Duygu Analizinde Aşırı Öğrenme Algoritması ve Uygulamaları: Sistematik Literatür Taraması

Year 2022, , 247 - 259, 28.12.2022

Rumeysa Erdoğan , Baha Şen

https://doi.org/10.53694/bited.1214454

Abstract

Duygu Analizi, yapılandırılmamış metin aracılığıyla insan duygularını tanımlama ve özellik çıkarma tekniği olarak kabul edilir ve Doğal Dil İşleme ve Makine Öğrenimi yoluyla yapılır. Günümüzde birçok kurum ve şirketler bunu kullanarak müşteri veya kullanıcının özelliklerini tanımak ve ona uygun şekilde hareket etmek istemektedir. Böylece duygu analizinin önemi ve etkinliği ve kullanılan algoritmaların çeşitliliği günden güne artmaktadır. Bu algoritmalardan biri de Aşırı Öğrenme Makinesi (Extreme Learning Machine)dir. Extreme Learning Machine (ELM) algoritması, duygu analizi ve sınıflandırması için önemli bir makine öğrenimi algoritmasıdır. Bu çalışma, ELM’nin duygu analizinde kullanımına ilişkin seçilen çalışmaların kullanılan yöntem, bağlam ve uygulamaları yönünden incelendiğini gösteren sistematik bir araştırmadır. 2020 ile 2022 yılları arasında yayınlanan çalışmaların sistematik bir incelemesi, Web of Science ve Google Scholar veri tabanları kullanılarak gerçekleştirilmiştir. Literatürün ilk ve derinlemesine taranmasından sonra inceleme sürecinden 28 makaleden 10'u seçilmiştir. Makaleler, çalışmanın amacına ve araştırma sorularına göre incelenmiştir. Araştırma kapsamında yapılan inceleme sonuçlarına göre, duygu analizinde çoğunlukla ELM ile birlikte farklı metotlar kullanılmış, ELM’ nin performansı iyileştirilmeye çalışılmıştır. Tedavi özetlerinin kalite analizi, sağlık, eğitim, website ürün değerlendirmeleri gibi farklı alanlarda kullanılmaktadır. ELM’nin duygu analizinde kullanımında kapsam olarak en çok sosyal medya verisi ve özellikle de Twitter platformunun kullanıldığı sonucuna ulaşılmıştır.

Keywords

Duygu analizi, Aşırı öğrenme makinesi, Makine öğrenmesi

Extreme Learning Machine Algorithm in Sentiment Analysis and Its Applications: Systematic Literature Review

Abstract

Natural language processing and machine learning are used to define and extract human emotions from unstructured text using a technique called sentiment analysis. Many organizations and companies today want to use this to recognize and act accordingly on the customer or user's features. This increases the importance and effectiveness of emotion analysis and the diversity of algorithms used day by day. One of these algorithms is the Extreme Learning machine. The Extreme Learning machine (ELM) algorithm is an important machine learning algorithm for emotion analysis and classification. In this study, the method used in the ELM's emotional analysis is systematic research that shows that the context and its applications have been studied. A systematic review of the works published between 2020 and 2022 was carried out using Web of Science and Google Scholar databases. After the first and in-depth screening of the literature, 10 of the 28 articles were selected from the review process. The articles have been reviewed based on the purpose of the study and research questions. According to the research results, different methods were used in the emotional analysis, mostly with the ELM, and ELM’s performance was improved. Quality analysis of treatment summaries is used in different areas, such as health care, education, and website product assessments. ELM's use of emotion analysis has resulted in most social media data as a scope, especially the Twitter platform.

Keywords

Sentiment analysis, Extreme learning machine, Machine learning

References

• Al-Baity, H. H., Alshahrani, H. J., Nour, M. K., Yafoz, A., Alghushairy, O., Alsini, R., & Othman, M. (2022). Computational linguistics based emotion detection and classification model on social networking data. Applied Sciences, 12(19), 9680. https://doi.org/10.3390/app12199680
• Alcin, O. F., Ucar, F., & Korkmaz, D. (2016, August). Extreme learning machine based robotic arm modeling. In 2016 21st International Conference on Methods and Models in Automation and Robotics (MMAR) (pp. 1160-1163). IEEE.
• Gough, D., Thomas, J., & Oliver, S. (2012). Clarifying differences between review designs and methods. Systematic Reviews, 1(1). https://doi.org/10.1186/2046-4053-1-28
• Hilal, A. M., Alfurhood, B. S., Al-Wesabi, F. N., Hamza, M. A., al Duhayyim, M., & Iskandar, H. G. (2022). Artificial intelligence based sentiment analysis for health crisis management in smart cities. Computers, Materials and Continua, 71(1), 143–157. https://doi.org/10.32604/cmc.2022.021502
• Hu, J., Heidari, A. A., Shou, Y., Ye, H., Wang, L., Huang, X., ... & Wu, P. (2022). Detection of COVID-19 severity using blood gas analysis parameters and Harris hawks optimized extreme learning machine. Computers in Biology and Medicine, 142, 105166.
• Hua, L., Zhang, C., Peng, T., Ji, C., & Nazir, M. S. (2022). Integrated framework of extreme learning machine (ELM) based on improved atom search optimization for short-term wind speed prediction. Energy Conversion and Management, 252, 115102.
• Huang, G. B., Zhu, Q. Y., & Siew, C. K. (2006). Extreme learning machine: theory and applications. Neurocomputing, 70(1-3), 489-501.
• Jindal, K., & Aron, R. (2021). A systematic study of sentiment analysis for social media data. Materials Today: Proceedings. https://doi.org/10.1016/J.MATPR.2021.01.048
• Menakadevi, P., & Ramkumar, J. (2022). Robust optimization based extreme learning machine for sentiment analysis in big data. 2022 International Conference on Advanced Computing Technologies and Applications, ICACTA 2022. https://doi.org/10.1109/ICACTA54488.2022.9753203
• Pan, B., Hirota, K., Jia, Z., Zhao, L., Jin, X., & Dai, Y. (2021). Multimodal emotion recognition based on feature selection and extreme learning machine in video clips. Journal of Ambient Intelligence and Humanized Computing. https://doi.org/10.1007/s12652-021-03407-2
• Salam, M. A., & Ali, M. (2020). Optimizing extreme learning machine using GWO algorithm for sentiment analysis. International Journal of Computer Applications, 176(38), 22-28.
• Sekhar, C., & Sri, C. S. (2021). Predicting cyber bullying on social media in the big data era using extreme learning machine 11(10).
• Shafqat-Ul-Ahsaan, Mourya A. K, & Singh, P. (2019). Predictive modeling and sentiment classification of social media through extreme learning machine. Proceedings of ICETIT 2019: Emerging Trends in Information Technology, 605, 356.
• Sun, A., Wei, F., Wang, G., & Li, Y. (2022). Chinese sentiment analysis using regularized extreme learning machine and stochastic optimization. 2022 4th International Conference on Natural Language Processing (ICNLP), 525–529. https://doi.org/10.1109/ICNLP55136.2022.00096
• Waheeb, S. A., Khan, N. A., Chen, B., & Shang, X. (2020). Machine learning based sentiment text classification for evaluating treatment quality of discharge summary. Information (Switzerland), 11(5). https://doi.org/10.3390/INFO11050281
• Waheeb, S. A., Khan, N. A., & Shang, X. (2022). Topic modeling and sentiment analysis of online education in the COVID-19 era using social networks-based datasets. Electronics (Switzerland), 11(5). https://doi.org/10.3390/electronics11050715
• Wang, J., Lu, S., Wang, S. H., & Zhang, Y. D. (2022). A review on extreme learning machine. Multimedia Tools and Applications, 81(29), 41611-41660.