Copy the page URI to the clipboard
Burel, Gregoire and He, Yulan
(2014).
DOI: https://doi.org/10.1145/2567948.2576949
Abstract
We describe the Joint Effort-Topic (JET) model and the Author Joint Effort-Topic (aJET) model that estimate the effort required for users to contribute on different topics. We propose to learn word-level effort taking into account term preference over time and use it to set the priors of our models. Since there is no gold standard which can be easily built, we evaluate them by measuring their abilities to validate expected behaviours such as correlations between user contributions and the associated effort.