Behavior Prediction in Social Networks Using Feedforward Neural Network Algorithm
DOI:
https://doi.org/10.48001/978-81-980647-5-2-1Keywords:
Behavior prediction, Feedforward Neural Network, social networks, user interactionsAbstract
This study investigates the use of a Feedforward Neural Network (FNN) for predicting user behavior in social networks, leveraging a dataset derived from a popular social media platform. By analyzing various features, including user demographics, historical interactions, and content attributes, the FNN model was trained to classify user actions such as liking or sharing content. The model performance was evaluated using several metrics, including precision, accuracy, F1-score, and recall. The FNN achieved an accuracy of 87.5\%, a precision of 85.0\%, a recall of 90.0\%, and an F1-score of 87.5\%, outperforming other algorithms such as SVM and Decision Trees. FNN is proven highly effective for behavior prediction tasks, providing valuable discernments for social media strategies and user engagement approaches.
Downloads
References
Almazroi, A. A., Matarneh, R. A., & Alhussein, M. (2021). Predicting user interaction in social networks using deep learning. Computers, Materials & Continua, 67(3), 2743–2758. https://doi.org/10.32604/cmc.2021.014014
Ghadge, A., & Joshi, A. (2019). Social media user behavior prediction using machine learning techniques. International Journal of Computer Applications, 182(14), 6–12. https://doi.org/10.5120/ijca2019918506
Li, X., Yang, F., & Yu, H. (2023). Dynamic user behavior prediction using feedforward neural networks. IEEE Transactions on Neural Networks and Learning Systems, 34(3), 1562–1575. https://doi.org/10.1109/TNNLS.2022.3155843
Liu, J., Wu, D., & Hu, Y. (2021). A deep learning-based approach for user behavior prediction in social networks. IEEE Transactions on Network and Service Management, 18(2), 1393–1406. https://doi.org/10.1109/TNSM.2021.3061125
Liu, L., Sulaiman, N. I. S., Liu, F., Zhou, S., Huang, Z., Tan, Y., & Cao, C. (2024). Classification and identification of male hair loss based on deep learning. ACM International Conference Proceeding Series, 252–257. https://doi.org/10.1145/3665689.3665733
Ma, L., & Khorasani, K. (2003). A new strategy for adaptively constructing multilayer feedforward neural networks. Neurocomputing, 51(4), 361–385. https://doi.org/10.1016/S0925-2312(02)00597-0
Nascimento, J. P., Costa, E. C., & Marinho, M. (2020). User sentiment analysis for behavior prediction in social networks. Journal of Ambient Intelligence and Humanized Computing, 11(7), 2903–2915. https://doi.org/10.1007/s12652-020-02345-3
Sadiq, S. M., Ali, A., & Khokhar, R. A. (2019). A survey of user behavior prediction models in social networks. Journal of King Saud University - Computer and Information Sciences, 34(1), 1–15. https://doi.org/10.1016/j.jksuci.2019.01.002
Xu, R., & Yang, J. (2019). Behavior prediction based on social media data: A deep learning approach. IEEE Access, 7, 63730–63739. https://doi.org/10.1109/ACCESS.2019.2904822
Zhang, H., & Wang, H. (2020). Predicting user behavior in social networks: A deep learning approach. Journal of Network and Computer Applications, 164, 102710. https://doi.org/10.1016/j.jnca.2020.102710
Zhang, J., Zhao, M., & Huang, Q. (2021). Multimodal behavior prediction on social media using deep learning. Information Processing & Management, 58(5), 102616. https://doi.org/10.1016/j.ipm.2021.102616
