Sentiment analysis in Arabic panic detection systems in Iraq

Abstract

The internet’s prevalence has increased the use of social media platforms for sharing peoples’ views, reviews, opinions, and sentiments. Consequently, sentiment analysis has become valuable to marketing, brand management, public policy, healthcare, and e-commerce. Panic detection systems refer to a system that utilizes sentiment analysis techniques to identify, quantify, and potentially track expressions of panic, fear, or related strong negative emotions within digital content. Sentiment analysis application can indicate a person’s attitude or cultural influences. The rise of Arabic digital content on social platforms presents unique challenges and opportunities for sentiment analysis. There are fewer Arabic sentiment lexicons, emotional connotations, and annotated corpora than in English. Therefore, this study applies machine learning and deep learning to identify sentiments within the IRAQI-Arabic panic detection systems. The proposed model is based on Residual Network (ResNet), MobileNet, and Convolutional Neural Network (CNN). A web scraping API collected COVID-19-related news from Google, Facebook, Twitter, and BBC News. The model used was retrained on the images and comments based on training, public, and private sub-sets. Bidirectional Encoder Representations from Transformers (BERT) were applied across SMOTE, Random oversampling, five-folds, and ten folds. The results show that the accuracy of BERT is 91%. The proposed MobileNet model had an accuracy of 0.98, recall of 0.98, and MAE of 0.032. The model’s performance confirms that it is suitable for critical applications that require high-level precision. The study offers a novel model for Arabic panic systems. Also, it presents an Iraqi-Arabic dataset tailored for panic detection.