YAPAY ZEKÂ DESTEKLİ DOĞAL DİL İŞLEME YAKLAŞIMLARININ MUHASEBE BİLGİ SİSTEMLERİNE ENTEGRASYONU

Abstract

Muhasebe bilgi sistemleri, işletmelerin finansal süreçlerini yönetmesinde ve karar destek mekanizmalarını güçlendirmesinde kritik bir rol üstlenmektedir. Ancak mevcut sistemler, karmaşık arayüzleri ve sorgu yapıları nedeniyle özellikle teknik uzmanlığı olmayan kullanıcılar için erişimi zorlaştırmaktadır. Yapay zekâ destekli doğal dil işleme (NLP) yaklaşımları, finansal verilere doğal dil aracılığıyla erişim sağlayarak bu sınırlılıkları aşma potansiyeline sahiptir. Çalışmanın temel amacı, NLP teknolojilerinin muhasebe bilgi sistemlerine entegrasyonunun kavramsal boyutlarını ve alan yazındaki araştırma boşluklarını literatür temelli bir analiz çerçevesinde tartışmaktır. Önerilen teorik çerçeve, muhasebe bilgi sistemlerinin geleceğine yönelik yeni bir paradigmaya işaret etmektedir. Literatür analizi, Türkçe muhasebe terminolojisine özgü mikro-domain NLP modellerinin geliştirilmesinin veri erişiminin demokratikleşmesi ve kullanıcı etkinliği açısından stratejik bir katkı potansiyeli taşıdığını ortaya koymaktadır.

Keywords

• Muhasebe bilgi sistemleri
• doğal dil işleme
• yapay zekâ
• etkileşimli raporlama

INTEGRATION OF ARTIFICIAL INTELLIGENCE-BASED NATURAL LANGUAGE PROCESING APPROACHES INTO ACCOUNTING INFORMATION SYSTEMS

Abstract

Accounting information systems play a critical role in managing the financial processes of businesses and strengthening decision-support mechanisms. However, existing systems make access difficult, especially for users without technical expertise, due to their complex interfaces and query structures. In this context, artificial intelligence-supported natural language processing (NLP) approaches have the potential to overcome these limitations by providing access to financial data through natural language. The main objective of the study is to discuss the conceptual dimensions of integrating NLP technologies into accounting information systems and the research gaps in the literature within a literature-based analytical framework. Thus, the proposed theoretical framework points to a new paradigm for the future of accounting information systems. The literature analysis reveals that the development of micro-domain NLP models tailored to Turkish accounting terminology will significantly contribute to the democratization data access and user efficiency.

Keywords

• Accounting information systems
• natural language processing
• artificial intelligence
• interactive reporting

References

1. Abu Bakar, A.A. & Ameer, R. (2011). Readability of Corporate Social Responsibility Communication in Malaysia. Corporate Social Responsibility and Environmental Management, 18(1), 50-60.
2. Al-Dmour, R., Alkhatib, O., Al-Dmour, H., & Amin, E. (2023). The Influence of Social Marketing Drives on Brand Loyalty via the Customer Satisfaction as a Mediating Factor in Travel and Tourism Offices. SAGE Open, 13.
3. Algrari, A.Y. & Mr. Rebwar, M. A. (2019). The impact of Accounting Information Systems’ Quality on Accounting Information Quality. Journal of Information Technology Management, 11, 62–80.
4. Bao, Y., Ke, B., Li, B., Yu, Y. J., & Zhang, J. (2020). Detecting accounting fraud in publicly traded US firms using a machine learning approach. Journal of Accounting Research, 58(1), 199-235.
5. Bean, R. (2016). How time-to-insight is Driving Big Data Business Investment. MIT Sloan: Management Review. Bochkay, K. Brown, S.V., Leona, A.J. & Tucker, W. (2022). Textual Analysis in Accounting: What’s Next?. Contemporary Accounting Research, 40(2): 765-805.
6. Ding, K., Lev, B., Peng, X., Sun, T., & Vasarhelyi, M.A. (2020). Machine Learning Improves Accounting Estimates: Evidence from Insurance Payments. S&P Global Market Intelligence.
7. Dong, M.M., Stratopoulos, T.C., & Wang, V.X. (2024). A Scoping Review of ChatGPT Research in Accounting and Finance. International Journal of Accounting Information Systems, 55, 100715. arXiv:2412.05731
8. Fisher, I. E., Garnsey, M. R., & Hughes, M. E. (2016). Natural Language Processing in Accounting, Auditing and Finance: A Synthesis of the Literature With a Roadmap for Future Research. Intelligent Systems in Accounting, Finance and Management, 23(3), 157–214.

9. Gumbo, L., Mashizha, M., Simon, C., & Phiri, P. (2023). Conversational artificial intelligence (AI) and bank operational efficiency. International Journal of Accounting and Management Information Systems, 1(2), 79–91.
10. Gururangan, S., Marasović, A., Swayamdipta, S. Lo, K., Beltagy, I., Downey, D. & Smith, N.A. (2020). Don’t Stop Pretraining: Adapt Language Models to Domains and Tasks. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, 8342–8360.
11. Hadi, M. U., Qasem A.T., Qureshi, R., Shah, A., Muneer, A., ırfan, M., Zafar, A., Shaikh, M.B., Akthar, N., Wu, J. & Mirjalili, S. (2023). Large Language Models: A Comprehensive Survey of Its Applications, Challenges, Limitations, and Future Prospects. Doi: 10.36227/techrxiv.23589741.v1.
12. Jurafsky, D. & Martin, J.H. (2025). Speech and Language Processing: An Introduction to Natural Processing, Computational Linguistics and Speech Recognition with Language Models. Stanford University, 3. Ed. Kim, A., Muhn, M., & Nikolaev, V. (2024). Financial Statement Analysis with Large Language Models, 2407.17866, arXiv.org,
13. Li, H. & Vasarhelyi, M. A. (2024). Applying Large Language Models in Accounting: A Comparative Analysis of Different Methodologies and Off-the-Shelf Examples. Forthcoming in the Journal of Emerging Technologies in Accounting.
14. Loughran, T., & McDonald, B. (2011). When Is a Liability Not a Liability? Textual Analysis, Dictionaries, and 10-Ks. Journal of Finance, 66(1), 35–65.
15. Manning, F. & Schutze, H. (1999). Foundation of Statistical Natural Language Processing. MIT Press.
16. O’Brien, J.A. & Marakas, G.M. (2006). Management Information Systems. McGraw-Hill Irwin. 7th Ed.
17. Petter, S., William D., & Ephraim R. M. (2013). Information systems success: The quest for the independent variables, Journal of Management Information Systems, 29: 7–62.
18. Rogers, A., Gardner, M., & Augenstein, I. (2023). QA dataset explosion: A taxonomy of NLP resources for question answering and reading comprehension. ACM Computing Surveys, 55(10), 1–45.
19. Romney, M.B. & Steinbart, P.J. (2018). Accounting Information Systems. Pearson. 14th Ed.
20. Schweter, S. (2020). BERTurk - BERTurk Models for Turkish. Zenodo. https://doi.org/10.5281/zenodo.3770924
21. Street, D., Wilck, J., & Chism, Z. (2023). Six Principles for the Effective Use of ChatGPT and other Large Language Models in Accounting. CPA Journal, SSRN Scholarly Paper. NY, 1-20.
22. Urbach, N., Smolnik, S., & Riempp, G. (2010). Improving the Success of Employee Portals: A Causal and Performance-Based Analysis. ECIS 2010 Proceedings. 54.
23. Wong, M.F. (2024). The Impact of Large-Scale Language Models on the Future Development of Accounting. World Journal of Management Science. 2 (1), 58-62.
24. Wood, D., Akpan, M., & Allee, K.D. (2023). The ChatGPT Artificial Intelligence Chatbot: How well does it answer accounting assessment questions?. Issues in Accounting Education, 38 (4),1-28.