o:2303 Deep Learning Analysis of Tweets Regarding Covid19 Vaccination in the Serbian Language en In this paper, we present an efficient classifier that is able to perform automatic filtering and detection of tweets with clear negative sentiment towards COVID-19 vaccination process. We used a transformer-based architecture in order to build the classifier. A pre-trained transformer encoder that is trained in ELECTRA fashion, BERTic, was selected and fine-tuned on a dataset we collected and manually annotated. Such an automatic filtering and detection algorithm is of utmost importance in order to explore the reasons behind the negative sentiment of Twitter users towards a particular topic and develop a communication strategy to educate them and provide them with accurate information regarding their specific beliefs that have been identified. 1552100 978-86-85525-24-7 1552101 2738-1447 2023-06-14T14:09:52.415Z 44 yes 46 Nikola Prodanović The Institute for Artificial Intelligence Research and Development of Serbia person 0000-0001-8698-9830 Adela Ljajić The Institute for Artificial Intelligence Research and Development of Serbia 0000-0001-7326-059X Darija Medvecki The Institute for Artificial Intelligence Research and Development of Serbia person 0000-0002-4180-0050 Jelena Mitrović The Institute for Artificial Intelligence Research and Development of Serbia; Faculty of Computer Science and Mathematics, University of Passau, Germany person 0000-0003-3220-8749 Dubravko Ćulibrk The Institute for Artificial Intelligence Research and Development of Serbia person 0000-0003-3417-1687 application/pdf 126930 https://unilib.phaidrabg.rs/o:2303 no yes 1 70 92000004 71A08 Proceedings of the 12th International Conference on Information Society and Technology ISOS Conference Proceedings Series 64 66 Information Society of Serbia - ISOS 2022