A5038466637- Hate Speech and Cyberbullying Detection
- Misinformation and Its Impacts
- Speech and Audio Processing
- Topic Modeling
- Music and Audio Processing
- Digital Media Forensic Detection
- Swearing, Euphemism, Multilingualism
- Terrorism, Counterterrorism, and Political Violence
- Social Media and Politics
- Gender Studies in Language
- Advanced Text Analysis Techniques
- Sexual Assault and Victimization Studies
- Freedom of Expression and Defamation
- Spam and Phishing Detection
- Video Analysis and Summarization
- Bullying, Victimization, and Aggression
Austrian Institute of Technology
2021-2024
Darmstadt University of Applied Sciences
2022-2023
In this work, we present a new publicly available offensive language dataset of 10.278 German social media comments collected in the first half 2021 that were annotated by total six annotators. With twelve different annotation categories, it is far more comprehensive than other datasets, and goes beyond just hate speech detection. The labels aim particular also at toxicity, criminal relevance discrimination types comments.Furthermore, about are from coherent parts conversations, which opens...
Sexism has become an increasingly major problem on social networks during the last years. The first shared task sEXism Identification in Social neTworks (EXIST) at IberLEF 2021 is international competition field of Natural Language Processing (NLP) with aim to automatically identify sexism media content by applying machine learning methods. Thereby detection formulated as a coarse (binary) classification and fine-grained that distinguishes multiple types sexist (e.g., dominance,...
In this paper, we present deep learning frameworks for audio-visual scene classification (SC) and indicate how individual visual audio features as well their combination affect SC performance.Our extensive experiments, which are conducted on DCASE (IEEE AASP Challenge Detection Classification of Acoustic Scenes Events) Task 1B development dataset, achieve the best accuracy 82.2\%, 91.1\%, 93.9\% with input only, both input, respectively.The highest 93.9\%, obtained from an ensemble...
In this paper, we present deep learning frameworks for audio-visual scene classification (SC) and indicate how individual visual audio features as well their combination affect SC performance. Our extensive experiments, which are conducted on DCASE (IEEE AASP Challenge Detection Classification of Acoustic Scenes Events) Task 1B development dataset, achieve the best accuracy 82.2%, 91.1%, 93.9% with input only, both input, respectively. The highest 93.9%, obtained from an ensemble audio-based...