• Neetu Ahirwar
• Reshma Shivhare

Single-modal spam filtering systems have a high text spam detection rate. Spammers introduce garbage information into the multi-modality component of an email to diminish the single-modal spam filtering systems' identification rate and evade detection. A novel model dubbed text-based dataset modal architecture based on model fusion (MMA-MF) is suggested to successfully filter spam buried in text. The spam-filtering model combines a CNN and LSTM. Using the LSTM model and the CNN model to evaluate email text independently, two classification probability values are obtained and combined to determine whether an email is spam. For the MMA-MF model's hyperparameters, we apply grid search optimization and k-fold cross-validation to assess its performance. Our experiments demonstrate that our model is more accurate than typical spam filtering systems (92.64–98.48%).

Spam Filtering System; Multi-Modal; MMA-MF; Fusion Model; LSTM; CNN

"E-Mail Spam Filtring Using Machine Learning Classification Technique", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.9, Issue 6, page no.j361-j367, June-2022, Available :http://www.jetir.org/papers/JETIR2206949.pdf

"E-Mail Spam Filtring Using Machine Learning Classification Technique", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.9, Issue 6, page no. ppj361-j367, June-2022, Available at : http://www.jetir.org/papers/JETIR2206949.pdf