Knowledge-based Temporal Fusion Network for Interpretable Online Video Popularity Prediction
Authors:
Open Access
- 25 April 2022
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 2879-2887
Abstract
Predicting the popularity of online videos has many real-world applications, such as recommendation, precise advertising, and edge caching strategies. Despite many efforts have been dedicated to the online video popularity prediction, there still exist several challenges: (1) The meta-data from online videos is usually sparse and noisy, which makes it difficult to learn a stable and robust representation. (2) The influence of content features and temporal features in different life cycles of online videos is dynamically changing, so it is necessary to build a model that can capture the dynamics. (3) Besides, there is a great need to interpret the predictive behavior of the model to assist administrators of video platforms in the subsequent decision-making. In this paper, we propose a Knowledge-based Temporal Fusion Network (KTFN) that incorporates knowledge graph representation to address the aforementioned challenges in the task of online video popularity prediction. To be more specific, we design a Tree Attention Network (TAN) to learn the embedding of online video entities in knowledge graphs via selectively aggregating local neighborhood information, thus enabling our model to learn the importance of different entities under the same relation. Besides, an Attention-based Long Short-Term Memory (ALSTM) is utilized to learn the temporal feature representation. Finally, we propose an Adaptively Temporal Feature Fusion (ATFF) scheme to adaptively fuse content features and temporal features, in which a learnable exponential decay function with the global attention mechanism is constructed. We collect two large-scale real-world datasets from the server logs of two popular Chinese online video platforms, and experimental results on the two datasets have demonstrated the superiority and interpretability of KTFN.Keywords
This publication has 24 references indexed in Scilit:
- DeepHawkes2017
- Expecting to be HIP2017
- Recurrent Marked Temporal Point Processes2016
- Attention-based LSTM for Aspect-level Sentiment Classification2016
- SEISMIC2015
- Predicting the Popularity of Online Serials with Autoregressive Models2014
- What makes an image popular?2014
- Using early view patterns to predict the popularity of youtube videos2013
- Predicting popular messages in Twitter2011
- A self-correcting point processStochastic Processes and their Applications, 1979