The emergence of anti-social behaviour in online environments presents a serious issue in today’s society. Automatic detection and identification of such behaviour are becoming increasingly important. Modern machine learning and natural language processing methods can provide effective tools to detect different types of anti-social behaviour from the pieces of text. In this work, we present a comparison of various deep learning models used to identify the toxic comments in the Internet discussions. Our main goal was to explore the effect of the data preparation on the model performance. As we worked with the assumption that the use of traditional pre-processing methods may lead to the loss of characteristic traits, specific for toxic content, we compared several popular deep learning and transformer language models. We aimed to analyze the influence of different pre-processing techniques and text representations including standard TF-IDF, pre-trained word embeddings and also explored currently popular transformer models. Experiments were performed on the dataset from the Kaggle Toxic Comment Classification competition, and the best performing model was compared with the similar approaches using standard metrics used in data analysis.

Spreading of misinformation on the web nowadays represents a serious issue, as their influence on peoples opinions may be significant. Fake news represents a specific type of misinformation. While its detection was mostly being performed manually in the past, automated methods using machine learning and related fields became more critical. On the other hand, deep learning methods became very popular and frequently used methods in the field of data analysis in recent years. The study presented in this paper deals with the detection of fake news from the textual data using deep learning techniques. Our main idea was to train different types of neural network models using both entire texts from the articles and to use just the title text. The models were trained and evaluated on the Fake News dataset obtained from the Kaggle competition.

Machine-learning techniques have been increasingly used in astronomical applications and have proven to successfully classify objects in image data with high accuracy. The current work uses archival data from the Faint Images of the Radio Sky at Twenty Centimeters (FIRST) to classify radio galaxies into four classes: Fanaroff–Riley Class I (FRI), Fanaroff–Riley Class II (FRII), Bent-Tailed (BENT), and Compact (COMPT). The model presented in this work is based on Convolutional Neural Networks (CNNs). The proposed architecture comprises three parallel blocks of convolutional layers combined and processed for final classification by two feed-forward layers. Our model classified selected classes of radio galaxy sources on an independent testing subset with an average of 96 per cent for precision, recall, and F1 score. The best selected augmentation techniques were rotations, horizontal or vertical flips, and increase of brightness. Shifts, zoom, and decrease of brightness worsened the performance of the model. The current results show that model developed in this work is able to identify different morphological classes of radio galaxies with a high efficiency and performance.

Structures in the solar corona are the main drivers of space weather processes that might directly or indirectly affect the Earth. Thanks to the most recent space-based solar observatories, with capabilities to acquire high-resolution images continuously, the structures in the solar corona can be monitored over the years with a time resolution of minutes. For this purpose, we have developed a method for automatic segmentation of solar corona structures observed in the EUV spectrum that is based on a deep-learning approach utilizing convolutional neural networks. The available input data sets have been examined together with our own data set based on the manual annotation of the target structures. Indeed, the input data set is the main limitation of the developed model’s performance. Our SCSS-Net model provides results for coronal holes and active regions that could be compared with other generally used methods for automatic segmentation. Even more, it provides a universal procedure to identify structures in the solar corona with the help of the transfer learning technique. The outputs of the model can be then used for further statistical studies of connections between solar activity and the influence of space weather on Earth.