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

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