BİLİŞİM SİSTEMLERİ ARAŞTIRMA ALANINDAKİ GENİŞLETİLMİŞ GERÇEKLİK YAYINLARININ METİN MADENCİLİĞİ VE DOĞAL DİL İŞLEME (NLP) TEKNİKLERİ YOLUYLA ANALİZİ

Abstract

The aim of the study is to cluster and to classify the scientific papers regarding Extended Reality indexed in Web of Science database. To achieve this goal, Extended Reality related publications were located and gathered from the database. NLTK library was used for tokenization, stop words removal, and lemmatization operations. The TF-IDF vectorizer method in the Sklearn library was used to convert words to vector format. Then, the keywords of the publications were clustered using K-Means. The keywords in each cluster were searched throughout the abstract of each publication. The publication was labeled as the name of the cluster wherein the largest number of keywords matches the words in its abstract. Then, Support Vector Classifier, and Multinomial Naïve Bayes machine learning algorithms and Gated Recurrent Unit deep learning algorithms were conducted for classification. The results of deep learning and machine learning have been compared and this comparison yielded that the dataset is more suitable for deep learning in comparison to machine learning. Accuracy values are reported as 90.4%, 77.2%, and 99.8% for Support Vector Classifier, Multinomial Naïve Bayes, and Gated Recurrent Unit respectively. This study provides evidence that the GRU architecture is more effective than the classical machine learning algorithms.