Prodanović, Nikola Ljajić, Adela Medvecki, Darija Mitrović, Jelena Ćulibrk, Dubravko info:eu-repo/semantics/conferenceProceedings 2022 eng application/pdf 126930 bytes Information Society of Serbia - ISOS Proceedings of the 12th International Conference on Information Society and Technology All rights reserved https://unilib.phaidrabg.rs/o:2303 ISSN: 2738-1447 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. Deep Learning Analysis of Tweets Regarding Covid19 Vaccination in the Serbian Language