Classification of Turkishtweet emotions by n- stage latent dirichlet allocation
Künye
Güven, Z:A., Diri, B. & Çakaloğlu, T. (2018). Classification of TurkishTweet emotions by n- stage Latent Dirichlet Allocation. 2018 Electric Electronics, Computer Science, Biomedical Engineerings' Meeting, EBBT 2018, 1-4, 137380. https://doi.org/10.1109/EBBT.2018.8391454Özet
The classification of the emotions contained in the social media is of great importance in terms of its use in related fields such as media as well as developing technology. The Latent Dirichlet Allocation (LDA), a topic modeling algorithm, was used to determine which emotions the tweets on Twitter had in the study. Dataset consists of angry, fear, happy, sadness and surprise, 5 emotions and 4000 tweets. Zemberek, Snowball and the first 5 letter root extraction methods are used to create the model. The generated models were tested with the n-stage GDA method we developed and compared with the GDA. For the 5 classes of normal GDA method, the highest 60.4% success was achieved; 70.5% for 2-stage GDA and 76.4% for 3-stage GDA. © 2018 IEEE.