A Comparative Study on Detecting Financial and Administrative Corruption Using AI and Real-World Datasets
DOI:
https://doi.org/10.25130/jfa.conf.10.5.20Keywords:
Artificial Intelligence, Machine Learning, Corruption Detection, Financial Corruption, Administrative Corruption, Governance Indicators, LearningAbstract
This study examines how learners of English as a foreign language use language to create identity, stimulate motivation, and manage cognitive stress in AI-mediated learning contexts. The study emphases on the sociocultural backgrounds of the learners. The analysis involves a thematically sensitive discourse coding aligned with Self-Determination Theory, Sociocultural Theory, and Cognitive Load Theory. The study is grounded on semi-structured interviews with fifteen students from two university faculties. The findings reveal that learner strategies were to employ narrative discourses and evaluative language to confirm identity or reduce linguistic dominance. Students also use metaphors and temporal markers to describe cognitive load. Peer and teacher prompts, as well as AI tools, also reflect the learners' identities. It was revealed that contextual factors, such as ways of peer interaction, resource limits, and faculty norms stimulus the occurrence and understanding of these practices. The study shows that in AI-enhanced classrooms, language practise assists as a medium that supports sociocultural bonds and makes motivational dynamics more stable. These findings support the proposal of pedagogical approaches which are identity-sensitive, feedback designed linguistic approaches, and assessments which are aware of the discourse of AI tools in EFL contexts. The study is an attempt to add to the improvement of applied linguistics in the field of technology-mediated language acquisition, by focusing on the discourse as a way to access motivational experience and linking the micro-level linguistic practices to larger sociocultural processes. .
Downloads
References
Pearson, K. (1901). On lines and planes of closest fit to systems of points in space. Philosophical Magazine, 2(11), 559–572. https://doi.org/10.1080/14786440109462720
World Bank. (2016). The cost of corruption worldwide. Washington, DC: World Bank Publications. https://doi.org/10.1596/978-1-4648-0867-0
Gasanova, O., Medvedev, D., & Komotskiy, I. (2017). Corruption and its macroeconomic effects. Economic Policy Review, 23(3), 56–78. https://doi.org/10.2139/ssrn.2938475
United Nations Development Programme (UNDP). (2024). Human development report 2024: Governance and corruption. https://www.undp.org/publications
Stockemer, D. (2018). Predicting corruption using AI models: Evidence from global datasets. Journal of Comparative Policy Analysis, 20(5), 427–445. https://doi.org/10.1080/13876988.2018.1456223
Sun, W., & Medaglia, R. (2019). Machine learning applications in corruption research. Government Information Quarterly, 36(4), 101393. https://doi.org/10.1016/j.giq.2019.05.001
Tang, Y., Chen, S., & Zhang, L. (2019). AI in financial fraud detection: A review. Expert Systems with Applications, 126, 270–285. https://doi.org/10.1016/j.eswa.2019.02.017
Zhang, H., Li, X., & Wu, J. (2021). Deep learning for predicting corruption risks: Evidence from public datasets. Information Processing & Management, 58(6), 102678. https://doi.org/10.1016/j.ipm.2021.102678
Transparency International. (2023). Corruption perception map 2023. https://www.transparency.org/en/cpi/2023
Rose-Ackerman, S., & Palifka, B. J. (2016). Corruption and government: Causes, consequences, and reform (2nd ed.). Cambridge University Press.
Kaggle. (n.d.). Credit card fraud detection dataset. https://www.kaggle.com/datasets/mlg-ulb/creditcardfraud
Transparency International. (n.d.). Corruption perceptions index (CPI). https://www.transparency.org/en/cpi
Kaufmann, D., & Kraay, A. (2024). The Worldwide Governance Indicators: Methodology and 2024 update (World Bank Policy Research Working Paper No. 10952). World Bank. https://www.govindicators.org
Springer, N. W. K. (2025). Data pre-processing in machine learning-based corruption detection. Springer. https://link.springer.com/series/15179
Ahmed, I., Naseer, S., & Mahmood, Z. (2023). Predictive-analysis-based machine learning model for fraud detection with boosting classifiers. Journal of Intelligent & Fuzzy Systems, 44(3), 3451–3462. https://doi.org/10.3233/JIFS-223157
Katiyar, S., Kumar, A., & Kannan, R. (2025). CatBoost and AdaBoost-based approaches for imbalanced financial datasets. Future Generation Computer Systems, 152, 327–339. https://doi.org/10.1016/j.future.2024.11.005
Rusakov, K., Zhelezniakova, A., & Chugunov, A. (2021). Fraud detection in credit cards using logistic regression. International Journal of Advanced Computer Science and Applications, 12(12), 650–656. https://doi.org/10.14569/IJACSA.2021.0121275
Doostmohammadi, R., & Nassajian, M. (2019). Credit card fraud detection using Naïve Bayes model. International Journal of Advance Research, Ideas and Innovations in Technology, 5(3), 123–128.
Taunk, K., De, S., Verma, S., & Swetapadma, A. (2019). A brief review of nearest neighbor algorithm for learning and classification. In 2019 International Conference on Intelligent Computing and Control Systems (ICCS) (pp. 1255–1260). IEEE. https://doi.org/10.1109/ICCS45141.2019.9065747
Sothe, N., Kumar, S., & Sharma, P. (2020). Credit card fraud detection using decision tree and random forest. International Journal of Innovative Technology and Exploring Engineering, 9(3), 1103–1107. https://doi.org/10.35940/ijitee.C8313.019320
Opitz, J. (2024). A closer look at classification evaluation metrics and a critical reflection of common evaluation practice. Transactions of the Association for Computational Linguistics, 12, 820–836. https://doi.org/10.1162/tacl_a_00675
Tuarob, S., Tatiyamaneekul, P., Pongpaichet, S., Tawichsri, T., & Noraset, T. (2025). Beyond administrative reports: A deep learning framework for classifying and monitoring crime and accidents leveraging large-scale online news. Neural Computing and Applications, 37, 7183–7205. https://doi.org/10.1007/s00521-024-10833-8
Bhandari, H. N., Rimal, R. P., & Wang, Q. (2024). Implementation of deep learning models in predicting ESG index volatility: A comparative study. Financial Innovation, 10(75). https://doi.org/10.1186/s40854-023-00604-0
