Journals / Konya Journal of Engineering Sciences / 2023 / Cilt: 11 Sayı: 2

SENTIMENT CLASSIFICATION ON TURKISH TWEETS ABOUT COVID-19 USING LSTM NETWORK

COVID-19 Hakkındaki Türkçe Tweetlerde LSTM Ağı Kullanılarak Duygu Sınıflandırması

Pages
341–353
Publication Date
2023-06-01
DOI
—
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

Results of these experiments have shown that CNN-LSTM model outperforms other machine learning algorithms which are used in this study in both binary classification and multi-class classification tasks.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:As Covid-19 pandemic affected everyone in various aspects, people have been expressing their opinions on these aspects mostly on social media platforms because of the pandemic.
📊
Key Findings & Data:In this study, Turkish tweets on Covid-19 topic were collected from March 2020 to January 2021 and labelled as positive, negative, or neutral in terms of sentiment using BERT which is a pre-trained text classifier model.
💡
Conclusion & Impact:Results of these experiments have shown that CNN-LSTM model outperforms other machine learning algorithms which are used in this study in both binary classification and multi-class classification tasks.
🔬Design:Modeling & Simulation
📍Scope:2020 Verileri
⚙️Variables:Duygu Analizi · Türkçe Twitter · Sınıflandırma

Abstract

As Covid-19 pandemic affected everyone in various aspects, people have been expressing their opinions on these aspects mostly on social media platforms because of the pandemic. These opinions play a crucial role in understanding the sentiments towards the pandemic. In this study, Turkish tweets on Covid-19 topic were collected from March 2020 to January 2021 and labelled as positive, negative, or neutral in terms of sentiment using BERT which is a pre-trained text classifier model. Using this labelled dataset, a set of experiments were carried out with SVM, Naive Bayes, K-Nearest Neighbors, and CNN-LSTM model machine learning algorithms for binary and multi-class classification tasks. Results of these experiments have shown that CNN-LSTM model outperforms other machine learning algorithms which are used in this study in both binary classification and multi-class classification tasks.

Özet

Covid-19 pandemisi herkesi çeşitli yönlerden etkilediğinden, pandemi nedeniyle insanlar daha çok sosyal medya platformlarında bu yönlere ilişkin görüşlerini dile getiriyorlar. Bu görüşler, pandemiye yönelik duyguları anlamada çok önemli bir rol oynamaktadır. Bu çalışmada, 2020'den 2021'e kadar Covid-19 konulu Türkçe tweet'ler toplanmış ve önceden eğitilmiş bir metin sınıflandırıcı modeli kullanılarak duygu açısından olumlu, olumsuz veya nötr olarak etiketlenmiştir. Bu etiketli veri kümesini kullanarak, ikili ve çok sınıflı sınıflandırma görevleri için SVM, Naive Bayes, K-Nearest Neighbors ve CNN-LSTM model makine öğrenme algoritmaları için bir dizi deney gerçekleştirilmiştir.

🔖

Cite This Article

ÇATALTAŞ, M., ÜSTÜNEL, B., BAYKAN, N. A. (2023). SENTIMENT CLASSIFICATION ON TURKISH TWEETS ABOUT COVID-19 USING LSTM NETWORK. Konya Journal of Engineering Sciences, Cilt: 11 Sayı: 2, 341–353. https://ajindex.com/articles/937912

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (13)

  1. H. Abid, J. Mohd, and V. Raju, "Effects of COVID 19 pandemic in daily life," Current Medicine Research and Practice, vol. 10, no. 2, pp. 78-79, 2020
  2. B. Gokulakrishnan, P. Priyanthan, T. Ragavan, N. Prasath, and A. Perera, "Opinion mining and sentiment analysis on a twitter data stream," in International conference on advances in ICT for emerging regions (ICTer2012), 2012: IEEE, pp. 182-188
  3. B. Özyurt and M. A. Akçayol, "Fikir Madenciliği ve Duygu Analizi, Yaklaşimlar, Yöntemler Üzerine Bir Araştirma," Selçuk Üniversitesi Mühendislik, Bilim ve Teknoloji Dergisi, vol. 6, no. 4, pp. 668-693, 2018
  4. W. Medhat, A. Hassan, and H. Korashy, "Sentiment analysis algorithms and applications: A survey," Ain Shams Engineering Journal, vol. 5, no. 4, pp. 1093-1113, 2014
  5. A. Singh, N. Thakur, and A. Sharma, "A review of supervised machine learning algorithms," in 2016 3rd International Conference on Computing for Sustainable Global Development (INDIACom), 2016: IEEE, pp. 1310-1315
  6. A. Öztürk, Ü. Durak, and F. Badilli, "Twitter Verilerinden Doğal Dil Işleme Ve Makine Öğrenmesi Ile Hastalik Tespiti," Konya Mühendislik Bilimleri Dergisi, vol. 8, no. 4, pp. 839-852, 2020
  7. H. Çetiner, "Multi-Label Text Analysis With A CNN And LSTM Based Hybrid Deep Learning Model," Adıyaman Üniversitesi Mühendislik Bilimleri Dergisi, vol. 9, no. 17, pp. 15-16, 2022
  8. A. H. Alamoodi et al., "Sentiment analysis and its applications in fighting COVID-19 and infectious diseases: A systematic review," Expert systems with applications, vol. 167, p. 114155, 2021
  9. C. R. Machuca, C. Gallardo, and R. M. Toasa, "Twitter sentiment analysis on coronavirus: Machine learning approach," in Journal of Physics: Conference Series, 2021, vol. 1828, no. 1: IOP Publishing, p. 012104
  10. L. Nemes and A. Kiss, "Social media sentiment analysis based on COVID-19," Journal of Information and Telecommunication, vol. 5, no. 1, pp. 1-15, 2021
  11. Ö. Çoban, B. Özyer, and G. T. Özyer, "Sentiment analysis for Turkish Twitter feeds," in 2015 23nd Signal Processing and Communications Applications Conference (SIU), 2015: IEEE, pp. 2388-2391
  12. Z. A. Guven, "Comparison of BERT models and machine learning methods for sentiment analysis on Turkish tweets," in 2021 6th International Conference on Computer Science and Engineering (UBMK), 2021: IEEE, pp. 98-101
  13. Y. E. Karaca and S. Aslan, "Sentiment Analysis of Covid-19 Tweets by using LSTM Learning Model," Computer Science, no. Special,