Sentiment Analysis of Russia-Ukraine Conflict Tweets Using RoBERTa
[Objective] The moment Russia officially invaded Ukraine, the world experienced a period of tension and uncertainty. As a social release valve digital communication, channels increased their number of users and activity, generating a large amount of data. Twitter, in particular, being one of the most popular channels for sharing information and opinions, exploded with activities related to this historical moment. And as with many other social events, such as COVID-19, this social network became one of the main sources of information, opinion, and knowledge. This paper analyzes sentiments in tweets related to the armed conflict between Russia and Ukraine. [Methodology] The analyzed dataset contains tweets from January 1, 2022, through March 3, 2022, and was collected using event-related hashtags. In total, 603,552 tweets in English and 1,664 in Russian were analyzed. To perform emotion classification, DistilRoBERTa variant and the pre-trained XLM-RoBERTa-Base model were used, respectively. English tweets were classified into seven emotions: anger, disgust, fear, joy, neutral, sadness, and surprise. Russian tweets were classified into positive negative, and neutral polarities. [Results] The results showed that most English tweets convey fear and anger as predominant feelings, reaching 32.08% and 15.18% of the total tweets analyzed, respectively. Regarding tweets in Russian, the majority presented negative polarity, with 86.83% of the total. Some of the most recurrent phrases in the analysis allude to support for Ukraine and call for a halt to the war. Likewise, phrases of concern for the crisis, weapons, and fatalities are recurrent. [Conclusion] As expected, most people were concerned about the armed conflict and upset and angry about its consequences. Future works could use more tweets to improve the analysis and increase the time range to be studied. The analysis could also be segmented to study the sentiments of tweets according to different groupings and compare them with other societies, for instance, tweets could be segmented by country and analyzed accordingly.
Dougherty, J., & Ilyankou, I. (2021). Hands-On Data Visualization. O'Reilly Media, Inc.
Ekman, P. (1992). An argument for basic emotions. Cognition & emotion, 6, 169-200. https://doi.org/10.1080/02699939208411068
Hartmann, J. (2022). Emotion English DistilRoBERTa-base.
Imran, A., Daudpota, S., Kastrati, Z., & Batra, R. (2020). Cross-cultural polarity and emotion detection using sentiment analysis and deep learning on covid-19 related tweets. IEEE Access, 8, 181074-181090. https://doi.org/10.1109/ACCESS.2020.3027350
Janiesch, C., Zschech, P., & Heinrich, K. (2021). Machine learning and deep learning. Electronic Markets, 31, 685-695. https://doi.org/10.1007/s12525-021-00475-2
Jianqiang, Z., & Xiaolin, G. (2017). Comparison Research on Text Pre-processing Methods on Twitter Sentiment Analysis. IEEE Access, 2870-2879. https://doi.org/10.1109/ACCESS.2017.2672677
Karin, E. (2019). Primate Ecology and Behavior. Retrieved from https://pressbooks-dev.oer.hawaii.edu/explorationsbioanth/chapter/__unknown__-6/
Khun, N., & Thant, H. (2019). Visualization of Twitter Sentiment during the Period of US Banned Huawei. International Conference on Advanced Information Technologies, ICAIT 2019 (pp. 274-279). Institute of Electrical and Electronics Engineers Inc. https://doi.org/10.1109/AITC.2019.8921014
Kret, M., Prochazkova, E., Sterck, E., & Clay, Z. (2020). Emotional expressions in human and non-human great apes. Neuroscience & Biobehavioral Reviews, 115. https://doi.org/10.1016/j.neubiorev.2020.01.027
Li, Q. (2020). Overview of Data Visualization. Embodying Data, 17-47. doi:10.1007/978-981-15-5069-0_2
Mbah, R., & Wasum, D. (2022). Russian-Ukraine 2022 War: A Review of the Economic Impact of Russian-Ukraine Crisis on the USA, UK, Canada, and Europe. Advances in Social Sciences Research Journal, 9, 144-153. https://doi.org/10.14738/assrj.93.12005
Mota, F., & Cilento, I. (2020). Competence for internet use: Integrating knowledge, skills, and attitudes. Computers and Education Open, 1, 115. https://doi.org/10.1016/j.caeo.2020.100015
Neogi, A., Garg, K., Mishra, R., & Dwivedi, Y. (2021). Sentiment analysis and classification of Indian farmers’ protest using twitter data. International Journal of Information Management Data Insights, 1(2), 100019. https://doi.org/10.1016/j.jjimei.2021.100019
Pota, M., Ventura, M., Fujita, H., & Esposito, M. (2021). Multilingual evaluation of pre-processing for BERT-based sentiment analysis of tweets. Expert Systems with Applications, 115119. https://doi.org/10.1016/j.eswa.2021.115119
Sanh, V., Debut, L., Chaumond, J., & Wolf, T. (2019). DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter. ArXiv.
Signe, P. (2000). Primate Faces and Facial Expressions. Social Research, 67, 245-271.
Smetanin, S., & Komarov, M. (2019). Sentiment Analysis of Product Reviews in Russian using Convolutional Neural Networks. 2019 IEEE 21st Conference on Business Informatics (CBI) (pp. 482-486). IEEE. https://doi.org/10.1109/CBI.2019.00062
Smetanin, S., & Komarov, M. (2021). Deep transfer learning baselines for sentiment analysis in Russian. Information Processing & Management, 102484. https://doi.org/10.1016/j.ipm.2020.102484
Tomkins, S. (1962). Affect imagery consciousness: Volume I: The positive affects. Springer publishing company.
Zhang, C., & Lu, Y. (2021). Study on artificial intelligence: The state of the art and future prospects. Journal of Industrial Information Integration, 23. https://doi.org/10.1016/j.jii.2021.100224
Copyright (c) 2023 Shared by Journal and Authors (CC-BY-NC-ND)
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
Authors who publish with this journal agree to the following terms:
1. Authors guarantee the journal the right to be the first publication of the work as licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
2. Authors can set separate additional agreements for non-exclusive distribution of the version of the work published in the journal (eg, place it in an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
3. The authors have declared to hold all permissions to use the resources they provided in the paper (images, tables, among others) and assume full responsibility for damages to third parties.
4. The opinions expressed in the paper are the exclusive responsibility of the authors and do not necessarily represent the opinion of the editors or the Universidad Nacional.
Uniciencia Journal and all its productions are under Creative Commons Atribución-NoComercial-SinDerivadas 4.0 Unported.
There is neither fee for access nor Article Processing Charge (APC)