Frequency-Domain Popularity Forecasting with Shape-Based Retrieval

Abstract

In recent years, social media popularity forecasting has become a research hotspot. There are two mainstream methods: cascade-based and sequence-based ones. Cascade-based methods are inefficient for large-scale data because of the cascade-graph representation and learning, while sequence-based methods face challenges in capturing global temporal features due to the inputs of short time series. Actually, there exists strong correlated history data with the new short input. What’s more, the complete trend information in similar historical data contain rich temporal feature for the popularity prediction, which often neglects in the existing methods. Thus, this paper proposes a Frequency-domain Popularity Forecasting model based on Shape Retrieval (FPF-SR). A shape similarity retrieval is used in FPF-SR to select strong correlated history data efficiently with only the new short input. Furthermore, from the retrieved history data and the new post, FPF-SR extracts the inter-sequence and temporal features in the frequency domain. Therefore, FPF-SR uses not only the complete history trend information but also the frequency features for popularity forecasting. Detailedly FPF-SR first retrieves the top K relevant sequences from historical data based on shape correlation, then applies a Fourier transform to the retrieved target sequences, and finally extracts and fuses similar information through linear operations in the frequency domain. Additionally, multi-point trend forecasting is introduced to improve the accuracy of single-point predictions. Experimental results demonstrate that FPF-SR achieves excellent forecasting performance on four real-world datasets. Code is available at: https://anonymous.4open.science/r/FPF-SR-AE10.