Üniversite Bilgi Yönetim Sistemi Servis Destek Taleplerinin Konu Modelleme Tabanlı Analizi

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.