Generative models of online discussion threads: state of the art and research challenges

Abstract

Online discussion in form of written comments is a core component of many social media platforms. It has attracted increasing attention from academia, mainly because theories from social sciences can be explored at an unprecedented scale. This interest has led to the development of statistical models which are able to characterize the dynamics of threaded online conversations. In this paper, we review research on statistical modeling of online discussions, in particular, we describe current generative models of the structure and growth of discussion threads. These are parametrized network formation models that are able to generate synthetic discussion threads that reproduce certain features of the real discussions present in different online platforms. We aim to provide a clear overview of the state of the art and to motivate future work in this relevant research field.

Analyzing Wikipedia Deletion Debates with a Group Decision-Making Forecast Model

“…This activity has value -for instance, citing policies on article talk pages does influence editing behavior [48] -but ingrained norms and expectations can have an effect of preventing new or underserved users from meaningfully contributing to Wikipedia [36]. In particular, Wikipedia's editor culture has a highly visible and discussed gender gap 3 . An early study found that among the 3% of site editors who self-reported gender, only 9% of edits are made by women [40].…”

“…These votes are public, signed, and timestamped. Users can also make non-voting comments, either in direct reply to the nomination, or in reply to a vote or other comments, in the standard "reply tree" model of online discussion forums [3]. AfD is highly active, with more than one third of all articles in the English-language administrative namespace Wikipedia: related to deletion debates.…”

Impact of network density on cascade size and community growth

“…They demonstrated that TRF events can create dense user communities. There have been several studies that focused on link-creation events such as triadic closure (Leskovec et al 2008), shortcuts , homophily (Hours et al 2016;Aragón et al 2017), and social influence (Aragón et al 2017). This paper formulates a retweet diffusion model based on TRF events because the events express general content sharing and link creation dynamics on Twitter.…”

Differences in structure and dynamics of networks retrieved from dark and public web forums

“…The huge increase in the number of users of forums as time goes on have lead researchers to study the type and structure of the resulting interactions [12]. Many statistical models have been developed [13,14,15] for characterizing the dynamics of online discussions [16,17,18] and understanding the structure of threads and the resulting networks [19]. Some of them have been aiming at the prediction of the dynamics of threads and user behaviour [20,17].…”