A Deep Learning Approach to Sentiment Analysis in Turkish

Ciftci B., APAYDIN M. S.

International Conference on Artificial Intelligence and Data Processing (IDAP), Malatya, Türkiye, 28 - 30 Eylül 2018 identifier

  • Yayın Türü: Bildiri / Tam Metin Bildiri
  • Basıldığı Şehir: Malatya
  • Basıldığı Ülke: Türkiye
  • Acıbadem Mehmet Ali Aydınlar Üniversitesi Adresli: Hayır

Özet

This study proposes using deep learning for sentiment analysis in Turkish. Traditional machine learning methods such as logistic regression or Naive Bayes are often applied to this problem however their applicability is limited since they use bag of -words model which does not take into account the order of the words in a sentence. In this study we compare these approaches with a modern technique called recurrent neural networks using LSTM units on a dataset crawled from Turkish shopping and movie websites. Our results show that RNN based approaches improve the classification accuracies.