A Hybrid Deep Learning Model to Accurately Detect Anomalies in Online Social Media
Article Sidebar
Main Article Content
Abstract
Online social media (OSM) generates a massive amount of data about human behavior based on their interactions. People express their opinions, comments and share information about variety of topics of their daily life through OSM. The majority of the comments are divided into three categories: Positive, negative, and natural. Regarding the negative comments, the OSM platform facilitates abnormal actions, such as unsolicited messages, misinformation, rumors, the dissemination of fake news and propaganda, as well as the dissemination of malicious links. Therefore, one of the most significant data analytic activities for identifying normal and deviant individuals on social networks is abnormality detection. This paper proposes a hybrid model based on three famous deep learning approaches to discover the behavioral abnormalities, and negative comments in the OSM platforms. The selected benchmark for our research is the airline sentiment in a Twitter dataset. In the proposed method, the dataset is fed to the LSTM network; next, the output of LSTM feeds the CNN network. CNN combines features and generates various feature maps. In the next step, we reduce and select the most important features. Finally, the selected features are given to ANN to classify the data. The proposed method (LSTM + CNN + ANN) is compared with various classical machine-learning (ML) techniques. The experimental results show that the proposed method enhances the accuracy and precision on average by %8.6 and %8.4, respectively in compared to the classical ML techniques.
Article Details
This work is licensed under a Creative Commons Attribution 4.0 International License.
Tikrit Journal of Pure Science is licensed under the Creative Commons Attribution 4.0 International License, which allows users to copy, create extracts, abstracts, and new works from the article, alter and revise the article, and make commercial use of the article (including reuse and/or resale of the article by commercial entities), provided the user gives appropriate credit (with a link to the formal publication through the relevant DOI), provides a link to the license, indicates if changes were made, and the licensor is not represented as endorsing the use made of the work. The authors hold the copyright for their published work on the Tikrit J. Pure Sci. website, while Tikrit J. Pure Sci. is responsible for appreciate citation of their work, which is released under CC-BY-4.0, enabling the unrestricted use, distribution, and reproduction of an article in any medium, provided that the original work is properly cited.
References
[1] Md. Shafiur, R. et al. (2021). An efficient hybrid system for anomaly detection in social networks. springeropen.
[2] Keith, Henderson. et al. (2011). Graph Mining using Recursive Structural Features. San Diego, United States: p. 663–671.
[3] Akoglu, L.; McGlohon, M. and Faloutsos, a. C. (2010). Spotting Anomalies in Weighted Graphs. Advances in Knowledge Discovery and Data Mining, Volume 6119: p. 410–421.
[4] Abdolazim, R. et al. (2013). Anomaly Detection in Online Social Networks using Structure-Based Technique. London, UK, IEEE.
[5] Sujatha, A. K. and Balachandran, K. (2020). Self-Supervised Learning Based Anomaly Detection in Online social media. International Journal of Intelligent Engineering and Systems, 13(3).
[6] Nicholas, A. H. et al. (2010). Bayesian anomaly detection methods for social networks. The Annals of Applied Statistics.
[7] Renjun, H. et al. (2016). An embedding approach to anomaly detection. Helsinki, Finland, IEEE.
[8] M.Sai, S. L. Y.et al. (2017). Identifying Malicious Data in social media. International Research Journal of Engineering and Technology.
[9] Rose, Y.; Xinran, H. and Yan, L. (2015). Group Anomaly Detection in Social Media Analysis. ACM Journals, 10(2): 1–22.
[10] Anshika, C.; Himangi, M. and Anuja, A. (2019). Anomaly Detection using Graph Neural Networks. Faridabad, India, IEEE.
[11] Jing, G. et al. (2011). A spectral framework for detecting inconsistency across multi-source object relationships. Vancouver, BC, Canada, IEEE.
[12] Kumar, S. and Kamalika, D. (2014). Localizing anomalous changes in time evolving graphs. ACM SIGMOD: 1347-1358.
[13] Md. Shafiur, R. et al. (2021). An efficient hybrid system for anomaly detection in social networks. springeropen.
[14] Agovic, A. et al. (2009). Anomaly detection using manifold embedding and its applications in transportation corridors. Intelligent Data Analysis, 13(3): 435-455.
[15] Renjun, H. et al. (2016). An embedding approach to anomaly detection. Helsinki, Finland, IEEE.
[16] Abdolazim, R. et al. (2013). Anomaly Detection in Online Social Networks using Structure-Based Technique. London, UK, IEEE.
[17] Wenchao, Y. et al. (2018). A Flexible Deep Embedding Approach for Anomaly Detection in Dynamic Networks. London, United, Kingdom, ACM SIGKDD: p. 2672–2681.
[18] Luan, T.; Liyue, F. and Cyrus, S. (2016). Distance-based outlier detection in data streams. In: Proc. of the VLDB Endowment, 9(12): 1089–1100.
[19] Ahmet, Ş. D. (2019). ANOMALOUS ACTIVITY DETECTION FROM DAILY SOCIAL MEDIA USER MOBILITY DATA. Omer Halisdemir University Journal of Engineering Sciences, 8(2): 638 - 651.
[20] Sujatha, A. K. and Balachandran, K. (2020). Self-Supervised Learning Based Anomaly Detection in Online social media. International Journal of Intelligent Engineering and Systems, 13(3).
[21] Amogh, M.; Nisheeth, S. and Jaideep, S. (2012). Contextual Anomaly Detection in Text Data, 5(4): 469-489.
[22] Guixian, X. et al. (2019). Research on Topic Detection and Tracking for Online News Texts. IEEE Access, 30 April. Volume 7: 58407 - 58418.
[23] Ying, F. et al. (2014). Self-Adaptive Topic Model: A Solution to the Problem of ‘Rich Topics get Richer. China Communications, Dec, 11(12): 35 - 43.
[24] Than, T. W. and Sint, S. A. (2018). TPMTM: Topic Modeling over Papers' Abstract. Advances in Science, Technology and Engineering Systems Journal, Volume 3: 69-73.
[25] Brejit, L. A. and Anjana.P.Nair. (2018). Anomalous Topic Discovery Based on Topic Modeling from Document Cluster. International Research Journal of Engineering and Technology, Feb, 5(2): 966-972.
[26] MUHAMMAD, A. and SAJID, Y. B., (2015). Classifier ensembles using structural features for spammer detection in online social networks. Foundations of Computing and Decision Sciences, 40(2): 89-105.
[27] Carl, S. and Alta, d. W. (2016). Semi-supervised machine learning for textual anomaly detection. Stellenbosch, South Africa, IEEE: 1-5.
[28] Ravneet, K.; Sarbjeet, S. and Harish, K. (2018). AuthCom: Authorship Verification and Compromised Account Detection in Online Social Networks using AHP-TOPSIS Embedded Profiling based Technique. ELSEVIER, 15 December, Volume 113: 397-414.
[29] Mei, M. et al. (2018). Using Semantic Clustering and Auto Encoders for Detecting Novelty in Corpora of Short Texts. Rio de Janeiro, Brazil, IEEE: 1-8.
[30] Oliver, L. H. et al. (2017). Relationship Breakup Disclosures and Media Ideologies on Facebook. New Media & Society, 20(5): 1931-1952.
[31] Thin, N. et al. (2014). Affective and Content Analysis of Online Depression Communities. IEEE Transactions on Affective Computing, 5(3): 217 - 226.
[32] Randa, A. et al. (2019). Anomaly detection over differential preserved privacy in online social networks. Volume 14: 1-20.
[33] Savyan, P. and S. Mary, S. B., (2017). Behaviour Profiling of Reactions in Facebook Posts for Anomaly Detection. Chennai, India, IEEE.
[34] Anon. 2015. Kaggle. [Online]
Available at: https://www.kaggle.com/datasets/crowdflower/twitter-airline-sentiment