Clustering academic texts using natural language processing

Today, access to data has become extremely easy. In order to use these data efficiently, it is necessary to categorize the data according to the required properties. While doing research in the academic field, text-based data such as articles, papers or thesis studies are generally used. Categorizing these data in order to reach the needed information in a short time provides great convenience. Natural language processing and machine learning methods are used for the categorization of text-based data. Natural language processing is a field of linguistics, artificial intelligence and computer science that deals with the interaction between human languages (natural language) and computers. It studies the usage of computers in understanding, analysing and manipulating the natural language texts and natural speech. In this thesis, clustering was done on academic texts using natural language processing techniques. With frequency-based and neural network-based text representation methods, the results from different clustering algorithms were compared and analyzed.