Doğal dil işleme kullanımı ile nesne tabanlı analiz ve kaynak kod değerlendirmesi

Software requirements include description of the features for the target system, and express the expectations of users. In analysis phase, requirements are transformed into easy-to-understand conceptual models that facilitate communication between stakeholders. Although creating conceptual model using requirements is mostly implemented manually by an analyst, the number of models that automate this process, has increased recently. Most of the models and tools are developed to analyze requirements in English, and there is no study for agglutinative languages such as Turkish or Finnish. In this thesis, we propose an automatic concept identification model which transforms Turkish requirements into Unified Modelling Language (UML) class diagram to ease the work of individuals in the software team and reduce the cost of software projects. The proposed thesis is based on the Natural Language Processing (NLP) techniques and a new rule-set containing twenty-six rules is created to find out Object Oriented (OO) design elements from requirements. Since there is no publicly available dataset on the online repositories, we have created a well-defined dataset containing ten software requirements in Turkish and made it publicly available on GitHub to be used by other researchers. We also proposed a novel evaluation model based on Analytical Hierarchy Process (AHP) that considers the experts' views and calculate the performance of the overall system as enough successful. We can state that this result is promising for the future works in this domain.