This paper presents a deep neural network model for performing spam detection. Unlike conventional machine learning models like naïve Bayes, support vector machines, a deep neural network is immune to various fluctuating environments. This paper also proposes the application of CountVectorizer in order to perform feature extraction on the text-based data. In order to increase the accuracy score of the proposed model, hyperparameter tuning has also been done. This paper also compares the accuracy of the proposed deep neural network to various machine learning classifiers like logistic regression, support vector machine, k-nearest neighbor, Bayes, etc. Experimental results of this paper show that the proposed deep neural network model is able to outclass all other machine learning models in terms of achieved accuracy score, and naïve Bayes classifier is the most efficient model with respect to its computation cost.
CITATION STYLE
Vashisth, S., Dhall, I., & Aggarwal, G. (2020). An Approach to Automated Spam Detection Using Deep Neural Network and Machine Learning Classifiers. In Lecture Notes in Networks and Systems (Vol. 106, pp. 143–151). Springer. https://doi.org/10.1007/978-981-15-2329-8_15
Mendeley helps you to discover research relevant for your work.