AFRF: Angle Feature Retrieval Based Popularity Forecasting

Haoyu Wang, Zongxia Xie, Meiyao Liu, Canhua Guan

Abstract: Social media popularity forecasting has become a hot research topic in recent years. It is of great significance in assisting public opinion monitoring and advertising placement. Time series prediction is one of the simple and commonly used methods for popularity forecasting, which takes the popularity of the first few time steps in the observed data as inputs. However, the complete popularity trend of each social media is known in the training dataset, while the historical time series information except for the first few time steps is neglected in the existing models. In order to utilize the complete historical information from the observed data, a retrieval method is introduced in this paper. Therefore, how to retrieve similar social media based on the first few steps time series and how to integrate the similar historical information have become two challenges. A two-stage prediction method named Angle Feature Retrieval based Forecasting (AFRF) is proposed in this paper to solve the upper two problems. In the first stage, based on the angle features of series, we retrieve K similar series from the historical posts and concatenate them with the target series as the model's input. In the second stage, an attention mechanism is used to learn the temporal relationships among the series and generate future popularity forecasts. We evaluated the multi-step and single-point forecasting performance of AFRF on three real-world datasets and compared it with state-of-the-art popularity forecasting methods, such as temporal feature-based and cascade-based methods, verifying the effectiveness of AFRF.