Spring

Mobile devices have become a part of our very daily lives. In the last two decades a lot of thing has been changed in the field of mobile communications. The last and very exciting development is the 5G technology which is better and improved version of the LTE as well as supporting green technology. 5G technology proposes a diferent architecture than usual such as new antenna designs, working with higher frequencies and Cloud Radio Access Network Architectures.

I propose a categorization technique for topic modeling in Twitter, which train models using Latent Dirichlet Allocation (LDA) on datasets consisting of tweets and their responses. This categorization technique is designed for the telecommunication companies in this project and aims to increase customer satisfaction. 

In this project, it is aimed to implement a named entity recognition tool for Turkish based on the thesis that Hakan Demir conducted in 2014. A named entity recognition tool is a program which seeks to locate and classify named entities in text into pre-defined categories such as the names of persons, organizations, locations, expressions of times, quantities, monetary values, percentages, etc. Considering it is a morphologically rich language, Turkish texts were tried to be classified. Turkish is considered so since it is an agglutinative and inflectional language.

The goal of this research is to investigate effects of image captions in text summarization. Most of the news contain additional information such as images, image captions and titles in the body part, however text summarization only studies text of the document. It is shown that image captions and titles of texts can improve ROUGE score on text summarization task. However, I showed that image captions increase quality of the summarization in unsupervised models, too. Recent papers about text summarization study multi-document text summarization.