A Hybrid Approach Based on Particle Swarm Optimization and Random Forests for E-Mail Spam Filtering

Faris, Hossam; Aljarah, Ibrahim; Al-Shboul, Bashar

doi:10.1007/978-3-319-45243-2_46

Cited by 32 publications

(10 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…shown by Kill Herd algorithm are more accurate than the other two algorithms. Another optimization based system is proposed by Al-Shboul et al [12] for the detection of spam mails. The authors have considered a hybrid approach for the email filtration process.…”

Section: Related Workmentioning

confidence: 44%

Machine Learning based Spam E-Mail Detection

Sharma¹,

Bhardwaj²

2018

IJIES

View full text Add to dashboard Cite

Abstract:Spam email is one of the biggest issues in the world of internet. Spam emails not only influence the organisations financially but also exasperate the individual email user. This paper aims to propose a machine learning based hybrid bagging approach by implementing the two machine learning algorithms: Naïve Bayes and J48 (decision tree) for the spam email detection. In this process, dataset is divided into different sets and given as input to each algorithm. Total three experiments are performed and the results obtained are compared in terms of precision, recall, accuracy, f-measure, true negative rate, false positive rate and false negative rate. The two experiments are performed using individual Naïve Bayes & J48 algorithms. Third experiment is the proposed SMD system implemented using hybrid bagged approach. The overall accuracy of 87.5% achieved by the hybrid bagged approach based SMD system.

show abstract

Section: Related Workmentioning

confidence: 44%

Machine Learning based Spam E-Mail Detection

Sharma¹,

Bhardwaj²

2018

IJIES

View full text Add to dashboard Cite

show abstract

“…Faris [29] proposed a PSO-based Wrapper with a Random Forest algorithm that effectively detects spam messages. Ajaz [30] used a secure hash algorithm with the Naïve Bayes feature extraction method for spam filtering.…”

Section: Combine Based / Other Approachesmentioning

confidence: 99%

Universal Spam Detection using Transfer Learning of BERT Model

Tida¹,

Hsu²

2022

Proceedings of the Annual Hawaii International Conference on System Sciences

View full text Add to dashboard Cite

Deep learning transformer models become important by training on text data based on self-attention mechanisms. This manuscript demonstrated a novel universal spam detection model using pre-trained Google's Bidirectional Encoder Representations from Transformers (BERT) base uncased models with four datasets by efficiently classifying ham or spam emails in real-time scenarios. Different methods for Enron, Spamassain, Lingspam, and Spamtext message classification datasets, were used to train models individually in which a single model was obtained with acceptable performance on four datasets. The Universal Spam Detection Model (USDM) was trained with four datasets and leveraged hyperparameters from each model. The combined model was finetuned with the same hyperparameters from these four models separately. When each model using its corresponding dataset, an F1-score is at and above 0.9 in individual models. An overall accuracy reached 97%, with an F1 score of 0.96. Research results and implications were discussed.

show abstract

“…This inductive algorithm is trained using cross-validation and then tested. The next stage is to train a model with a subset of features based on the selection from PSO [20] and test it [21].…”

Section: Building the Modelmentioning

confidence: 99%