Novel email spam detection method using sentiment analysis and personality recognition

Abstract

Unsolicited email campaigns remain as one of the biggest threats affecting millions of users per day. During the past years several techniques to detect unsolicited emails have been developed. This work provides means to validate the hypothesis that the identification of the email messages’ intention can be approached by sentiment analysis and personality recognition techniques. These techniques will provide new features that improve current spam classification techniques. We combine personality recognition and sentiment analysis techniques to analyse email content. We enrich a publicly available dataset adding these features, first separately and after in combination, of each message to the dataset, creating new datasets. We apply several combinations of the best email spam classifiers and filters to each dataset in order to compare results.

Detecting Illegal Online Gambling (IOG) Services in the Mobile Environment

“…Recent studies that detect spam include CNN-based filtering with deep learning [30][31][32]. Spam filtering based on sentimental analysis using SentiWordNet has also been proposed [33]. Various other spam filtering methods are discussed in academic literature, such as similarity-based corpus and Wikipedia link-based spam filtering [34].…”

Detection of Email Spam using Natural Language Processing Based Random Forest Approach

“…The new features provided by these techniques helps in improving existing spam classification approach. Thus, in [19], the sentiment analysis and spam classification techniques are combined to analyze the email messages. The extracted new features are added to existing dataset individually and then combined to compare the results of several best spam email filters and classifiers [19].…”

“…Thus, in [19], the sentiment analysis and spam classification techniques are combined to analyze the email messages. The extracted new features are added to existing dataset individually and then combined to compare the results of several best spam email filters and classifiers [19]. Various machine learning algorithms like Naïve Bayes, Random Forest, and SVM are used for spam email detection and their accuracy is evaluated.…”

“…Spam filtering is important in the field of scientific as well as industries. In [19], the hypothesis of spam detection through personality recognition and sentiment analysis is validated, and expecting to achieve improvements in current techniques of spam filtering.…”

Makine Öğrenmesi Yaklaşımlarının Spam-Mail Sınıflandırma Probleminde Karşılaştırmalı Analizi

“…Aynı veri setini kullanılarak yapılan farklı bir çalışmada ayırt edici özellikler elde edildikten sonra belirlenen BOW histogramları üzerinde 3 ayrı algoritmayla sınıflandırma işlemleri yapılmış [29]. Başka bir çalışmada spam e-posta tespit edilirken içeriğ i analiz edebilmek amacıyla LR algoritması Movie Reviews, CSDMC 2010 Spam Corpus ve TREC 2007 Public Corpus [30] veri setlerine ayrı ayrı uygulanmış [31]. Bassiouni vd.…”