Bilgisayar Bilimleri Alanındaki Türkçe Akademik Makalelerin Doğal Dil İşleme Teknikleri Kullanılarak Analizi

Öz

Bilimsel makaleler başvurudan yayına kadar kapsam, biçim ve kalite açısından titiz ve uzun bir süreçten geçer. Bu inceleme sürecine rağmen, yayınlar anlam bütünlüğünü tehlikeye atan hatalar içerebilir. Ancak anlatım bütünlüğü olan bir yayını bile okumak ve anlamak zaman alırken, bütünlüğü dikkate alınmamış bir yayının detaylarını incelemek daha da zorlaşmaktadır. Bu çalışmada, SCI-EXPANDED, ESCI ve TR Dizin'de taranan çeşitli dergilerde yayımlanan bilgisayar bilimleri alanındaki 492 tam metin Türkçe araştırma makalesi analiz edilmiştir. Çalışmanın amacı, belirlenen kriterlere göre incelenen makalelerin tüm bölümlerinin bütünlüğünü ortaya koymaktır. Genel değerlendirme sonucunda en yüksek puanı alan makale 84.900 puan ile 358 ID numaralı makale, en düşük puanı alan makale ise 34.733 puan ile 197 ID numaralı makale olmuştur. Sonuç olarak, makalelerin özet bölümlerinin çoğu kapsam, problem, amaç, yöntem, bulgular ve sonuç açısından kısmen veya büyük ölçüde eksiktir. Bu değerlendirme, bilimsel araştırma makalelerinin özet bölümlerinin etkili bir şekilde yazılmadığını göstermektedir.

Anahtar Kelimeler

• Doğal dil işleme
• Derin öğrenme
• Yapay zeka
• Araştırma makalesi

Analysis of Turkish Academic Papers in Computer Science Using Natural Language Processing Techniques

Abstract

Scientific articles undergo a rigorous and lengthy process from submission to publication in terms of scope, form, and quality. Despite this review process, publications may contain errors that compromise the integrity of their meaning. However, while it takes time to read and understand even a publication with narrative integrity, it becomes even more difficult to examine the details of a publication whose integrity has not been considered. In this study, 492 full-text Turkish research articles in the field of computer science published in various journals indexed in SCI-EXPANDED, ESCI and TR Index were analyzed. The aim of the study is to reveal the integrity of all sections of the articles analyzed according to the criteria determined. As a result of the general evaluation, the article with the highest score was the article with ID number 358 with 84.900 points, and the lowest was the article with ID number 197 with 34.733 points. In conclusion, most abstract sections of articles are partially or largely lacking in terms of scope, problem, purpose, method, results, and conclusion. This evaluation shows that abstract sections of scientific research papers are not written effectively.

Keywords

• Natural language processing
• deep learning
• artificiall intelligence
• research articles

References

1. Alsuhaibani M. Fine-Tuned Pegasus: Exploring the performance of the transformer-based model on a diverse text summarization dataset. 9th World Congress on Electrical Engineering and Computer Systems and Sciences (EECSS’23), August 03-05 2023, London.
2. BERT Extractive Summarizer. 2020; https://github.com/dmmiller612/bert-extractive-summarizer. (Access Date: 11.02.2025)
3. Campesato O. Natural language processing fundamentals for developers. Herndon: Mercury Learning and Information; 2021.
4. Chen YM., Lin P., Yeh EH., Yang SR., Lu R. CPBW: A change-point-detection and bag-of-words based mechanism utilizing smartphone triaxial accelerometer data for driver identification. IEEE Internet of Things Journal 2024; 11(18): 29766-29780.
5. Erhandı B., Text summarization with deep learning. Sakarya University Institute of Science and Technology, Master Thesis, Sakarya, Turkiye, 2020.
6. Feltrim VD., Pelizzoni JM., Teufel S., Das Graças Volpe Nunes M., Aluísio SM. Applying argumentative zoning in an automatic critiquer of academic writing. 17th Brazilian Symposium on Artificial Intelligence, September 29-Ocotber 1 2004, Sao Luis.
7. Gastel B., Day RA. How to write and publish a scientific paper. New York: Bloomsbury Publishing; 2022.
8. Jackson P., Moulnier I. Natural language processing for online applications: Text retrieval, extraction and categorization Chapter 1: Natural language processing. John Benjamins Publishing Company 2002; 1-17.

9. Karuna G., Akshith M., Dinesh PS., Vardhan BV., Bisht YS., Narsaiah MN. Automated abstractive text summarization using deep learning. 15th International Conference on Materials Processing and Characterization (ICMPC 2023), September 5- 8 2023, England.
10. Kemaloğlu Alagöz N. Automatic text summarization with deep learning. Süleyman Demirel University Institute of Science and Technology, PhD. Thesis, Isparta, Turkiye, 2022.
11. Kemik Doğal Dil İşleme Grubu 2020; http://www.kemik.yildiz.edu.tr/. (Access Date: 11.02.2025)
12. Lewis M., Liu Y., Goyal N., Ghazvininejad M., Mohamed A., Levy O., Stoyanov V., Zettlemoyer L. BART: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. arXiv preprint arXiv:1910.13461. 2020.
13. Mallik A., Kumar S. Word2Vec and LSTM based deep learning technique for context-free fake news detection. Multimedia Tools and Applications 2024; 83(1): 919-940.
14. Mcculloch WS., Pitts W. A logical calculus of the ideas immanent in nervous activity. Bulletin of Mathematical Biophysics 1943; 5: 115–133.
15. Minaee S., Kalchbrenner N., Cambria E., Nikzad N., Chenaghlu M., Gao J. Deep learning--based text classification: a comprehensive review. ACM computing surveys (CSUR) 2021; 54(3): 1-40.
16. Mwandau B. Investigating keystroke dynamics as a two-factor biometric security. Strathmore University, Faculty of Information Technology, PhD. Thesis, Nairobi, Kenya, 2018.
17. Raffel C., Shazeer N., Roberts A., Lee K., Narang S., Matena M., Zhou Y., Liu PJ. Exploring the limits of transfer learning with a unified text-to-text transformer. Journal of Machine Learning Research 2020; 21(140): 1-67.
18. Russel SJ., Norvig P. Artificial intelligence: A modern approach. New Jersey: Pearson Education Publishing; 2013.
19. Türkiye Bilimsel ve Teknolojik Araştırma Kurumu. 2000; https://trdizin.gov.tr. . (Access Date: 11.02.2025)
20. Shafiq N., Hamid I., Asif M., Nawaz Q., Aljuaid H., Ali H. Abstractive text summarization of low-resourced languages using deep learning. PeerJ Computer. Science 2023; 9: e1176.
21. Shaik T., Tao X., Li Y., Dann C., McDonald J., Redmond P., Galligan L. A review of the trends and challenges in adopting natural language processing methods for education feedback analysis. IEEE Access 2022; 10: 56720-56739.
22. Shopnil TA., Das A., Saha D. Automatic text summarization using deep learning methods. Authorea Preprints 2024.
23. Singh S., Mahmood A. The NLP cookbook: Modern recipes for transformer based deep learning architectures. IEEE Access 2021; 9: 68675–68702.
24. Sun G., Wang Z., Zhao J. Automatic text summarization using deep reinforcement learning and beyond. Information Technology and Control 2021; 50(3): 458-469.
25. Tahseen R., Omer U., Farooq MS., Adnan F. Text summarization techniques using natural language processing: A systematic literature Review. VFAST Transactions on Software Engineering 2021; 9(4): 102-108.
26. Teng K., Qiang B., Wang Y., Yang X., Wang Y., Wang C. Abstractive text summarization model based on BERT vectorization and bidirectional decoding. International Conference on Cyber Security, Artificial Intelligence, and Digital Economy (CSAIDE 2023), March 3-5 2023, China.
27. Teufel S. Argumentative zoning: information extraction from scientific text. University of Edinburgh, PhD. Thesis, Scotland, 1999.
28. Teufel S., Carletta J., Moens M. An annotation scheme for discourse-level argumentation in research articles. Ninth Conference of the European Chapter of the Association for Computational Linguistics, June 8-12 1999, 110-117, Norway.
29. Teufel S., Moens M. Discourse-level argumentation in scientific articles: Human and automatic annotation. In Proceedings of the ACL99 Workshop on Standards and Tools for Discourse Tagging 1999; 10: 977035-977051.
30. Vaswani A., Shazeer N., Parmar N., Uszkoreit J., Jones L., Gomez AN., Kaiser Ł., Polosukhin I. Attention is all you need. 31st International Conference on Neural Information Processing Systems, December 4 – 9 2017, Cambridge.
31. Veyssier L. Abstractive text summarization model in Keras. 2020; https://github.com/LaurentVeyssier/Abstractive-Text-Summarization-model-in-Keras. (Access Date: 11.02.2025)
32. Zhang J., Zhao Y., Saleh M., Liu P. Pegasus: Pre-training with extracted gap-sentences for abstractive summarization. 37th International Conference on Machine Learning, July 13-18 2020, Austria.
33. Zhou J., Ye Z., Zhang S., Geng Z., Han N., Yang T. Investigating response behavior through TF-IDF and Word2vec text analysis: A case study of PISA 2012 problem-solving process data. Heliyon 2024; 10(16): e35945.