The following system description presents our approach to the detection of persuasion techniques in texts and images. The given task has been framed as a multi-label classification problem with the different techniques serving as class labels. The multi-label classification problem is one in which a list of target variables such as our class labels is associated with every input chunk and assumes that a document can simultaneously and independently be assigned to multiple labels or classes. In order to assign class labels to the given memes, we opted for RoBERTa (A Robustly Optimized BERT Pretraining Approach) as a neural network architecture for token and sequence classification. Starting off with a pre-trained model for language representation we fine-tuned this model on the given classification task with the provided annotated data in supervised training steps. To incorporate image features in the multi-modal setting, we rely on the pre-trained VGG-16 model architecture.
Information Space Dashboard
Theresa Krumbiegel | Albert Pritzkau | Hans-Christian Schmitz
Proceedings for the First International Workshop on Social Threats in Online Conversations: Understanding and Management
The information space, where information is generated, stored, exchanged and discussed, is not idyllic but a space where campaigns of disinformation and destabilization are conducted. Such campaigns are subsumed under the terms “hybrid warfare” and “information warfare” (Woolley and Howard, 2017). In order to enable awareness of them, we propose an information state dashboard comprising various components/apps for data collection, analysis and visualization. The aim of the dashboard is to support an analyst in generating a common operational picture of the information space, link it with an operational picture of the physical space and, thus, contribute to overarching situational awareness. The dashboard is work in progress. However, a first prototype with components for exploiting elementary language statistics, keyword and metadata analysis, text classification and network analysis has been implemented. Further components, in particular, for event extraction and sentiment analysis are under development. As a demonstration case, we briefly discuss the analysis of historical data regarding violent anti-migrant protests and respective counter-protests that took place in Chemnitz in 2018.