This is the case of Backstrom et al. [86] which, as discussed above, is not strictly speaking a generative model of discussion threads but a predictive model.
The next model under consideration, Backstrom et al. [86], is not strictly speaking a generative model of discussion threads, but proposes how to predict structural properties of a thread (e.g. size) by combining features of different nature.
Odds ratio (95% CI), logistic model of discussion and arm.
Aber, JD; Bernhardt, ES; Dijkstra, FA; Gardner, RH; Macneale, KH; Parton, WJ; Pickett, STA; Urban, DL; Weathers, KC, Standards of practice for review and publication of models: Summary of discussion, in Chapter 11 in The Role of Models in Ecosystem Science, edited by Canham, CD; Cole, JJ; Lauenroth, WK, Models in Ecosystem Science (January, 2003), pp. 204-210, PRINCETON UNIV PRESS [Gateway.cgi].cgi]
As we specified in the introduction, this is a survey on generative models of online discussion threads.
Despite the recent effort on surveying statistical graph models for social networks [7, 8], to our best knowledge, there is no formal review of generative models of online discussion threads.
Our article surveys generative models of online discussion threads, i.e. conversations from platforms corresponding to asynchronous communication (leafs of the left main branch of the tree) Synchronous communication.
A carefully designed syntax can increase the accessibility of models for discussion and presentation, especially for domain experts that are not extensively familiar with modeling and the underlying mathematical formalism.
In this model, the representation of discussion threads differs from the previous models.
At the other end, this modest but dense blog post is a model of intelligent discussion.
