Popularity Prediction of Online Contents via Cascade Graph and Temporal Information

Predicting the popularity of online content is an important task for recommendation, social influence prediction and so on. Recent deep learning models generally utilize graph neural networks to model complex relationship between information cascade future popularity, have shown better results compared with traditional methods. However, existing adopt simple pooling strategies, e.g., summation or average, which prone generate inefficient representation lead unsatisfactory results. Meanwhile, they often overlook temporal in diffusion process has been proved be a salient predictor prediction. To focus attention on users exclude noises caused by other less relevant when generating representation, we learn importance coefficient sample mechanism process. In order capture features process, incorporate inter-infection duration time into our using LSTM network. The show that rather than popularity. experimental real datasets significantly improves accuracy state-of-the-art