Research Article
BibTex RIS Cite

Tweetlerin Duygu Analizi İçin Hibrit Bir Yaklaşım

Year 2023, Volume: 6 Issue: 1, 57 - 68, 17.12.2023
https://doi.org/10.57244/dfbd.1314901

Abstract

Sosyal medyada ifade edilen görüşler, çeşitli işletmeler için her zaman dikkate alınan ve faydalı bir kaynak olmuştur. Duygu analizi, kullanıcılar tarafından oluşturulan içeriği belirli kutuplara (pozitif, negatif) etkin bir şekilde sınıflandırmayı ifade eden genel bir terimdir. Duyguların sınıflandırma ve analizini gerçekleştirmek için çeşitli araçlar ve teknikler bulunmaktadır. Bunlar, veri üzerinde ön işleme adımları tamamlandıktan sonra hedef grubu sınıflandıran denetimli makine öğrenimi tekniklerini içermektedir. Hibrit araçlar, makine öğrenimi ve sözlük tabanlı algoritmaların birleşimini kullanarak, işaretlenmiş verilere dayalı olarak sınıflandırma yapar. Bu makalede, duyguların analizinde SVM algoritmasını Weka adında açık kaynaklı bir yazılım ile birlikte kullandık. İki önceden kategorize edilmiş tweet veri seti kullanıldı. SVM algoritmasının performansı, analitik metrikler yardımıyla değerlendirildi.

References

  • Appel, O., Chiclana, F., Carter, J., & Fujita, H. (2016). A hybrid approach to sentiment analysis. In IEEE Congress on Evolutionary Computation.
  • Beleveslis, D., Tjortjis, C., Psaradelis, D., & Nikoglou, D. (2019). A Hybrid Method For Sentiment Analysis Of Election Related Tweets. In 4th SouthEast Europe Design Automation, Computer Engineering, Computer Networks and Social Media Conference (SEEDA-CECNSM).
  • Çelik, E., Dal, D.., & Aydın, T. (2021). Duygu Analizi İçin Veri Madenciliği Sınıflandırma Algoritmalarının Karşılaştırılması. Avrupa Bilim ve Teknoloji Dergisi, (27), 880-889.
  • Erşahin, B., Aktaş, Ö., Kılınç, D., & Erşahin, M. (2019). A hybrid sentiment analysis method for Turkish. Turkish Journal of Electrical Engineering and Computer Science, 27, 1780–1793.
  • Genuer, R. (2010). Forêts aléatoires: aspect théoriques, sélection de variables et applications (Thèse de Doctorat Mathématiques, Université de Paris-Sud XI).
  • Liu, S., Li, F., Li, F., Cheng, X., & Shen, H. (2013). Adaptive co-training SVM for sentiment classification on tweets. In Proceedings of the 22nd ACM international conference on Information & Knowledge Management ACM.
  • Mudinas, A., Zhang, D., & Levene, M. (2012). Combining lexicon and learning based approaches for concept-level sentiment analysis. In Proceedings of the First International Workshop on Issues of Sentiment Discovery and Opinion Mining.
  • Naz, S., Sharan, A., & Malik, N. (2018). Sentiment Classification On Twitter Data Using Support Vector Machine. In IEEE/WIC/ACM International Conference on Web Intelligence (WI).
  • Ohana, B., & Tierney, B. (2009). Sentiment classification of reviews using SentiWordNet. In 9th IT&T Conference.
  • Polat, H., & Ağca, Y. (2022). TripAdvisor Kullanıcılarının Türkçe ve İngilizce Yorumları Kapsamında Duygu Analizi Yöntemlerinin Karşılaştırmalı Analizi. Abant Sosyal Bilimler Dergisi, 22(2), 901-916.
  • Rodríguez-Galiano, V. F., Abarca-Hernández, F., Ghimire, B., Chica-Olmo, M., Akinson, P. M., & Jeganathan, C. (2011). Incorporating Spatial Variability Measures in Land-cover Classification using Random Forest. Procedia Environmental Sciences, 3, 44-49.
  • Sham, N. M., & Mohamed, A. (2022). Climate Change Sentiment Analysis Using Lexicon, Machine Learning and Hybrid Approaches. Sustainability, 14(8), 4723-4751. DOI: 10.3390/su14084723.
  • Türkmenoğlu, C. (2015). Türkçe Metinlerde Duygu Analizi (Yüksek Lisans Tezi, Bilgisayar Mühendisliği Anabilim Dalı, İstanbul Teknik Üniversitesi).
  • Zainudin, S., Jasim, D. S., & Bakar, A. A. (2016). International Journal on Advanced Science, Engineering and Information Technology, 6(6), 1148-1153.

A Hybrid Approach for Sentiment Analysis of Tweets

Year 2023, Volume: 6 Issue: 1, 57 - 68, 17.12.2023
https://doi.org/10.57244/dfbd.1314901

Abstract

The views and inputs expressed by the community have always been a crucial and valuable resource for various enterprises. The advent of widespread community media has provided an exceptional opportunity for studying and assessing diverse fields, replacing the peculiar, laborious, and inaccurate approaches that companies used to rely on. This particular type of analysis falls under the subclass of sentence analysis. Sentiment analysis, a broad term, refers to the process of effectively classifying user-generated content into specific polarities. To perform sentiment identification and analysis, a range of tools and techniques are available, including supervised machine learning techniques that classify the target group after training on data. Hybrid instruments, combining machine learning and lexicon-based algorithms, classify content based on annotated dictionaries. In this study, we employed the Support Vector Machine (SVM) algorithm with Weka, an open-source software, to analyze sentiments. Two pre-categorized datasets of tweets were utilized. The performance of the SVM algorithm was assessed using analytical metrics.

References

  • Appel, O., Chiclana, F., Carter, J., & Fujita, H. (2016). A hybrid approach to sentiment analysis. In IEEE Congress on Evolutionary Computation.
  • Beleveslis, D., Tjortjis, C., Psaradelis, D., & Nikoglou, D. (2019). A Hybrid Method For Sentiment Analysis Of Election Related Tweets. In 4th SouthEast Europe Design Automation, Computer Engineering, Computer Networks and Social Media Conference (SEEDA-CECNSM).
  • Çelik, E., Dal, D.., & Aydın, T. (2021). Duygu Analizi İçin Veri Madenciliği Sınıflandırma Algoritmalarının Karşılaştırılması. Avrupa Bilim ve Teknoloji Dergisi, (27), 880-889.
  • Erşahin, B., Aktaş, Ö., Kılınç, D., & Erşahin, M. (2019). A hybrid sentiment analysis method for Turkish. Turkish Journal of Electrical Engineering and Computer Science, 27, 1780–1793.
  • Genuer, R. (2010). Forêts aléatoires: aspect théoriques, sélection de variables et applications (Thèse de Doctorat Mathématiques, Université de Paris-Sud XI).
  • Liu, S., Li, F., Li, F., Cheng, X., & Shen, H. (2013). Adaptive co-training SVM for sentiment classification on tweets. In Proceedings of the 22nd ACM international conference on Information & Knowledge Management ACM.
  • Mudinas, A., Zhang, D., & Levene, M. (2012). Combining lexicon and learning based approaches for concept-level sentiment analysis. In Proceedings of the First International Workshop on Issues of Sentiment Discovery and Opinion Mining.
  • Naz, S., Sharan, A., & Malik, N. (2018). Sentiment Classification On Twitter Data Using Support Vector Machine. In IEEE/WIC/ACM International Conference on Web Intelligence (WI).
  • Ohana, B., & Tierney, B. (2009). Sentiment classification of reviews using SentiWordNet. In 9th IT&T Conference.
  • Polat, H., & Ağca, Y. (2022). TripAdvisor Kullanıcılarının Türkçe ve İngilizce Yorumları Kapsamında Duygu Analizi Yöntemlerinin Karşılaştırmalı Analizi. Abant Sosyal Bilimler Dergisi, 22(2), 901-916.
  • Rodríguez-Galiano, V. F., Abarca-Hernández, F., Ghimire, B., Chica-Olmo, M., Akinson, P. M., & Jeganathan, C. (2011). Incorporating Spatial Variability Measures in Land-cover Classification using Random Forest. Procedia Environmental Sciences, 3, 44-49.
  • Sham, N. M., & Mohamed, A. (2022). Climate Change Sentiment Analysis Using Lexicon, Machine Learning and Hybrid Approaches. Sustainability, 14(8), 4723-4751. DOI: 10.3390/su14084723.
  • Türkmenoğlu, C. (2015). Türkçe Metinlerde Duygu Analizi (Yüksek Lisans Tezi, Bilgisayar Mühendisliği Anabilim Dalı, İstanbul Teknik Üniversitesi).
  • Zainudin, S., Jasim, D. S., & Bakar, A. A. (2016). International Journal on Advanced Science, Engineering and Information Technology, 6(6), 1148-1153.
There are 14 citations in total.

Details

Primary Language Turkish
Subjects Statistical Data Science, Data Communications
Journal Section Makaleler
Authors

Erol Kına 0000-0002-7785-646X

Emre Biçek 0000-0001-6061-9372

Publication Date December 17, 2023
Submission Date June 15, 2023
Published in Issue Year 2023 Volume: 6 Issue: 1

Cite

APA Kına, E., & Biçek, E. (2023). Tweetlerin Duygu Analizi İçin Hibrit Bir Yaklaşım. Doğu Fen Bilimleri Dergisi, 6(1), 57-68. https://doi.org/10.57244/dfbd.1314901