Search for Articles:

MECS Press Menu

Zafer Aydin

Work place: Abdullah Gül University, Department of Computer Engineering, Kayseri 38080, Turkey

E-mail: zafer.aydin@agu.edu.tr

Website:

Research Interests: Computer systems and computational processes, Computer Architecture and Organization, Computer Networks

Biography

Zafer AYDIN Dr. Aydin received his Bachelor of Science (B.Sc.) and Master of Science (M.Sc.) degrees with high honor from the Electrical and Electronics Engineering Department of Bilkent University in 1999 and 2001, respectively. He then enrolled in the PhD program of the same department and worked as a teaching assistant for one year. Starting from 2002, he worked as a Graduate Research Assistant in School of Electrical and Computer Engineering at Georgia Institute of Technology, Atlanta GA USA and received the PhD degree in 2008. As a result of maintaining an interest in bioinformatics research, he worked as a post-doctoral fellow for three years in Noble Research Lab, which is part of the Genome Sciences Department at University of Washington, Seattle, WA USA. From September 2011 to Februray 2014, he worked as an Assistant Professor in Electrical and Electronics Engineering Department of Bahcesehir University, Istanbul, Turkey. Currently he is an Assistant Professor in Computer Enginering Department of Abdullah Gul University, Kayseri, Turkey.

Author Articles
FBSEM: A Novel Feature-Based Stacked Ensemble Method for Sentiment Analysis

By Yasin Gormez Yunus E. Isik Mustafa Temiz Zafer Aydin

DOI: https://doi.org/10.5815/ijitcs.2020.06.02, Pub. Date: 8 Dec. 2020

Sentiment analysis is the process of determining the attitude or the emotional state of a text automatically. Many algorithms are proposed for this task including ensemble methods, which have the potential to decrease error rates of the individual base learners considerably. In many machine learning tasks and especially in sentiment analysis, extracting informative features is as important as developing sophisticated classifiers. In this study, a stacked ensemble method is proposed for sentiment analysis, which systematically combines six feature extraction methods and three classifiers. The proposed method obtains cross-validation accuracies of 89.6%, 90.7% and 67.2% on large movie, Turkish movie and SemEval-2017 datasets, respectively, outperforming the other classifiers. The accuracy improvements are shown to be statistically significant at the 99% confidence level by performing a Z-test.

[...] Read more.
Other Articles

Subscribe to receive issue release notifications and newsletters from MECS Press journals