Bulletin of Electrical Engineering and Informatics Vol. 14, No. 4, August 2025, pp. 2772~2781 ISSN: 2302-9285, DOI: 10.11591/eei.v14i4.7712  2772 Journal homepage: http://beei.org Optimized convolutional neural network enabled technique for sentiment analysis from social media data Chinta Veena 1 , Kavita A. Sultanpure 2 , Meenakshi 3 , Sunil L. Bangare 4 , Punam Sunil Raskar 5 , Shriram Sadashiv Kulkarni 4 , Myla M. Arcinas 6 , Kantilal Pitambar Rane 7 1 Department of Computer Science and Engineering, PVKK Institute of Technology, Anantapuramu, India 2 Department of Information Technology, Vishwakarma Institute of Technology, Savitribai Phule Pune University, Pune, India 3 School of Journalism and Mass Communication, Apeejay Stya University, Sohna Haryana, India 4 Department of Information Technology, Sinhgad Academy of Engineering, Savitribai Phule Pune University, Pune, India 5 Department of Computer and Electronics and Telecommunication Engineering, Smt. Kashibai Navale College of Engineering, Savitribai Phule Pune University, Pune, India 6 Department of Sociology and Behavioral Sciences, De La Salle University, Manila, Philippines 7 Department of Electronics and Telecommunications Engineering, Bharati Vidyapeeth College of Engineering, Navi Mumbai, India Article Info ABSTRACT Article history: Received Oct 13, 2023 Revised Jan 15, 2025 Accepted Mar 9, 2025 Sentiment analysis is an area of computational linguistics that studies natural language processing. The most significant subtasks are gathering people's thoughts and organizing them into groups to determine how they feel. The primary purpose of sentiment analysis is to determine whether the individual who created a piece of material has a positive or negative opinion about a subject. It has been claimed that sentiment analysis and social media mining have contributed to the recent success of both private sector and the government. Emotional analysis has applications in practically every aspect of modern life, from individuals to corporations, telecommunications to medical, and economics to politics. This article describes an improved sentiment analysis model based on gray level co-occurrence matrix (GLCM) texture feature extraction and a convolutional neural network (CNN). This model was created using tweets. First, texture characteristics are extracted from the input data set using the GLCM technique. This feature extraction improves categorization accuracy. CNNs are used to classify objects. It outperforms both the support vector machine and the AdaBoost algorithms in terms of accuracy. CNN has achieved an accuracy of 98.5% for sentiment analysis task. Keywords: Accuracy Convolutional neural network Deep learning Feature extraction Gray level co-occurrence matrix Sentiment analysis Social data analysis This is an open access article under the CC BY-SA license. Corresponding Author: Chinta Veena Department of Computer Science and Engineering, PVKK Institute of Technology Sanapa Road, Rudrampeta, Anantapuramu, Andhra Pradesh, India Email: cveena30@gmail.com 1. INTRODUCTION During the course of human history, several innovations have been created to boost agricultural output while also decreasing the amount of time and energy needed for farming. Yet, the enormous population rate thwarted all of their efforts [1]. The estimated global population of 9.8 billion in 2050 is a rise of around 25% from the current population of 7.2 billion [2]. The majority of the aforementioned increase is expected to occur in developing countries. Contrarily, the trend of urbanisation is likely to speed up, with more than “70%” of the world's population (now 49%) forecast to reside in cities by 2050 [3]. Furthermore, incomes will be several times what they are now, driving up demand for food everywhere but especially in developing countries. Because of this, people in these nations will pay more attention to what they eat and