-based models. Using a pre-trained language model such as BERT, we can effectively learn the representations for noisy text in social media. Besides, to boost the performance of offensive language detection, we leverage the supervision signals from other related tasks. In the OffensEval-2020 competition, our model achieves 91.51% F1 score in English Sub-task A, which is comparable to the first place (92.23%F1). An empirical analysis is provided to explain the effectiveness of our approaches.
With the spread of online social networks, it is more and more difficult to monitor all the user-generated content. Automating the moderation process of the inappropriate exchange content on Internet has thus become a priority task. Methods have been proposed for this purpose, but it can be challenging to find a suitable dataset to train and develop them. This issue is especially true for approaches based on information derived from the structure and the dynamic of the conversation. In this work, we propose an original framework, based on the Wikipedia Comment corpus, with comment-level abuse annotations of different types. The major contribution concerns the reconstruction of conversations, by comparison to existing corpora, which focus only on isolated messages (i.e. taken out of their conversational context). This large corpus of more than 380k annotated messages opens perspectives for online abuse detection and especially for context-based approaches. We also propose, in addition to this corpus, a complete benchmarking platform to stimulate and fairly compare scientific works around the problem of content abuse detection, trying to avoid the recurring problem of result replication. Finally, we apply two classification methods to our dataset to demonstrate its potential.
Reducing hateful and offensive content in online social media pose a dual problem for the moderators. On the one hand, rigid censorship on social media cannot be imposed. On the other, the free flow of such content cannot be allowed. Hence, we require efficient abusive language detection system to detect such harmful content in social media. In this paper, we present our machine learning model, HateMonitor, developed for Hate Speech and Offensive Content Identification in Indo-European Languages (HASOC), a shared task at FIRE 2019. We have used a Gradient Boosting model, along with BERT and LASER embeddings, to make the system language agnostic. Our model came at First position for the German sub-task A. We have also made our model public at https://github.com/punyajoy/HateMonitors-HASOC .
In recent years, online social networks have allowed worldwide users to meet and discuss. As guarantors of these communities, the administrators of these platforms must prevent users from adopting inappropriate behaviors. This verification task, mainly done by humans, is more and more difficult due to the ever growing amount of messages to check. Methods have been proposed to automatize this moderation process, mainly by providing approaches based on the textual content of the exchanged messages. Recent work has also shown that characteristics derived from the structure of conversations, in the form of conversational graphs, can help detecting these abusive messages. In this paper, we propose to take advantage of both sources of information by proposing fusion methods integrating content-and graph-based features. Our experiments on raw chat logs show that the content of the messages, but also of their dynamics within a conversation contain partially complementary information, allowing performance improvements on an abusive message classification task with a final F-measure of 93.26%.
This paper describes the UM-IU@LING's system for the SemEval 2019 Task 6: OffensEval. We take a mixed approach to identify and categorize hate speech in social media. In subtask A, we fine-tuned a BERT based classifier to detect abusive content in tweets, achieving a macro F1 score of 0.8136 on the test data, thus reaching the 3rd rank out of 103 submissions. In subtasks B and C, we used a linear SVM with selected character n-gram features. For subtask C, our system could identify the target of abuse with a macro F1 score of 0.5243, ranking it 27th out of 65 submissions.
SemEval-2019 Task 6 (Zampieri et al., 2019b) requires us to identify and categorise offensive language in social media. In this paper we will describe the process we took to tackle this challenge. Our process is heavily inspired by Sosa (2017) where he proposed CNN-LSTM and LSTM-CNN models to conduct twitter sentiment analysis. We decided to follow his approach as well as further his work by testing out different variations of RNN models with CNN. Specifically, we have divided the challenge into two parts: data processing and sampling and choosing the optimal deep learning architecture. In preprocessing, we experimented with two techniques, SMOTE and Class Weights to counter the imbalance between classes. Once we are happy with the quality of our input data, we proceed to choosing the optimal deep learning architecture for this task. Given the quality and quantity of data we have been given, we found that the addition of CNN layer provides very little to no additional improvement to our model's performance and sometimes even lead to a decrease in our F1-score. In the end, the deep learning architecture that gives us the highest macro F1-score is a simple BiLSTM-CNN.
The context-dependent nature of online aggression makes annotating large collections of data extremely difficult. Previously studied datasets in abusive language detection have been insufficient in size to efficiently train deep learning models. Recently, Hate and Abusive Speech on Twitter, a dataset much greater in size and reliability, has been released. However, this dataset has not been comprehensively studied to its potential. In this paper, we conduct the first comparative study of various learning models on Hate and Abusive Speech on Twitter, and discuss the possibility of using additional features and context data for improvements. Experimental results show that bidirectional GRU networks trained on word-level features, with Latent Topic Clustering modules, is the most accurate model scoring 0.805 F1.
This paper addresses the important problem of discerning hateful content in social media. We propose a detection scheme that is an ensemble of Recurrent Neural Network (RNN) classifiers, and it incorporates various features associated with user-related information, such as the users' tendency towards racism or sexism. These data are fed as input to the above classifiers along with the word frequency vectors derived from the textual content. Our approach has been evaluated on a publicly available corpus of 16k tweets, and the results demonstrate its effectiveness in comparison to existing state of the art solutions. More specifically, our scheme can successfully distinguish racism and sexism messages from normal text, and achieve higher classification quality than current state-of-the-art algorithms.