Can cascades be predicted?
Cheng, Adamic, Dow, Kleinberg and Leskovec build a framework for predicting how cascades of photo reshares grow on a large social network. Their models predict with good accuracy whether a cascade will keep growing, and prediction of relative growth improves as more reshares are observed. Temporal and structural features are the most useful for predicting final size, and early breadth is a better signal of eventual size than depth. For separate cascades of the same photo that reach different sizes, the models can still identify which will become the largest.
Cheng, Adamic, Dow, Kleinberg and Leskovec build a framework for predicting how cascades of photo reshares grow on a large social network. Their models predict with good accuracy whether a cascade will keep growing, and prediction of relative growth improves as more reshares are observed. Temporal and structural features are the most useful for predicting final size, and early breadth is a better signal of eventual size than depth. For separate cascades of the same photo that reach different sizes, the models can still identify which will become the largest.
Written from the abstract, arXiv record of the paper (1403.4608).
What our sources record
Recorded when this source was checked, figures included, with page references and quotation marks removed.
Proceedings of the 23rd International Conference on World Wide Web, 925-936. doi:10.1145/2566486.2567997 https://doi.org/10.1145/2566486.2567997