Citation :

R. Pushpavalli, Prabhu Rengaramanujam, I.Eugene Berna, D. Suseela, Dilli babu M, R.S.Vignesh, "Detection of Cyber Threats on Social Media using Optimized Sentiment-Aware Deep Learning Models," International Journal of Engineering Trends and Technology (IJETT), vol. 74, no. 3, pp. 336-352, 2026. Crossref, https://doi.org/10.14445/22315381/IJETT-V74I3P123

Abstract

In the modern age of digital society, the ramping up of cybercrime proves to be a severe issue that causes significant financial losses, emotional pain, and social impairment. Popularization of social media networking sites with possibilities of real-time communications and expressing oneself in society has seen an exponential increase in user content generated, which unfortunately has also led to the flourishing of negative actions like spreading fake news, cyberbullying, phishing, opinion spamming, and identity theft. These emerging threats are a very big threat to cyberspace security, privacy, and trust online, thus requiring smart and aggressive defense. To this end, this study proposes an exhaustive state of the cyber intelligence framework christened DSO-CAM-CDL that would identify/solve fake actions and threat-related sentiments that ensue on social network applications. The model also starts with the application of a new Dolphin-Sparrow Optimization method to acknowledge and pick the most relevant and high-impact features in large social media data. This refined set of features is then returned to the Customized Deep Learner (CDL), capable of doing sentiment analysis and behavioral prediction, using much higher precision and having much better computation speed. In order to further increase resilience and adaptive security, a Convoluted Auto-Encoding Memory (CAM) mechanism is added, which indicates that the system would learn complex patterns and anomalies that are specific to cyber threats. Experimental evaluation that is performed on a standard Twitter data demonstrates that the suggested DSO-CAM-CDL model performs extremely well, with accuracy of 99.1%, precision of 99%, recall of 98.9%, F1-score of 99% and specificity of 98.9%. The evaluation against other traditional classifiers like SVM, Naive Bayes, SVC, and CNN-LDA proves the evident advantage of the proposed model on all the assessment data.

Keywords

Cybercrime Detection, Sentiment Analysis, Social Media Security, Feature Optimization, Deep Learning, Auto-Encoding Memory Networks.

References

[1] Yanyan Wei et al., “Structural and Functional Abnormalities Across Clinical Stages of Psychosis: A Multimodal Neuroimaging Investigation,” Asian Journal of Psychiatry, vol. 99, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[2] Wenqian Shang et al., “Aspect-Level Sentiment Analysis based on Aspect-Sentence Graph Convolution Network,” Information Fusion, vol. 104, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[3] Kate Sherren et al., “Social Media and Social Impact Assessment: Evolving Methods in a Shifting Context,” Current Sociology, vol. 72, no. 4, pp. 630-648, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[4]  Muhammad Zulqarnain et al., “An Efficient Two-State GRU based on Feature Attention Mechanism for Sentiment Analysis,” Multimedia Tools and Applications, vol. 83, no. 1, pp. 3085-3110, 2022.
[CrossRef] [Google Scholar] [Publisher Link]

[5] Sanur Sharma, and Anurag Jain, “Role of Sentiment Analysis in Social Media Security and Analytics,” Wiley Interdisciplinary Reviews: WIRE’s Data Mining and Knowledge Discovery, vol. 10, no. 5, pp. 1-27, 2020.
[CrossRef] [Google Scholar] [Publisher Link]

[6] V. Ragu, and P. Jesu Jayarin, “Detecting Flooding Attacks in Distributed Denial of Service using Deep Neural Network Compared with Decision Tree,” AIP Conference Proceedings, vol. 3267, no. 1, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[7] Jose Ramon Saura, Domingo Ribeiro-Soriano, and Daniel Palacios-Marqués, “Evaluating Security and Privacy Issues of Social Networks based Information Systems in Industry 4.0,” Enterprise Information Systems, vol. 16, no. 10-11, pp. 1694-1710, 2022.
[CrossRef] [Google Scholar] [Publisher Link]

[8] Pratham Shah et al., “A Comprehensive Review on Sentiment Analysis of Social/Web Media Big Data for Stock Market Prediction,” International Journal of System Assurance Engineering and Management, vol. 15, no. 6, pp. 2011-2018, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[9] V. Ragu, and P. Jesu Jayarin, “Detecting Flooding Attacks in Distributed Denial of Service Attacks using Deep Neural Network Compared with Recurrent Neural Network,” AIP Conference Proceedings, vol. 3193, no. 1, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[10] Jose Ramon Saura, Daniel Palacios-Marqués, and Domingo Ribeiro-Soriano, “Using Data Mining Techniques to Explore Security Issues in Smart Living Environments in Twitter,” Computer Communications, vol. 179, pp. 285-295, 2021.
[CrossRef] [Google Scholar] [Publisher Link]

[11] Hussain AlSalman, “An Improved Approach for Sentiment Analysis of Arabic Tweets in Twitter Social Media,” 2020 3^rd International Conference on Computer Applications and Information Security (ICCAIS), Riyadh, Saudi Arabia, pp. 1-4, 2020.
[CrossRef] [Google Scholar] [Publisher Link]

[12] Anna Golebiowska et al., “Cybersecurity of Business Intelligence Analytics based on the Processing of Large Sets of Information with the Use of Sentiment Analysis and Big Data,” European Research Studies Journal, vol. 24, no. 4, pp. 850-871, 2021.
[CrossRef] [Google Scholar] [Publisher Link]

[13] Mohammed Al-Shabi, “Evaluating the Performance of the Most Important Lexicons Used to Sentiment Analysis and Opinions Mining,” International Journal of Computer Science and Network Security (IJCSNS), vol. 20, no. 1, pp. 51-57, 2020.
[Google Scholar] [Publisher Link]

[14] Sheela Pitta, S. Gopalakrishnan, and S. Ravi Chand, “Securing WSN-IoT Networks using SwinAlert-GAN: A Deep Learning-based Intrusion Detection Framework,” 2025 Third International Conference on Augmented Intelligence and Sustainable Systems (ICAISS), Trichy, India, pp. 211-218, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[15] Sulaiman Ainin et al., “Sentiment Analyses of Multilingual Tweets on Halal Tourism,” Tourism Management Perspectives, vol. 34, pp. 1-8, 2020.
[CrossRef] [Google Scholar] [Publisher Link]

[16] Kristian Bondo Hansen, and Christian Borch, “Alternative Data and Sentiment Analysis: Prospecting Non-Standard Data in Machine Learning-Driven Finance,” Big Data and Society, vol. 9, no. 1, pp. 1-14, 2022.
[CrossRef] [Google Scholar] [Publisher Link]

[17] Prajval Sudhir, and Varun Deshakulkarni Suresh, “Comparative Study of Various Approaches, Applications and Classifiers for Sentiment Analysis,” Global Transitions Proceedings, vol. 2, no. 2, pp. 205-211, 2021.
[CrossRef] [Google Scholar] [Publisher Link]

[18] Wang Yue, and Lei Li, “Sentiment Analysis using Word2vec-CNN-BiLSTM Classification,” 2020 Seventh International Conference on Social Networks Analysis, Management and Security (SNAMS), Paris, France, pp. 1-5, 2020.
[CrossRef] [Google Scholar] [Publisher Link]

[19] Qianwen Ariel Xu, Victor Chang, and Chrisina Jayne, “A Systematic Review of Social Media-based Sentiment Analysis: Emerging Trends and Challenges,” Decision Analytics Journal, vol. 3, pp. 1-16, 2022.
[CrossRef] [Google Scholar] [Publisher Link]

[20] Mohd Suhairi Md Suhaimin et al., “Social Media Sentiment Analysis and Opinion Mining in Public Security: Taxonomy, Trend Analysis, Issues and Future Directions,” Journal of King Saud University - Computer and Information Sciences, vol. 35, no. 9, pp. 1-25, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[21] Mansour Alshaikh et al., “Social Network Analysis and Mining: Privacy and Security on Twitter,” 2020 10^th Annual Computing and Communication Workshop and Conference (CCWC), Las Vegas, NV, USA, pp. 0712-0718, 2020.
[CrossRef] [Google Scholar] [Publisher Link]

[22] Hameedur Rahman et al., “Multi-Tier Sentiment Analysis of Social Media Text using Supervised Machine Learning,” Computational and Mathematical Methods in Medicine, vol. 74, no. 3, pp. 5527-5543, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[23] Staphord Bengesi et al., “A Machine Learning-Sentiment Analysis on Monkeypox Outbreak: An Extensive Dataset to Show the Polarity of Public Opinion from Twitter Tweets,” IEEE Access, vol. 11, pp. 11811-11826, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[24] Hamed Taherdoost, and Mitra Madanchian, “Artificial Intelligence and Sentiment Analysis: A Review in Competitive Research,” Computers, vol. 12, no. 2, pp. 1-15, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[25] José Ramón Trillo et al., “A Larg Scale Group Decision Making System based on Sentiment Analysis Cluster,” Information Fusion, vol. 91, pp. 633-643, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[26] Thanveer Shaik et al., “Sentiment Analysis and Opinion Mining on Educational Data: A Survey,” Natural Language Processing Journal, vol. 2, pp. 1-11, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[27] Mohammed Boukabous, and Mostafa Azizi, “Review of Learning-based Techniques of Sentiment Analysis for Security Purposes,” Innovations in Smart Cities Applications: The Proceedings of the 5^th International Conference on Smart City Applications, Safranbolu, Turkey, vol. 183, pp. 96-109, 2021.
[CrossRef] [Google Scholar] [Publisher Link]

[28] Chiara Zucco et al., “Sentiment Analysis for Mining Texts and Social Networks Data: Methods and Tools,” Wiley Interdisciplinary Reviews: WIRE’s Data Mining and Knowledge Discovery, vol. 10, no. 1, 2020.
[CrossRef] [Google Scholar] [Publisher Link]

[29] Ankit Kumar Jain, Somya Ranjan Sahoo, and Jyoti Kaubiyal, “Online Social Networks Security and Privacy: Comprehensive Review and Analysis,” Complex Intelligent Systems, vol. 7, no. 5, pp. 2157-2177, 2021.
[CrossRef] [Google Scholar] [Publisher Link]

[30] Pradeep Mani, and Gopalakrishnan Subburayalu, “Enhancing Network Security with Memory-Augmented Visual Attention Networks and Predator-Prey Optimization Models,” Iran Journal of Computer Science, vol. 8, no. 3, pp. 893-912, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[31] Nandita Pattnaik, Shujun Li, and Jason R.C. Nurse, “Perspectives of Non-Expert users on Cyber Security and Privacy: An Analysis of Online Discussions on Twitter,” Computers and Security, vol. 125, pp. 1-15, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[32] Fethi Fkih, and Ghadeer Al-Turaif, “Threat Modelling and Detection using Semantic Network for Improving Social Media Safety,” International Journal of Computer Network and Information Security (IJCNIS), vol. 15, no. 1, pp. 39-53, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[33] Linli Wang, Hu Wang, and Hanlu Lei, “Public Sentiment Analysis of Social Security Emergencies based on Feature Fusion Model of BERT and TextLevelGCN,” Journal of Computer and Communications, vol. 11, no. 5, pp. 194-204, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[34] Jeong-Ha Park, and Hyuk-Yoon Kwon, “Cyberattack Detection Model using Community Detection and Text Analysis on Social Media,” ICT Express, vol. 8, no. 4, pp. 499-506, 2022.
[CrossRef] [Google Scholar] [Publisher Link]

[35] Renato Marinho, and Raimir Holanda, “Automated Emerging Cyber Threat Identification and Profiling based on Natural Language Processing,” IEEE Access, vol. 11, pp. 58915-58936, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[36] Yong Fang et al., “Detecting Cyber Threat Event from Twitter using IDCNN and BiLSTM,” Applied Sciences, vol. 10, no. 17, pp. 1-10, 2020.
[CrossRef] [Google Scholar] [Publisher Link]

[37] Jun Zhao et al., “Timiner: Automatically Extracting and Analyzing Categorized Cyber Threat Intelligence from Social Data,” Computers and Security, vol. 95, pp. 1-27, 2020.
[CrossRef] [Google Scholar] [Publisher Link]

[38] Fahim Sufi, “A New Social Media-Driven Cyber Threat Intelligence,” Electronics, vol. 12, no. 5, 1-21, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[39] Fahim Sufi, “A New AI-based Semantic Cyber Intelligence Agent,” Future Internet, vol. 15, no. 7, pp. 1-27, 2023.
[CrossRef] [Google Scholar] [Publisher Link]