Short Message Service (SMS) have been identified to be a fast communication approach due to its low cost and stress-free nature. The general acceptability of SMS has exposed it to many threats and one of these is spamming. In SMS spam detection, the feature extraction plays a vital role, the extraction of SMS features involves a process of decreasing an initial set of raw features into more measurable forms before the classification. This paper considered the improvement of One Dimensional Ternary Pattern (1D-TP) by the introduction of nature-inspired optimization algorithm known as simulated annealing to obtain optimized features. Seven machine learning algorithms; Bayesian Network (BN), Naïve Bayes (NB), Radial Basic Artificial Neural Network (RBFN), Random Forest (RF), K-nearest neighbours (KNN), Logistic Regression (LR), and Support Vector Machine (SVM) were employed for classification. The developed was evaluated using Kaggle SMS Spam Dataset. Experimental results showed that the highest accuracy of 86.56% was obtained in LR for non-optimized upper features and the highest accuracy of 92.56% was recorded in RF for optimized upper features. The highest precision of 0.95 was achieved in BN for non-optimized upper features of 1D-TP and the highest precision of 0.94 was obtained in optimized upper features of 1D-TP. The highest recall of 1.00 was obtained in NB, SVM and LR for non-optimized lower/upper features and the highest recall of 1.00 was recorded in NB and RF for lower /upper features of 1D-TP.
Published In:IJCAT Journal Volume 7, Issue 6
Date of Publication : June 2020
Pages : 94-102
Figures :04
Tables :06
Taofeek-Ibrahim Fatimoh Abidemi :
is working an Assistant Professor
Department of Computer Science, Federal Polytechnic Offa
Kwara State, Nigeria.
Oluwakemi Christiana Abikoye :
Department of Computer Science, University of Ilorin
Ilorin, Ilorin, Nigeria.
Toye Nike Toyin :
Department of Computer Science, Federal Polytechnic Offa
Kwara State, Nigeria.
Accuracy, Feature Extraction, Short Message Service, Spam SMS, One Dimensional Ternary Pattern
The upturn in mobile communication technology produces numerous effects on people. One of the usefulness is communication through SMS, which is one of the most
prevalent communication methods nowadays. Similar to other general communication techniques, SMS also suffers from spam messages. In SMS Spam detection, the feature extraction is a core step which precedes the classification stage. This paper optimized 1D-TP feature extraction for SMS Spam filtering system by the application of nature-inspired optimization algorithm known as simulated annealing. The results obtained from the optimized 1D-TP features outperformed the non-optimized 1D-TP features for SMS spam detection. Thus showed that the proposed system is an effective approach for SMS Spam filtering.
[1] P. Nivaashini, M., Soundariya, R. S, Kodiieswari, A. & Thangaraj, "SMS Spam Detection Using Neural Network Classifier," Int. J. Pure Appl. Math., vol. 119, no. 18, pp. 2425-2436, 2018.
[2] A. Mizuki, T. Matsumoto, T. Uemura, and S. Kichimi, "Improving SMS Processing Power for the Increasing Smartphone Demand," NTT DOCOMO Tech. J., vol. 14, no. 4, pp. 60-62, 2013.
[3] V. K. Katankar, "Short Message Service using SMS Gateway," Int. J. Comput. Sci. Eng., vol. 2, no. 5, pp. 1487-1491, 2010.
[4] N. Choudhary and A. K. Jain, "Towards filtering of SMS Spam Messages using Machine Learning-Based Technique," in Communications in Computer and Information Science, 2017, vol. 712, pp. 18-30.
[5] W. N. Gansterer, A. G. K. Janecek, and R. Neumayer, "Spam filtering based on latent semantic indexing," in Survey of Text Mining II: Clustering, Classification, and Retrieval, 2008, pp. 165-183.
[6] M. Gupta, A. Bakliwal, S. Agarwal, and P. Mehndiratta, "A Comparative Study of Spam SMS Detection Using Machine Learning Classifiers," in 2018 11th International Conference on Contemporary Computing, IC3 2018, 2018, pp. 1-7.
[7] M. Abdulhamid, M. Shafie, A. Latiff, H. Chiroma, and O. Osho, "A Review on Mobile SMS Spam Filtering Techniques A Review on Mobile SMS Spam Filtering Techniques," no. February, 2017.
[8] T. M. & Mahmoud and A. M. Mahfouz, "SMS Spam Filtering Technique Based on Artificial Immune System," Int. J. Comput. Sci. Issues, vol. 9, no. 2, pp. 589-597, 2012.
[9] N. Chaudhari, P. Jayvala, and P. Vinitashah, "Survey on Spam SMS filtering using Data mining Techniques," Ijarcce, vol. 5, no. 11, pp. 193-195, 2016.
[10] A. K. Uysal, S. Gunal, S. Ergin, and E. S. Gunal, "The Impact of Feature Extraction and Selection on SMS Spam Filtering," Elektron. IR ELEKTROTECHNIKA, vol. 19, no. 5, pp. 67-72, 2014.
[11] T. Subramaniam, H. A. Jalab, and A. Y. Taqa, "Overview of textual anti-spam filtering techniques," Int. J. Phys. Sci., vol. 5, no. 12, pp. 1869-1882, 2010.
[12] A. K. Uysal, S. Gunal, S. Ergin, and E. S. Gunal, "The impact of feature extraction and selection on SMS spam filtering," Elektron. ir Elektrotechnika, vol. 19, no. 5, pp. 67-72, 2013.
[13] R. Kaur and R. Rajput, "Face recognition and its various techniques : a review," Int. J. Sci. Eng. Technol. Res., vol. 2, no. 3, pp. 670-675, 2013.
[14] S. Telgaonkar, A. H & Deshmukh, "Dimensionality Reduction and Classification through PCA and LDA," Int. J. Comput. Appl., vol. 122, no. 17, pp. 4-8, 2015.
[15] D. Suleiman and G. Al-Naymat, "SMS Spam Detection using H2O Framework SMS Spam Detection using H2O Framework," in Procedia Computer Science, 2017, vol. 113, pp. 154-161.
[16] M. Ramabai, "Spam Detection using NLP Techniques," Int. J. Recent Technol. Eng., vol. 8, no. 2, pp. 2423-2426, 2019.
[17] H. H. Mansoor and S. H. Shaker, "Using classification techniques to SMS spam filter," Int. J. Innov. Technol. Explor. Eng., vol. 8, no. 12, pp. 1734-1739, 2019.
[18] A. S. Rajput, J. S. Sohal, and V. Athavale, "Email Header Feature Extraction using Adaptive and Collaborative approach for Email Classification," Int. J. Innov. Technol. Explor. Eng., vol. 8, no. 7, pp. 158-164, 2019.
[19] R. K. Kaliyar, P. Narang, and A. Goswami, "SMS Spam Filtering on Multiple Background Datasets Using Machine Learning Techniques: A Novel Approach," in Proceedings of the 8th International Advance Computing Conference, IACC 2018, 2018, pp. 59-65.
[20] O. F. Kaya, Y., & Ertugrul, "A Novel Feature Extraction Approach in SMS Spam Filtering for Mobile Communication: One-Dimensional Ternary Patterns," Secure. Commun. Networks, vol. 9, pp. 4680-4690, 2016.
[21] O. O. Abayomi-alli, S. A. Onashoga, and A. S. Sodiya, "A Critical Analysis of Existing SMS SPAM Filtering Approaches," in 1st International Conference on Applied Information Technology, 2015, pp. 211-220.
