Anytime User Engagement Prediction in Information Cascades for Arbitrary Observation Periods
Keywords:APP: Social Networks, DMKM: Mining of Spatial, Temporal or Spatio-Temporal Data, ML: Applications, ML: Probabilistic Methods, ML: Time-Series/Data Streams
AbstractPredicting user engagement -- whether a user will engage in a given information cascade -- is an important problem in the context of social media, as it is useful to online marketing and misinformation mitigation just to name a couple major applications. Based on split population multi-variate survival processes, we develop a discriminative approach that, unlike prior works, leads to a single model for predicting whether individual users of an information network will engage a given cascade for arbitrary forecast horizons and observation periods. Being probabilistic in nature, this model retains the interpretability of its generative counterpart and renders count prediction intervals in a disciplined manner. Our results indicate that our model is highly competitive, if not superior, to current approaches, when compared over varying observed cascade histories and forecast horizons.
How to Cite
Aravamudan, A., Zhang, X., & Anagnostopoulos, G. C. (2023). Anytime User Engagement Prediction in Information Cascades for Arbitrary Observation Periods. Proceedings of the AAAI Conference on Artificial Intelligence, 37(4), 4999-5009. https://doi.org/10.1609/aaai.v37i4.25627
AAAI Technical Track on Domain(s) of Application