Dirk Labudde


2022

pdf
DeTox: A Comprehensive Dataset for German Offensive Language and Conversation Analysis
Christoph Demus | Jonas Pitz | Mina Schütz | Nadine Probol | Melanie Siegel | Dirk Labudde
Proceedings of the Sixth Workshop on Online Abuse and Harms (WOAH)

In this work, we present a new publicly available offensive language dataset of 10.278 German social media comments collected in the first half of 2021 that were annotated by in 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 in particular also at toxicity, criminal relevance and discrimination types of comments. Furthermore, about half of the comments are from coherent parts of conversations, which opens the possibility to consider the comments’ contexts and do conversation analyses in order to research the contagion of offensive language in conversations.

2021

pdf
Automatically Identifying Online Grooming Chats Using CNN-based Feature Extraction
Svenja Preuß | Luna Pia Bley | Tabea Bayha | Vivien Dehne | Alessa Jordan | Sophie Reimann | Fina Roberto | Josephine Romy Zahm | Hanna Siewerts | Dirk Labudde | Michael Spranger
Proceedings of the 17th Conference on Natural Language Processing (KONVENS 2021)

pdf
DeTox at GermEval 2021: Toxic Comment Classification
Mina Schütz | Christoph Demus | Jonas Pitz | Nadine Probol | Melanie Siegel | Dirk Labudde
Proceedings of the GermEval 2021 Shared Task on the Identification of Toxic, Engaging, and Fact-Claiming Comments

In this work, we present our approaches on the toxic comment classification task (subtask 1) of the GermEval 2021 Shared Task. For this binary task, we propose three models: a German BERT transformer model; a multilayer perceptron, which was first trained in parallel on textual input and 14 additional linguistic features and then concatenated in an additional layer; and a multilayer perceptron with both feature types as input. We enhanced our pre-trained transformer model by re-training it with over 1 million tweets and fine-tuned it on two additional German datasets of similar tasks. The embeddings of the final fine-tuned German BERT were taken as the textual input features for our neural networks. Our best models on the validation data were both neural networks, however our enhanced German BERT gained with a F1-score = 0.5895 a higher prediction on the test data.