Classifying Comments in Social Media Networks Using CNN with SVM

Abstract

People can now communicate with each other and share ideas thanks to social media by posting content on many communication platforms every day. Text comments have become the most widely used in posts across various social media platforms, through which users express their opinions. Manually classifying these comments is a time-consuming process, so this study aims to use artificial intelligence techniques to solve this problem effectively. In this study, we rely on natural language processing (NLP) techniques to classify comments into three categories: positive, negative, and neutral, while using deep learning techniques to increase classification accuracy. The study focuses on classifying tweets posted on the Twitter platform, using a dataset obtained from Kaggle. A long-short-term memory (LSTM) network architecture improved the model performance. The results showed that the proposed model was able to achieve up to 87% accuracy in classifying tweets, highlighting its effectiveness in this field. This model enables reviews to be automatically categorized, which helps customers in their search for goods or services before transacting and saves time. Additionally, marketers can use it to find out what audiences think about their brands and products