Research Article
BibTex RIS Cite

Topic Modelling Based Analysis of Service Support Requests on University Information Management

Year 2020, Ejosat Special Issue 2020 (HORA), 389 - 397, 15.08.2020
https://doi.org/10.31590/ejosat.780642

Abstract

University Information Management System (ÜBYS) is being developed within our institution (İzmir Kâtip Çelebi University) and various institutions outside of our own institution use different components under UBYS. Various errors may arise in the process in line with the size of the software and arise from the nature of the software development, and various improvements are requested regardless of the errors that occur. In this study, we present a topic modelling based analysis on service support requests provided by different institutions and people on university information manament system. Topic models that arise because of topic modelling of service support requests can be regarded as key concepts derived from the data collection. The issues raised are expressed as a collection of terms, but are of great value to summarize most of the text documents (UBYS service support requests). Moreover, hidden patterns and semantics in the data are revealed. Topic modeling helps us understand large collections of unstructured text bodies, organize and present information. Latent Dirichlet allocation, which is used for topic modeling, is an important method of topic modeling in which each document is considered a collection of topics and each word in the document corresponds to one of the topics. Therefore, when a document (text data) is given, LDA clusters each subject group into subject groups with a set of words that best describe that group based on the document. In this study, four components, namely, Student Information System (AIS), Personnel Information System (HRM), Electronic Document Management System (ERMS) and Scientific Research Projects (SRP) within the body of information system are taken into account. Analysis of the service support requests of these components has been carried out by latent Dirichlet allocation, which is one of the most basic methods for topic modeling. The study presents the main results and visualizations obtained by the latent Dirichlet allocation method.

References

  • Schwarz, C. (2018). ldagibbs: A command for topic modeling in Stata using latent Dirichlet allocation. The Stata Journal, 18(1), 101-117.
  • Sun, M., & Zheng, H. (2018, September). Topic Detection for Post Bar Based on LDA Model. In International Conference of Pioneering Computer Scientists, Engineers and Educators (pp. 136-149). Springer, Singapore.
  • Shah, A. H. (2019). How episodic frames gave way to thematic frames over time: A topic modeling study of the Indian media’s reporting of rape post the 2012 Delhi gang-rape. Poetics, 72, 54-69.
  • Karami, A., Ghasemi, M., Sen, S., Moraes, M. F., & Shah, V. (2019). Exploring diseases and syndromes in neurology case reports from 1955 to 2017 with text mining. Computers in biology and medicine, 109, 322-332.
  • Onan, A., Bulut, H., & Korukoglu, S. (2017). An improved ant algorithm with LDA-based representation for text document clustering. Journal of Information Science, 43(2), 275-292.
  • Blei, D. M., Ng, A. Y., & Jordan, M. I. (2003). Latent dirichlet allocation. Journal of machine Learning research, 3(Jan), 993-1022.
  • Agrawal, A., Fu, W., & Menzies, T. (2018). What is wrong with topic modeling? and how to fix it using search-based software engineering. Information and Software Technology, 98, 74-88.
  • Blei, D. M., Ng, A. Y., & Jordan, M. I. (2002). Latent dirichlet allocation. In Advances in neural information processing systems (pp. 601-608).
  • D'Urso, P., & Leski, J. M. (2019). Fuzzy clustering of fuzzy data based on robust loss functions and ordered weighted averaging. Fuzzy Sets and Systems, 389, 1-28.
  • Ekinci, E., Omurca, S. İ., KIRIK, E., & TAŞÇI, Ş. Tıp Veri Kümesi için Gizli Dirichlet Ayrımı. Dokuz Eylül Üniversitesi Mühendislik Fakültesi Fen ve Mühendislik Dergisi, 22(64), 67-80.
  • 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.
  • Onan, A. (2017). Türkçe Twitter Mesajlarında Gizli Dirichlet Tahsisine Dayalı Duygu Analizi. Akademik Bilişim, 8-10.
  • Karami, A., Gangopadhyay, A., Zhou, B., & Karrazi, H. (2015, August). Flatm: A fuzzy logic approach topic model for medical documents. In 2015 Annual Conference of the North American Fuzzy Information Processing Society (NAFIPS) held jointly with 2015 5th World Conference on Soft Computing (WConSC) (pp. 1-6). IEEE.
  • Bagheri, A., Saraee, M., & De Jong, F. (2013). Care more about customers: Unsupervised domain-independent aspect detection for sentiment analysis of customer reviews. Knowledge-Based Systems, 52, 201-213.
  • Wang, T., Cai, Y., Leung, H. F., Lau, R. Y., Li, Q., & Min, H. (2014). Product aspect extraction supervised with online domain knowledge. Knowledge-Based Systems, 71, 86-100.
  • Zheng, X., Lin, Z., Wang, X., Lin, K. J., & Song, M. (2014). Incorporating appraisal expression patterns into topic modeling for aspect and sentiment word identification. Knowledge-Based Systems, 61, 29-47.
  • Jo, Y., & Oh, A. H. (2011, February). Aspect and sentiment unification model for online review analysis. In Proceedings of the fourth ACM international conference on Web search and data mining (pp. 815-824).
  • Li, F., Huang, M., & Zhu, X. (2010, July). Sentiment analysis with global topics and local dependency. In Twenty-Fourth AAAI Conference on Artificial Intelligence.
  • Xianghua, F., Guo, L., Yanyan, G., & Zhiqiang, W. (2013). Multi-aspect sentiment analysis for Chinese online social reviews based on topic modeling and HowNet lexicon. Knowledge-Based Systems, 37, 186-195.
  • Onan, A., Atik, E., & Yalçın, A. (2020). Machine learning approach for automatic categorization of service support requests on university information management system. In Proceedings of the Second International Conference on Intelligent and Fuzzy Systems (pp. 1-7).
  • Řehůřek, R., & Sojka, P. (2011). Gensim—statistical semantics in python. Retrieved from genism. org.

Üniversite Bilgi Yönetim Sistemi Servis Destek Taleplerinin Konu Modelleme Tabanlı Analizi

Year 2020, Ejosat Special Issue 2020 (HORA), 389 - 397, 15.08.2020
https://doi.org/10.31590/ejosat.780642

Abstract

Kurumumuz (İzmir Kâtip Çelebi Üniversitesi) bünyesinde Üniversite Bilgi Yönetim Sistemi(ÜBYS) geliştirilmekte ve kendi kurumumuz dışında çeşitli kurumlar tarafından da ÜBYS altındaki farklı bileşenler kullanılmaktadır. Yazılım geliştirmenin doğasından kaynaklanan ve yazılımın büyüklüğü ile doğru orantılı olarak süreç içerisinde çeşitli hatalar oluşabilmekte, oluşan hatalardan bağımsız olarak çeşitli geliştirmelerin yapılması istenmektedir. Bu çalışmada, Üniversite Bilgi Yönetim Sistemi(ÜBYS) geliştirilirken farklı kurum ve bu kurumlardaki kişilerden gelen hata bildirimi ve isteklerin konu modelleme yöntemlerine dayalı analizi gerçekleştirilmektedir. Servis destek taleplerinin konu modellemesi sonucunda ortaya çıkan konu modelleri ÜBYS servis destek veri koleksiyonundan bulunup çıkartılan anahtar kavramlar olarak adlandırılabilirler. Çıkartılan konular bir terim koleksiyonu olarak ifade edilmekle birlikte metin dokümanlarının (ÜBYS servis destek taleplerinin) büyük bir kısmını özetlemek için çok değerlidir. Dahası verilerdeki gizlikalmış kalıplar ve anlamsallık ortaya çıkarılmış olmaktadır. Büyük boyutlu dokümanlardan denetimsiz bir şekilde gizli yapıyı keşfeden konu modeleme güçlü bir yöntemdir. Konu modelleme yapılandırılmamış (unstructured) metin gövdelerinin büyük koleksiyonlarını anlamamıza, bilgileri düzenlememize ve sunmamıza yardımcı olur. Konu modellemesi için kullanılan gizli Dirichlet tahsisi (latent Dirichlet allocation), her belgenin bir konu koleksiyonu olarak kabul edildiği ve belgedeki her kelimenin konulardan birine karşılık geldiği bir konu modelleme yöntemidir. Dolayısıyla, bir belge(metin verisi) verildiğinde LDA, belgeyi temel alarak her konu grubunu o grubu en iyi açıklayan bir dizi kelimenin olduğu konu gruplarına kümeler. Bu çalışmada ÜBYS bünyesindeki Öğrenci Bilgi Sistemi (AIS), Personel Bilgi Sistemi (HRM), Elektronik Belge Yönetim Sistemi(ERMS) ve Bilimsel Araştırma Projeleri (SRP) olmak üzere dört bileşen ele alınmıştır. Bu bileşenlere ait servis destek taleplerinin konu modellemesi için en temel yöntemlerden biri olan gizli Dirichlet tahsisi ile analizi gerçekleştirilmiştir. Bileşenlerden elde edilen metin belgeleri üzerinde temel konulara ve konulara ilişkin temel anahtar sözcüklere ilişkin analiz ve görseller sunulmaktadır.

References

  • Schwarz, C. (2018). ldagibbs: A command for topic modeling in Stata using latent Dirichlet allocation. The Stata Journal, 18(1), 101-117.
  • Sun, M., & Zheng, H. (2018, September). Topic Detection for Post Bar Based on LDA Model. In International Conference of Pioneering Computer Scientists, Engineers and Educators (pp. 136-149). Springer, Singapore.
  • Shah, A. H. (2019). How episodic frames gave way to thematic frames over time: A topic modeling study of the Indian media’s reporting of rape post the 2012 Delhi gang-rape. Poetics, 72, 54-69.
  • Karami, A., Ghasemi, M., Sen, S., Moraes, M. F., & Shah, V. (2019). Exploring diseases and syndromes in neurology case reports from 1955 to 2017 with text mining. Computers in biology and medicine, 109, 322-332.
  • Onan, A., Bulut, H., & Korukoglu, S. (2017). An improved ant algorithm with LDA-based representation for text document clustering. Journal of Information Science, 43(2), 275-292.
  • Blei, D. M., Ng, A. Y., & Jordan, M. I. (2003). Latent dirichlet allocation. Journal of machine Learning research, 3(Jan), 993-1022.
  • Agrawal, A., Fu, W., & Menzies, T. (2018). What is wrong with topic modeling? and how to fix it using search-based software engineering. Information and Software Technology, 98, 74-88.
  • Blei, D. M., Ng, A. Y., & Jordan, M. I. (2002). Latent dirichlet allocation. In Advances in neural information processing systems (pp. 601-608).
  • D'Urso, P., & Leski, J. M. (2019). Fuzzy clustering of fuzzy data based on robust loss functions and ordered weighted averaging. Fuzzy Sets and Systems, 389, 1-28.
  • Ekinci, E., Omurca, S. İ., KIRIK, E., & TAŞÇI, Ş. Tıp Veri Kümesi için Gizli Dirichlet Ayrımı. Dokuz Eylül Üniversitesi Mühendislik Fakültesi Fen ve Mühendislik Dergisi, 22(64), 67-80.
  • 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.
  • Onan, A. (2017). Türkçe Twitter Mesajlarında Gizli Dirichlet Tahsisine Dayalı Duygu Analizi. Akademik Bilişim, 8-10.
  • Karami, A., Gangopadhyay, A., Zhou, B., & Karrazi, H. (2015, August). Flatm: A fuzzy logic approach topic model for medical documents. In 2015 Annual Conference of the North American Fuzzy Information Processing Society (NAFIPS) held jointly with 2015 5th World Conference on Soft Computing (WConSC) (pp. 1-6). IEEE.
  • Bagheri, A., Saraee, M., & De Jong, F. (2013). Care more about customers: Unsupervised domain-independent aspect detection for sentiment analysis of customer reviews. Knowledge-Based Systems, 52, 201-213.
  • Wang, T., Cai, Y., Leung, H. F., Lau, R. Y., Li, Q., & Min, H. (2014). Product aspect extraction supervised with online domain knowledge. Knowledge-Based Systems, 71, 86-100.
  • Zheng, X., Lin, Z., Wang, X., Lin, K. J., & Song, M. (2014). Incorporating appraisal expression patterns into topic modeling for aspect and sentiment word identification. Knowledge-Based Systems, 61, 29-47.
  • Jo, Y., & Oh, A. H. (2011, February). Aspect and sentiment unification model for online review analysis. In Proceedings of the fourth ACM international conference on Web search and data mining (pp. 815-824).
  • Li, F., Huang, M., & Zhu, X. (2010, July). Sentiment analysis with global topics and local dependency. In Twenty-Fourth AAAI Conference on Artificial Intelligence.
  • Xianghua, F., Guo, L., Yanyan, G., & Zhiqiang, W. (2013). Multi-aspect sentiment analysis for Chinese online social reviews based on topic modeling and HowNet lexicon. Knowledge-Based Systems, 37, 186-195.
  • Onan, A., Atik, E., & Yalçın, A. (2020). Machine learning approach for automatic categorization of service support requests on university information management system. In Proceedings of the Second International Conference on Intelligent and Fuzzy Systems (pp. 1-7).
  • Řehůřek, R., & Sojka, P. (2011). Gensim—statistical semantics in python. Retrieved from genism. org.
There are 21 citations in total.

Details

Primary Language Turkish
Subjects Engineering
Journal Section Articles
Authors

Aytuğ Onan This is me 0000-0002-9434-5880

Adnan Yalçın This is me

Erdem Atik This is me

Publication Date August 15, 2020
Published in Issue Year 2020 Ejosat Special Issue 2020 (HORA)

Cite

APA Onan, A., Yalçın, A., & Atik, E. (2020). Üniversite Bilgi Yönetim Sistemi Servis Destek Taleplerinin Konu Modelleme Tabanlı Analizi. Avrupa Bilim Ve Teknoloji Dergisi389-397. https://doi.org/10.31590/ejosat.780642