Targeted Advertising in Social Media Platforms Using Hybrid Convolutional Learning Method besides Efficient Feature Weights

• Published in: Journal of Electrical and Computer Engineering Vol. 2022; pp. 1 - 17
• Main Authors: Ebadi Jokandan, Seyed Mohsen, Bayat, Peyman, Farrokhbakht Foumani, Mehdi
• Format: Journal Article
• Language: English
• Published: New York Hindawi 10.10.2022; John Wiley & Sons, Inc; Hindawi Limited
• Subjects: Advertisements; Advertising; Advertising expenditures; Algorithms; Brand loyalty; Classification; Clustering; Datasets; Deep learning; Digital media; Machine learning; Marketing; Methods; Neural networks; Online advertising; Popularity; Social media; Social networks; Web site management software; Iran; Germany
• ISSN: 2090-0147; 2090-0155
• DOI: 10.1155/2022/6159650

Advertising has been one of the most effective and valuable marketing tools for many years. Utilizing social media networks to market and sell products is becoming increasingly prevalent. The greatest challenges in this industry are the high cost of providing content and posting it on social networks, maximizing ad efficiency, and limiting spam advertisements. User engagement rate is one of the most frequently employed metrics for measuring the effectiveness of social media advertisements. Previous research has not comprehensively analyzed the factors influencing engagement rate. To this end, it is necessary to investigate the impact of various factors (such as user characteristics, posts, emotions, relationships, images, and backgrounds, among others) on engagement rate because assessing these influential factors in different networks can increase the engagement of users with advertising posts and thereby increase the success rate of targeted advertising. To predict the user engagement rate, we extract the significant attributes of posts and introduce an adaptive hybrid convolutional model based on FW-CNN-LSTM. We cluster the selected data based on the weight and significance of their attributes using the FCM and XGBoost algorithms and then apply CNN- and LSTM-based methods to select similar features. Using accuracy, recall, F-measure, and precision metrics, we compared our algorithm to standard techniques such as SVM, Logistic regression, Naïve Bayes, and CNN. According to the findings, hashtag, brand ID, movie title, and actors achieve the highest scores, and the values for actual training time in various data ratios are relatively linear, which confirms the scalability of the proposed model for large datasets. The results also demonstrate that our proposed method outperforms others and can lead to targeted ads on social media.