Characterizing and curating conversation threads

Abstract

Discussion threads form a central part of the experience on many Web sites, including social networking sites such as Facebook and Google Plus and knowledge creation sites such as Wikipedia. To help users manage the challenge of allocating their attention among the discussions that are relevant to them, there has been a growing need for the algorithmic curation of on-line conversations -the development of automated methods to select a subset of discussions to present to a user.Here we consider two key sub-problems inherent in conversational curation: length prediction -predicting the number of comments a discussion thread will receive -and the novel task of reentry prediction -predicting whether a user who has participated in a thread will later contribute another comment to it. The first of these sub-problems arises in estimating how interesting a thread is, in the sense of generating a lot of conversation; the second can help determine whether users should be kept notified of the progress of a thread to which they have already contributed. We develop and evaluate a range of approaches for these tasks, based on an analysis of the network structure and arrival pattern among the participants, as well as a novel dichotomy in the structure of long threads. We find that for both tasks, learning-based approaches using these sources of information yield improvements for all the performance metrics we used.

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

“…It can be used as well on the same underlying platform to compare different user communities but for example in different language versions or different spheres of interest, which allows then to measure the impact of a specific topic or cultural aspect. Four of the generative models surveyed in this article: Kumar et al [83], Wang et al [84], Gómez et al [85], and Backstrom et al [86] were validated in this respect with data from multiple online discussion platforms.…”

“…• Kumar et al [83] • Wang et al [84], • Gómez et al [85] • Backstrom et al [86] • Nishi et al [87] • Lumbreras [88] • Aragón et al [89] The selection of these models is based on the consideration of Kumar et al [83] as the first generative model for online discussion threads. The rest of the models in the survey were selected after examining the publications citing this work in Scopus (52 papers) and Google Scholar (92 papers) 2 , and including the studies which proposed a generative model for the structure and growth of online discussion threads.…”

“…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.…”

“…The model is motivated by observing that the structure of discussion threads is characterized by some long path-like reply trees, large star-like trees, and long irregular trees. Actually, some of the previous models already denoted long path-like reply trees as 'skinny' in Kumar et al [83] or 'focused' in Backstrom et al [86], and large star-like trees as 'bushy' in Kumar et al [83] or 'expansionary' Backstrom et al [86]. Because many of the previous models are based on the branching process model which does not capture appropriately long chains of messages in discussion threads, the depth distribution is often underestimated, as noted in Kumar et al [83] and Gómez et al [85].…”

Predicting Instructor's Intervention in MOOC forums

“…Our work is most closely related to that of Backstrom et al (2013) which introduced the re-entry prediction task -predicting whether a user who has participated in a thread will later contribute another comment to it. While seemingly related, their prediction task, focusing on users who have already commented on a thread, and their algorithmic approach are different than ours.…”