Enhancing Personalized Ads Using Interest Category Classification of SNS Users Based on Deep Neural Networks.

摘要: The classification and recommendation system for identifying social networking site (SNS) users’ interests plays a critical role in various industries, particularly advertising. Personalized advertisements help brands stand out from the clutter of online while enhancing relevance to consumers generate favorable responses. Although most user interest studies have focused on textual data, combined analysis images texts user-generated posts can more precisely predict consumer’s interests. Therefore, this research classifies SNS by utilizing both images. Consumers’ were defined using Curlie directory, convolutional neural network (CNN)-based models recurrent (RNN)-based tested our system. In hybrid (NN) model, CNN-based used classify postings RNN-based data. results extensive experiments show that performed best when together, at 96.55%, versus only, 41.38%, or 93.1%. Our proposed provides insights into personalized advertising informs marketers making (1) interest-based recommendations, (2) ranked-order (3) real-time recommendations.