Machine Learning for Textual Data Processing

The study course offers undergraduate students the opportunity to develop their knowledge, competences, and skills in applying and customizing the available machine-learning tools for textual data processing to solve a range of practical industry-related and research tasks including but not limited to corpus and textual data analysis, data preprocessing and representation, sentiment analysis, and machine translation applications. Students shall develop a comprehensive understanding of the nature of the contemporary multi-modal digital text considering, inter alia ethical, security, and sustainability aspects of textual data collection, processing, and representation. They will gain experience in the practical application of data and text mining approaches, data structuring, and data visualization techniques, learn to validate, segment, and reuse the results of textual data analysis using corresponding machine-learning methods, and develop skills in using qualitative and quantitative data analysis techniques.