Türkiye’de Yönetim Bilişim Sistemleri Alanında Yapılan Lisansüstü Tezlerin LDA Algoritması ile Konu Modellemesi

Yıl 2025, Cilt: 7 Sayı: 1, 1 - 13, 30.06.2025

Göktuğ İlisu , Nursal Arıcı

Öz

Yönetim Bilişim Sistemleri, işletmelerin ve kurumların stratejik, yönetsel ve operasyonel düzeylerdeki bilgi ihtiyaçlarını karşılamak için bilgi teknolojisi çözümlerini ve iş süreçlerini entegre etmeye odaklanan bir bilim alanıdır. Bu yönüyle bilgisayar bilimi, yönetim bilimi, istatistik, organizasyon teorisi, karar teorisi gibi çeşitli referans disiplinlerden beslenen çok disiplinli bir araştırma alanıdır. Bu çalışmanın temel amacı, Yönetim Bilişim Sistemleri bilim alanının Türkiye’deki lisansüstü tez konularına yansımalarını ve gelişimini incelemektir. Bu amaçla, 2002-2023 yılları arasında Yönetim Bilişim Sistemleri alanında hazırlanan ve YÖK Ulusal Tez Merkezi web sitesi üzerinden erişilebilen 1070 lisansüstü tez (Yüksek Lisans-f: 951 ve Doktora-f: 119) inceleme kapsamına alınarak LDA algoritmasıyla konu modellemesi gerçekleştirilmiştir. Konu modellemesinde kullanılan veri seti, lisansüstü tezlerin İngilizce özetleridir. Tez özetlerine öncelikle metin ön işleme ve kök çözümlemesi uygulanmıştır. Ortaya çıkan tüm kelimeler iç içe listelere dönüştürülüp LDA algoritması uygulanarak konu modelleri elde edilmiştir. Veri görselleştirme ile kelime bulutları, konu kümeleri, kelime sıklık histogramları ve belge- konu dağılımları oluşturulmuştur. Konu modellerinde çoğunlukla “data”, “model”, “research”, “technology”, “system” kelimelerinin yer aldığı tespit edilmiştir.

Anahtar Kelimeler

Yönetim bilişim sistemleri , konu modelleme , gizli dirichlet tahsisi algoritması

Topic Modelling of Postgraduate Theses in the Field of Management Information Systems in Turkey with LDA Algorithm

Öz

Management Information Systems is a branch of science that deals with integrating information technology solutions and business processes in order to meet the information requirements of businesses and organisations at strategic, managerial and operational levels. In this respect, it is a multidisciplinary research field that draws upon a number of different disciplines, including computer science, management science, statistics, organisation theory and decision theory. The primary objective of this study is to investigate the reflections and improvement of the field of Management Information Systems as evidenced by graduate thesis topics in Turkey. To this end, 1,070 graduate theses (951 MSc-f and 119 PhD-f) prepared in the field of Management Information Systems between 2002 and 2023 and accessible via the YÖK National Thesis Centre website were included in the scope of the study. Topic modelling was performed with the LDA algorithm. The data set employed in the topic modelling process comprised the English abstracts of graduate theses. The thesis abstracts were subjected to text preprocessing and stemming. The resulting words were converted into nested lists and topic models were obtained by applying the LDA algorithm. Data visualisation was employed to create word clouds, topic clusters, word frequency histograms and document-topic distributions. It was established that the terms "data," "model," "research," "technology," and "system" were predominantly incorporated into the topic models.

Anahtar Kelimeler

Management information systems , topic modelling , latent dirichlet allocation algorithm

Kaynakça

• [1] Baskerville, R. L., & Myers, M. D. (2002), “Information Systems as a Reference Discipline”. MIS Quarterly, 26(1), 1–14. https://doi.org/10.2307/4132338
• [2] Laudon, K. & Laudon, J. (2006), “Management Information Systems: Managing the Digital Firm”, 9th ed. Prentice Hall.
• [3] Berry, M. W., & Castellanos, M. (2007). “Survey of Text Mining: Clustering”, Classification, and Retrieval.
• [4] O’Mara-Eves, A., Thomas, J., McNaught, J. et al. “Using text mining for study identification in systematic reviews: a systematic review of current approaches”, Syst Rev 4, 5 (2015). https://doi.org/10.1186/2046-4053-4-5
• [5] Peersman, C., Edwards, M., Williams, E. & Rashid, A. (2022), “A Survey of Relevant Text Mining Technology”, 10.48550/arXiv.2211.15784.
• [6] Parlak, B., & Uysal, A. K. (2015, May). Classification of medical documents according to diseases. In 2015 23nd signal processing and communications applications conference (siu) (pp. 1635-1638). IEEE.
• [7] Kowsari, K., Meimandi, K. J., Heidarysafa, M., Mendu, S., Barnes, L., Brown, D. (2019), “Text Classification Algorithms: A Survey”, Information 2019(10), 150; doi:10.3390/info10040150.
• [8] Liang, H., Sun, X., Sun, Y., Gao, Y. (2017), “Text feature extraction based on deep learning: a review”, Liang et al. EURASIP Journal on Wireless Communications and Networking, (2017)211. doi: 10.1186/s13638-017-0993-1.
• [9] Cavnar, W. B., & Trenkle, J. M. (1994, April), “N-gram-based text categorization”, In Proceedings of SDAIR-94, 3rd annual symposium on document analysis and information retrieval (Vol. 161175, p. 14).
• [10] Biricik, G., Diri, B., Sönmez, A.C. (2012), “Abstract feature extraction for text classification”, Turk J Elec Eng & Comp Sci, Vol.20, No. Sup.1, 2012, TÜBİTAK doi:10.3906/elk-1102-1015.
• [11] Sakai, T., & Sparck-Jones, K. (2001, September), “Generic summaries for indexing in information retrieval”, In Proceedings of the 24th annual international ACM SIGIR conference on Research and development in information retrieval, 190-198.
• [12] Vayansky, I & Kumar, S. (2020), “A review of topic modeling methods”, Information Systems, 94. 101582. 10.1016/j.is.2020.101582.
• [13] Jurafsky, D., & Martin, J. H. (2000), “Speech and Language Processing: An Introduction to Natural Language Processing”, Computational Linguistics, and Speech Recognition.
• [14] Garoufallou, E., & Gaitanou, P. (2021), “Big data: opportunities and challenges in libraries, a systematic literature review”, College & Research Libraries, 82(3), 410.
• [15] Alghamdi, R., & Alfalqi, K. (2015), “A survey of topic modeling in text mining”, Int. J. Adv. Comput. Sci. Appl. (IJACSA), 6(1).
• [16] Blei, D. M., Ng, A. Y., & Jordan, M. I. (2003), “Latent dirichlet allocation”, Journal of machine Learning research, 3(Jan), 993-1022.
• [17] Onan, A., Korukoglu, S., & Bulut, H. (2016), “LDA-based topic modelling in text sentiment classification: An empirical analysis”, Int. J. Comput. Linguistics Appl., 7(1), 101-119.
• [18] Kuang, D., Choo, J., & Park, H. (2015), “Nonnegative matrix factorization for interactive topic modeling and document clustering”, Partitional clustering algorithms, 215-243.
• [19] Sievert, C., & Shirley, K. (2014). "LDAvis: A method for visualizing and interpreting topics", Proceedings of the Workshop on Interactive Language Learning, Visualization, and Interfaces.
• [20] Hasan, M., Rahman, A., Karim, M. R., Khan, M. S. I., & Islam, M. J. (2021), “Normalized approach to find optimal number of topics in Latent Dirichlet Allocation (LDA)”, In Proceedings of International Conference on Trends in Computational and Cognitive Engineering: Proceedings of TCCE 2020, 341-354. Springer Singapore.
• [21] Çallı, L., Çallı, F., & Alma Çallı, B. (2021), “Yönetim Bilişim Sistemleri Disiplininde Hazırlanan Lisansüstü Tezlerin Gizli Dirichlet Ayrımı Algoritmasıyla Konu Modellemesi”, MANAS Sosyal Araştırmalar Dergisi, 10(4), 2355-2372. https://doi.org/10.33206/mjss.894809
• [22] Parlina, A., & Kusumarani, R. (2023), “A Latent Dirichlet Allocation-Based Bibliometric Exploration of Top-3 Journals in Management Information Systems”, Jurnal Studi Komunikasi dan Media, 27(1), 77-92.
• [23] Özköse, H., & Gencer, C. T. (2017). “Bibliometric analysis and mapping of management information systems field”, Gazi University Journal of Science, 30(4), 356-371.
• [24] Internet: YÖK National Thesis Center Web Site. [Accessed: 02/05/2024.] https://tez.yok.gov.tr/UlusalTezMerkezi/
• [25] Sievert, C., & Shirley, K. (2014), "LDAvis: A method for visualizing and interpreting topics." Proceedings of the Workshop on Interactive Language Learning, Visualization, and Interfaces.