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

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