INTEGRATING OPTIMAL DEEP LEARNING WITH NATURAL LANGUAGE PROCESSING FOR ARABIC SPAM AND HAM TWEETS RECOGNITION
Abstract
Natural language processing (NLP) is a domain of artificial intelligence (AI) that concentrates on the communication between human and computer language. Detection of Arabic spam and ham tweets involves leveraging deep learning (DL) models, mainly NLP techniques such as brain-like computing and AI-driven tweets recognition, to mechanically differentiate between spam and ham messages dependent upon content semantics, linguistic patterns, and contextual data within the Arabic text. This study presents an optimal deep learning with natural language processing for Arabic spam and ham tweets recognition (ODLNLP-ASHTR) technique in various complex systems platforms. In the ODLNLP-ASHTR technique, the data pre-processing is initially performed to alter the input tweets into a compatible format, and a BERT word embedding process is used. For Arabic ham and spam tweet recognition, the ODLNLP-ASHTR technique makes use of the self-attention bidirectional gated recurrent unit (SA-BiGRU) model. At last, the detection performance of the SA-BiGRU model can be boosted by the design of an improved salp swarm algorithm (ISSA). The experimental evaluation of the ODLNLP-ASHTR technique takes place using the Arabic tweets dataset. The experimental results pointed out the improved performance of the ODLNLP-ASHTR model compared to recent approaches with a maximum accuracy of 98.11%.
