Abstract
Predicting the popularity of online content is an important task for content recommendation, social influence prediction and so on. Recent deep learning models generally utilize graph neural networks to model the complex relationship between information cascade graph and future popularity, and have shown better prediction results compared with traditional methods. However, existing models adopt simple graph pooling strategies, e.g., summation or average, which prone to generate inefficient cascade graph representation and lead to unsatisfactory prediction results. Meanwhile, they often overlook the temporal information in the diffusion process which has been proved to be a salient predictor for popularity prediction. To focus attention on the important users and exclude noises caused by other less relevant users when generating cascade graph representation, we learn the importance coefficient of users and adopt sample mechanism in graph pooling process. In order to capture the temporal features in the diffusion process, we incorporate the inter-infection duration time information into our model by using LSTM neural network. The results show that temporal information rather than cascade graph information is a better predictor for popularity. The experimental results on real datasets show that our model significantly improves the prediction accuracy compared with other state-of-the-art methods.
Highlights
Online social platforms such as Facebook, Twitter, Sina Weibo and Tiktok, promote and widen the spread of online contents by attracting an increasing number of active users
We formulate the cascade prediction task as a regression problem which aims at predicting the number of users who will participate in the propagation of an online content, i.e., the size of information cascade
In the graph pooling process, we emphasize the important users and exclude the noise brought by less relevant users by supervised learning the importance coefficient for each user. (b) Temporal representation: we use the widely adopted Long Short Term Memory (LSTM) model and sample mechanism to generate the temporal representation from the inter-infection duration time information. (c) Predictor: as a regression problem, we concatenate the cascade graph representation and temporal representation, and feed the embedding into multi-layer perceptrons (MLPs) to make the popularity prediction
Summary
Online social platforms such as Facebook, Twitter, Sina Weibo and Tiktok, promote and widen the spread of online contents by attracting an increasing number of active users. Predicting the popularity of online content is a hot research topic in recent years. Feature-based approaches identify and extract hand-crafted features, including content features [26,27], structural features [22,28], temporal features [12,29], etc., and use machine learning algorithms to Axioms 2021, 10, 159 make predictions. This type of approaches usually require heavy feature-engineering and their performance strongly depends on the effectiveness of extracted features. Generative approaches devote to model the diffusion process by probabilistic statistical generative approaches, e.g., epidemic models [30,31] and point processes [17,32,33,34], but the performance is normally limited by its strong assumptions of underlying diffusion mechanisms
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
