Improved Fruitfly Optimization with Stacked Residual Deep Learning Based Email Classification

Applied linguistics means a wide range of actions which include addressing few language-based problems or solving some concerns. Emails stay in the leading positions for business as well personal use. This popularity grabs interest individuals with malevolent intentions—phishing and spam email assaults. Email filtering mechanisms were developed incessantly to follow unwanted, malicious content advancement protect end-users. But prevailing solutions focused on phishing whereas labelling analysis not fully advanced. Thus, this study provides solution related message body text automatic classification into spam. paper presents an Improved Fruitfly Optimization Stacked Residual Recurrent Neural Network (IFFO-SRRNN) based Linguistics Classification. The presented IFFO-SRRNN technique examines intrinsic features identification emails. At preliminary level, model follows pre-processing stage make it compatible further computation. Next, SRRNN method can be useful recognizing classifying As hyperparameters need effectually tuned, IFFO algorithm utilized hyperparameter optimizer. To investigate effectual results IFFO-SRDL technique, series simulations taken placed public datasets, comparison outcomes highlight enhancements over other recent approaches accuracy 98.86%.