Predicting the Popularity of Online Videos via Deep Neural Networks
This addresses a problem for video streaming content providers, but it appears incremental as it builds on existing neural network approaches with specific modules.
The paper tackled predicting online video popularity, a challenging problem due to its wide and deep nature and multiple competitors, by proposing a model using multi-task learning and relation network modules, which significantly increased accuracy for total view counts of TV series.
Predicting the popularity of online videos is important for video streaming content providers. This is a challenging problem because of the following two reasons. First, the problem is both "wide" and "deep". That is, it not only depends on a wide range of features, but also be highly non-linear and complex. Second, multiple competitors may be involved. In this paper, we propose a general prediction model using the multi-task learning (MTL) module and the relation network (RN) module, where MTL can reduce over-fitting and RN can model the relations of multiple competitors. Experimental results show that our proposed approach significantly increases the accuracy on predicting the total view counts of TV series with RN and MTL modules.