SENTIMENT ANALYSIS BASED ON MACHINE LEARNING METHODS ON TWITTER DATA USING oneAPI


Abstract views: 98 / PDF downloads: 190

Authors

  • Fatih Şengül Dept. of Defense Technologies, Sivas University of Science and Technology, Turkey
  • Kemal Adem Dept. of Computer Engineering, Sivas University of Science and Technology, Turkey
  • Esra Kavalcı Yılmaz Dept. of Defense Technologies, Sivas University of Science and Technology, Turkey

DOI:

https://doi.org/10.59287/iccar.781

Keywords:

Sentiment Analysis, Twitter Data, oneAPI

Abstract

With the gradual development of technology, the use of digital social networks has become widespread. As a result of this increased use, the information sharing process has accelerated and increased. This has created an enormous amount of data on digital social networks. With the increasing amount of data, it has made it possible to make inferences about people, products, companies and many other areas. Various fields of study have emerged to process and analyze the data. One of these fields of study is sentiment analysis. Sentiment analysis is the analysis of data from different sources such as text, sound or image by classifying the attitude towards a subject as positive, negative or neutral. In this study, sentiment analysis was performed using Sentiment140 dataset created through Twitter application, one of the digital social network platforms. After preprocessing on the dataset containing English Tweet messages, Bernoulli Naive Bayes, Linear Support Vector Machine, Logistic Regression and artificial neural network algorithms LSTM and CNN methods were used in a hybrid way. Classification results were evaluated with f1 score. Accuracy rates of 0.80%, 0.82%, 83%, 85% were achieved for Bernoulli Naive Bayes, Linear Support Vector Machine, Logistic Regression, LSTM and CNN classifications respectively.

Downloads

Published

2023-05-24

How to Cite

Şengül, F., Adem, K., & Yılmaz, E. K. (2023). SENTIMENT ANALYSIS BASED ON MACHINE LEARNING METHODS ON TWITTER DATA USING oneAPI. International Conference on Contemporary Academic Research, 1, 207–213. https://doi.org/10.59287/iccar.781