A lack of demographic context in existing toxic speech datasets limits our understanding of how different age groups communicate online. In collaboration with funk, a German public service content network, this research introduces the first large-scale German dataset annotated for toxicity and enriched with platform-provided age estimates. The dataset includes 3,024 human-annotated and 30,024 LLM-annotated anonymized comments from Instagram, TikTok, and YouTube. To ensure relevance, comments were consolidated using predefined toxic keywords, resulting in 16.7\% labeled as problematic. The annotation pipeline combined human expertise with state-of-the-art language models, identifying key categories such as insults, disinformation, and criticism of broadcasting fees. The dataset reveals age-based differences in toxic speech patterns, with younger users favoring expressive language and older users more often engaging in disinformation and devaluation. This resource provides new opportunities for studying linguistic variation across demographics and supports the development of more equitable and age-aware content moderation systems.

Toxic speech on online platforms is a growing concern, impacting user experience and online safety. While text-based toxicity detection is well-studied, audio-based approaches remain underexplored, especially for low-resource languages like Vietnamese. This paper introduces ViToSA (Vietnamese Toxic Spans Audio), the first dataset for toxic spans detection in Vietnamese speech, comprising 11,000 audio samples (25 hours) with accurate human-annotated transcripts. We propose a pipeline that combines ASR and toxic spans detection for fine-grained identification of toxic content. Our experiments show that fine-tuning ASR models on ViToSA significantly reduces WER when transcribing toxic speech, while the text-based toxic spans detection (TSD) models outperform existing baselines. These findings establish a novel benchmark for Vietnamese audio-based toxic spans detection, paving the way for future research in speech content moderation.

The fundamental problem of toxicity detection lies in the fact that the term "toxicity" is ill-defined. Such uncertainty causes researchers to rely on subjective and vague data during model training, which leads to non-robust and inaccurate results, following the 'garbage in - garbage out' paradigm. This study introduces a novel, objective, and context-aware framework for toxicity detection, leveraging stress levels as a key determinant of toxicity. We propose new definition, metric and training approach as a parts of our framework and demonstrate it's effectiveness using a dataset we collected.

The proliferation of online toxic speech is a pertinent problem posing threats to demographic groups. While explicit toxic speech contains offensive lexical signals, implicit one consists of coded or indirect language. Therefore, it is crucial for models not only to detect implicit toxic speech but also to explain its toxicity. This draws a unique need for unified frameworks that can effectively detect and explain implicit toxic speech. Prior works mainly formulated the task of toxic speech detection and explanation as a text generation problem. Nonetheless, models trained using this strategy can be prone to suffer from the consequent error propagation problem. Moreover, our experiments reveal that the detection results of such models are much lower than those that focus only on the detection task. To bridge these gaps, we introduce ToXCL, a unified framework for the detection and explanation of implicit toxic speech. Our model consists of three modules: a (i) Target Group Generator to generate the targeted demographic group(s) of a given post; an (ii) Encoder-Decoder Model in which the encoder focuses on detecting implicit toxic speech and is boosted by a (iii) Teacher Classifier via knowledge distillation, and the decoder generates the necessary explanation. ToXCL achieves new state-of-the-art effectiveness, and outperforms baselines significantly.

The shift of public debate to the digital sphere has been accompanied by a rise in online hate speech. While many promising approaches for hate speech classification have been proposed, studies often focus only on a single language, usually English, and do not address three key concerns: post-deployment performance, classifier maintenance and infrastructural limitations. In this paper, we introduce a new human-in-the-loop BERT-based hate speech classification pipeline and trace its development from initial data collection and annotation all the way to post-deployment. Our classifier, trained using data from our original corpus of over 422k examples, is specifically developed for the inherently multilingual setting of Switzerland and outperforms with its F1 score of 80.5 the currently best-performing BERT-based multilingual classifier by 5.8 F1 points in German and 3.6 F1 points in French. Our systematic evaluations over a 12-month period further highlight the vital importance of continuous, human-in-the-loop classifier maintenance to ensure robust hate speech classification post-deployment.

You are free to share this article under the Attribution 4.0 International license. The main problem: There is a huge difference between evaluating more traditional AI tasks, like recognizing spoken language, and the much messier task of identifying hate speech, harassment, or misinformation--especially in today's polarized environment. "It appears as if the models are getting almost perfect scores, so some people think they can use them as a sort of black box to test for toxicity," says Mitchell Gordon, a PhD candidate in computer science at Stanford University who worked on the project. They're evaluating these models with approaches that work well when the answers are fairly clear, like recognizing whether'java' means coffee or the computer language, but these are tasks where the answers are not clear." Facebook says its artificial intelligence models identified and pulled down 27 million pieces of hate speech in the final three months of 2020.

The spectacular expansion of the Internet led to the development of a new research problem in the natural language processing field: automatic toxic comment detection, since many countries prohibit hate speech in public media. There is no clear and formal definition of hate, offensive, toxic and abusive speeches. In this article, we put all these terms under the "umbrella" of toxic speech. The contribution of this paper is the design of binary classification and regression-based approaches aiming to predict whether a comment is toxic or not. We compare different unsupervised word representations and different DNN classifiers. Moreover, we study the robustness of the proposed approaches to adversarial attacks by adding one (healthy or toxic) word. We evaluate the proposed methodology on the English Wikipedia Detox corpus. Our experiments show that using BERT fine-tuning outperforms feature-based BERT, Mikolov's word embedding or fastText representations with different DNN classifiers.

Anyone who has ventured into online gaming knows text chat can approach nuclear-waste-levels of toxicity. But what happens when it all shifts to voice-based chat in the future? Intel says it can help. Or at least, it hopes it can. The company said on Wednesday night it's working with Spirit AI on ways to use machine learning and artificial intelligence to reduce the acidic speech gamers often fall back on during intense gaming sessions. Spirit AI already has a machine-based tool developers can use to help monitor forums and online chat.