ICTACT Journal on Image and Video Processing

Open Access Open Access  Restricted Access Subscription Access
Open Access Open Access Open Access  Restricted Access Restricted Access Subscription Access

Classification of Social Media Content and Improved Community Detection (C&CD) Using VGGNet Learning and Analytics


Affiliations
1 Department of Electronics and Telecommunications Engineering, MIT Academy of Engineering, India
2 Department of Computer Science, Johns Hopkins University, United States
3 Department of Artificial Intelligence and Machine Learning, Excel Engineering College, India
4 Department of Electronics and Communication Engineering, Roever Engineering College, India
     

   Subscribe/Renew Journal


Social media platforms generate vast amounts of data, necessitating efficient content classification and community detection methods. This study addresses this challenge through the utilization of VGGNet analytics, a powerful deep learning architecture. We employed a two-step approach, beginning with VGGNet-based content classification to categorize social media posts. Subsequently, a community detection algorithm was applied to identify distinct user groups based on their interactions and content preferences. This research contributes an novel framework that seamlessly integrates VGGNet for content analysis and community detection, enhancing the understanding of user behavior in social media platforms. The proposed method aims to provide more accurate and insightful results compared to traditional approaches. Our experiments on diverse social media datasets demonstrate the effectiveness of the VGGNet-based approach. The content classification accurately assigns posts to relevant categories, while the community detection algorithm identifies cohesive user groups. The results highlight the potential for improved content recommendation systems and targeted marketing strategies.

Keywords

Community Detection, Content Classification, Social Media, VGGNet Analytics, Deep Learning.
Subscription Login to verify subscription
User
Notifications
Font Size

  • D. Rogers and I. Spasic, “Real-Time Text Classification of User-Generated Content on Social Media: Systematic Review”, IEEE Transactions on Computational Social Systems, Vol. 9, No. 4, pp. 1154-1166, 2021.

  • C. Southerton and R. Cover, “Restricted Modes: Social Media, Content Classification and LGBTQ Sexual Citizenship”, New Media and Society, Vol. 23, No. 5, pp. 920-938, 2021.

  • A. Kumar, Y.K. Dwivedi and N.P. Rana, “A Deep Multi-Modal Neural Network for Informative Twitter Content Classification during Emergencies”, Annals of Operations Research, Vol. 76, pp. 1-32, 2020.

  • R. Rivas, Y. Guo and V. Hristidis, “Classification of Health-Related Social Media Posts: Evaluation of Post Content-Classifier Models and Analysis of User Demographics”, JMIR Public Health and Surveillance, Vol. 6, No. 2, pp. 1-13, 2020.

  • Z. Shahbazi and D.C. Lee, “Toward Representing Automatic Knowledge Discovery from Social Media Contents based on Document Classification”, International Journal on Advance Science and Technology, Vol. 29, pp. 14089-14096, 2020.

  • A. Bhardwaj, “Sentiment Analysis and Text Classification for Social Media Contents using Machine Learning Techniques”, Proceedings of International Conference on IoT, Social, Mobile, Analytics and Cloud in Computational Vision and Bio Engineering, pp. 1-12, 2020.

  • I.H. Ting and C.S. Yen, “Towards Automatic Generated Content Website based on Content Classification and Auto-Article Generation”, Proceedings of IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, pp. 436-438, 2021.

  • M.A. Al Garadi and A. Sarker, “Text Classification Models for the Automatic Detection of Nonmedical Prescription Medication use from Social Media”, BMC Medical Informatics and Decision Making, Vol. 21, No. 1, pp. 1-13, 2021.

  • T. Xiang and N. Goharian, “ToxCCIn: Toxic Content Classification with Interpretability”, Proceedings of International Conference on Artificial Intelligence, pp. 1-8, 2021.

  • A.S. Raamkumar and H.L. Wee, “Use of Health Belief Model-Based Deep Learning Classifiers for Covid-19 Social Media Content to Examine Public Perceptions of Physical Distancing: Model Development and Case Study”, JMIR Public Health and Surveillance, Vol. 6, No. 3, pp. 1-12, 2020.

  • D. Kumar and M. Bailey, “Designing Toxic Content Classification for a Diversity of Perspectives”, Proceedings of 17th Symposium on Usable Privacy and Security, pp. 299-318, 2021.

  • S.D. Rane, “Social Media Content Analysis and Classification using Data Mining and ML”, International Journal of Data Analytics, Vol. 2, No. 2, pp. 75-84, 2021.


Abstract Views: 31

PDF Views: 0




  • Classification of Social Media Content and Improved Community Detection (C&CD) Using VGGNet Learning and Analytics

Abstract Views: 31  |  PDF Views: 0

Authors

Vishal Gangadhar Puranik
Department of Electronics and Telecommunications Engineering, MIT Academy of Engineering, India
V. Saravanan
Department of Computer Science, Johns Hopkins University, United States
P. Selvaraju
Department of Artificial Intelligence and Machine Learning, Excel Engineering College, India
R. Janaki
Department of Electronics and Communication Engineering, Roever Engineering College, India

Abstract


Social media platforms generate vast amounts of data, necessitating efficient content classification and community detection methods. This study addresses this challenge through the utilization of VGGNet analytics, a powerful deep learning architecture. We employed a two-step approach, beginning with VGGNet-based content classification to categorize social media posts. Subsequently, a community detection algorithm was applied to identify distinct user groups based on their interactions and content preferences. This research contributes an novel framework that seamlessly integrates VGGNet for content analysis and community detection, enhancing the understanding of user behavior in social media platforms. The proposed method aims to provide more accurate and insightful results compared to traditional approaches. Our experiments on diverse social media datasets demonstrate the effectiveness of the VGGNet-based approach. The content classification accurately assigns posts to relevant categories, while the community detection algorithm identifies cohesive user groups. The results highlight the potential for improved content recommendation systems and targeted marketing strategies.

Keywords


Community Detection, Content Classification, Social Media, VGGNet Analytics, Deep Learning.

References