Classification of Turkish News Content by Deep Learning Based LSTM Using Fasttext Model
Gözde Nergız, Yaşar SAFALI, Erdinç Avaroğlu, S.S. Erdogan · 2019 International Artificial Intelligence and Data Processing Symposium (IDAP) · 2019
With the increase in the rate of use of the Internet, the number of content produced has increased. Texture classification allows these categorized content to be automatically categorized. In this study, a special type of repetitive artificial neural networks(RNN) using the deep learning based Fasttext model, LSTM (Long-Short Term Memory) was used to classify the news texts. Fasttext, Word2vec and Doc2vec models are used to classify data on the data set and the success rates are compared. LSTM is used to classify the news data on the Fasttext model which gives the most successful result.