Deep Learning Based Classification of Turkish News Posts in Twitter

Social media platforms have become important news sources in recent years thanks to their increasing number of users and the ability to spread information much faster than traditional media. Using these platforms especially as news sources has brought the need of accessing news information easier an...

Full description

Saved in:
Bibliographic Details
Published in2021 6th International Conference on Computer Science and Engineering (UBMK) pp. 298 - 303
Main Authors Yolcu, Alper Beykan, Demirci, Sedef
Format Conference Proceeding
LanguageEnglish
Published IEEE 15.09.2021
Subjects
Blogs
Computer science
Deep learning
LSTM
Measurement
Media
news classification
Recurrent neural networks
RNN
Social networking (online)
Twitter
Online AccessGet full text

Cover

More Information
Summary:Social media platforms have become important news sources in recent years thanks to their increasing number of users and the ability to spread information much faster than traditional media. Using these platforms especially as news sources has brought the need of accessing news information easier and faster within the large amount and flow of data on these platforms. In this paper, a deep learning based approach has been proposed to classify Turkish news posts on Twitter automatically. In this regard, recurrent neural networks (RNN) and long short term memory (LSTM) which is a special type of RNN are used and the developed classifiers are evaluated in terms of different performance metrics. The results show that the achieved accuracy rates are reasonably high, despite the difficulty of classifying short tweets.
ISSN:2521-1641
DOI:10.1109/UBMK52708.2021.9558916