SMS spam filtering and thread identification using bi-level text classification and clustering techniques

Nagwani, Naresh Kumar; Sharaff, Aakanksha

doi:10.1177/0165551515616310

Cited by 53 publications

(25 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In other recent studies two-level classifiers are used to obtain better results in classifying spam. 5,6 In this study we are going to focus on improving one-level learning-based classifiers.…”

Section: Related Workmentioning

confidence: 99%

Short Messages Spam Filtering Combining Personality Recognition and Sentiment Analysis

Ezpeleta

Garitano

Zurutuza

et al. 2017

Int. J. Unc. Fuzz. Knowl. Based Syst.

View full text Add to dashboard Cite

Currently, short communication channels are growing up due to the huge increase in the number of smartphones and online social networks users. This growth attracts malicious campaigns, such as spam campaigns, that are a direct threat to the security and privacy of the users. While most researches are focused on automatic text classification, in this work we demonstrate the possibility of improving current short messages spam detection systems using a novel method. We combine personality recognition and sentiment analysis techniques to analyze Short Message Services (SMS) texts. 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 SMS spam classifiers and filters to each dataset in order to compare the results of each one. Taking into account the experimental results we analyze the real inuence of each feature and the combination of both. At the end, the best results are improved in terms of accuracy, reaching to a 99.01% and the number of false positive is reduced.

show abstract

Section: Related Workmentioning

confidence: 99%

Short Messages Spam Filtering Combining Personality Recognition and Sentiment Analysis

Ezpeleta

Garitano

Zurutuza

et al. 2017

Int. J. Unc. Fuzz. Knowl. Based Syst.

View full text Add to dashboard Cite

show abstract

“…Various spam filters have been developed with machine learning methods being particularly effective, including methods such as Naïve Bayes (NB) classifiers [7,51], decision trees [16,65], support vector machines (SVMs) [8,23], k-nearest neighbor algorithm (k-NN) [39], K-means clustering [53], artificial immune systems (AIS) [81], multilayer perceptron neural network (MLP) [19,78], and meta-learning methods [42,77]. Machine learning approaches aim to automatically construct word lists and their weights by classifying messages into two classes; the incoming message is either spam or not spam.…”

Section: Introductionmentioning

confidence: 99%

Spam filtering using integrated distribution-based balancing approach and regularized deep neural networks

Barushka

Hájek

2018

Appl Intell

View full text Add to dashboard Cite

Rapid growth in the volume of unsolicited and unwanted messages has inspired the development of many anti-spam methods. Supervised anti-spam filters using machine-learning methods have been particularly effective in categorizing spam and non-spam messages. These automatically integrate spam corpora pre-processing, appropriate word lists selection, and the calculation of word weights, usually in a bag-of-words fashion. To develop an accurate spam filter is challenging because spammers attempt to decrease the probability of spam detection by using legitimate words. Complex models are therefore needed to solve such a problem. However, existing spam filtering methods usually converge to a poor local minimum, cannot effectively handle high-dimensional data and suffer from overfitting issues. To overcome these problems, we propose a novel spam filter integrating an N-gram tf.idf feature selection, modified distribution-based balancing algorithm and a regularized deep multi-layer perceptron NN model with rectified linear units (DBB-RDNN-ReL). As demonstrated on four benchmark spam datasets (Enron, SpamAssassin, SMS spam collection and Social networking), the proposed approach enables capturing more complex features from high-dimensional data by additional layers of neurons. Another advantage of this approach is that no additional dimensionality reduction is necessary and spam dataset imbalance is addressed using a modified distribution-based algorithm. We compare the performance of the approach with that of state-of-the-art spam filters (Minimum Description Length, Factorial Design using SVM and NB, Incremental Learning C4.5, and Random Forest, Voting and Convolutional Neural Network) and several machine learning algorithms commonly used to classify text. We show that the proposed model outperforms these other methods in terms of classification accuracy, with fewer false negatives and false positives. Notably, the proposed spam filter classifies both major (legitimate) and minor (spam) classes well on personalized / non-personalized and balanced / imbalanced spam datasets. In addition, we show that the proposed model performs better than the results reported by previous studies in terms of accuracy. * significantly higher (p=0.05).

show abstract

“…Various machine learning classifiers have been employed to classify SMSes for filtering or detecting spam. Some of the classifiers that are extensively used include naïve Bayes (NB), Random Forest (RF) and support vector machine (SVM) (Ahmed et al, 2014;Hedieh et al, 2016;Nagwani & Sharaff, 2017;Nuruzzaman et al, 2011). The NB classifier is widely used for SMS classification due to its simplicity and speed, while the common use of SVM and RF tends to be motivated by their high classification accuracy (CA)-often reported to be in ranges above 90% (Nagwani & Sharaff, 2017).…”

Section: Sms Datasets Feature Extraction and Machine Learning Classmentioning

confidence: 99%

Application of Machine Learning Classification to Detect Fraudulent E‑wallet Deposit Notification SMSes

Enkono

Suresh

2020

Afr. j. inf. commun. (Online)

View full text Add to dashboard Cite

Fraudulent e-wallet deposit notification SMSes designed to steal money and goods from m-banking users have become pervasive in Namibia. Motivated by an observed lack of mobile applications to protect users from such deceptions, this study evaluated the ability of machine learning to detect the fraudulent e-wallet deposit notification SMSes. The naïve Bayes (NB) and support vector machine (SVM) classifiers were trained to classify both ham (desired) SMSes and scam (fraudulent) e-wallet deposit notification SMSes. The performances of the two classifier models were then evaluated. The results revealed that the SVM classifier model could detect the fraudulent SMSes more efficiently than the NB classifier.

show abstract

SMS spam filtering and thread identification using bi-level text classification and clustering techniques

Cited by 53 publications

References 41 publications

Short Messages Spam Filtering Combining Personality Recognition and Sentiment Analysis

Short Messages Spam Filtering Combining Personality Recognition and Sentiment Analysis

Spam filtering using integrated distribution-based balancing approach and regularized deep neural networks

Application of Machine Learning Classification to Detect Fraudulent E‑wallet Deposit Notification SMSes

Contact Info

Product

Resources

About