Fundamental Sentiment Analysis by Natural Language Processing and Machine Learning for Email Classification
Adesoji E. Adewale, Tatsuya Yamazaki · 2023
Due to its ease of use, speed, adaptability, and ability to keep a complete record of correspondence, email is a commonly used and trusted communication medium. The vulnerability of these emails to cyberattacks has increased. This study utilized the hybrid-based sentiment analysis approach for email fraud detection. The lexicon-based using the Word2Vec feature and Machine Learning (ML) classification approach using both the Bag of Words and TF-IDF feature extraction techniques are adopted to optimize accuracy. The ML classifiers adopted are Random Forest, k-nearest neighbors (k-NN), Support Vector Machine, and Logistic Regression. The predictive and classification comparison of the ML models suggests that Random Forest slightly outperformed the other models with 87% accuracy and 78% F1-score and k-NN performed worst.