OPINION MINING IN ESP CLASSROOMS: A COMPARATIVE ANALYSIS OF TRADITIONAL VS. AI-ASSISTED INSTRUCTION
DOI:
https://doi.org/10.18485/bells.2025.17.7Keywords:
opinion mining, sentiment analysis, sentiment lexicon, AI-assisted classroom, traditional paradigm, large language models in classroomAbstract
This study investigates sentiment analysis, specifically opinion mining, in English for Specific Purposes (ESP) classrooms by comparing traditional teaching methods with AI-assisted instruction. A total of 41 students (11 males, 30 females) were exposed to traditional classroom methods during the winter semester (serving as a Control group) and, later, participated in AI-assisted classroom during the summer semester (serving as a Target group). Employing advanced sentiment analysis techniques, we analysed 82 essays written by these students, focusing on their attitudes towards the provided learning materials. Our approach involved using a specialised sentiment lexicon for accurate scoring and classification. The findings reveal a shift towards positive sentiment in the AI-assisted classroom (Target group), underscoring AI's potential in augmenting the emotional aspects of language learning. These insights are critical for understanding student perceptions of different teaching paradigms and highlight the transformative impact of AI in educational settings.
Downloads
References
Baker, R. S. J. d., D’Mello, S. K., Rodrigo, M. M. T., & Graesser, A. C. (2010). Better to be frustrated than bored: The incidence, persistence, and impact of learners’ cognitive–affective states during interactions with three different computer-based learning environments. International Journal of Human–Computer Studies, 68(4), 223–241. https://doi.org/10.1016/j.ijhcs.2009.12.003.
Braun, V., & Clarke, V. (2006). Using thematic analysis in psychology. Qualitative Research in Psychology, 3(2), 77–101. https://doi.org/10.1191/1478088706qp063oa.
Colace, F., Casaburi, L., De Santo, M., & Greco, L. (2015). Sentiment detection in social networks and in collaborative learning environments. Computers in Human Behavior, 51, 1061–1067. https://doi.org/10.1016/j.chb.2014.11.090.
D’Mello, S., & Graesser, A. (2012). Dynamics of affective states during complex learning. Learning and Instruction, 22(2), 145–157. https://doi.org/10.1016/j.learninstruc.2011.10.001.
Feldman, R. & Ungar, L. (2012). Sentiment Mining from user generated content. Tutorial at the Sixth International AAAI Conference on Weblogs and Social Media. http://www.cis.upenn.edu/~ungar/AAAI/AAAI13.pdf.
Hutto, C. J. & Gilbert, E. E. (2014). VADER: A parsimonious rule-based model for sentiment analysis of social media text. Proceedings of the Eighth International AAAI Conference on Weblogs and Social Media (ICWSM-14), 216–225. https://doi.org/10.1609/icwsm.v8i1.14550.
Author (2023)
Author (2024)
Liu, B. (2010) Sentiment Analysis and Subjectivity. In: Indurkhya, N. and Damerauthe, F.J., Eds., Handbook of Natural Language Processing, 2nd Edition, Chapman and Hall/CRC, London, 1-38.
Ortigosa, A., Martín, J. M., & Carro, R. M. (2014). Sentiment analysis in Facebook and its application to e-learning. Computers in Human Behavior, 31, 527–541. https://doi.org/10.1016/j.chb.2013.05.024.
Weitl-Harms, S., Hastings, J. D., & Lum, J. (2024). Using LLMs to establish implicit user sentiment of software desirability. In 2024 International Conference on Machine Learning and Applications (ICMLA) (pp. 1645–1650). IEEE. https://doi.org/10.1109/ICMLA61862.2024.00254.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Igor Ivanović
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors are confirming that they are the authors of the submitting article, which will be published (print and online) in Belgrade English Language and Literature Studies by the Faculty of Philology, University of Belgrade (Faculty of Philology, Studentski trg 3, 11000 Belgrade, Serbia). Author’s name will be evident in the printed article in the journal. All decisions regarding layout and distribution of the work are in hands of the publisher.
- Authors guarantee that the work is their own original creation and does not infringe any statutory or common-law copyright or any proprietary right of any third party. In case of claims by third parties, authors commit their self to defend the interests of the publisher, and shall cover any potential costs.
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution-ShareAlike 4.0 International License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.
