Answering Twitter Questions: a Model for Recommending Answerers through Social Collaboration - Sorbonne Université Access content directly
Conference Papers Year : 2016

Answering Twitter Questions: a Model for Recommending Answerers through Social Collaboration

Abstract

In this paper, we specifically consider the challenging task of solving a question posted on Twitter. The latter generally remains unanswered and most of the replies, if any, are only from members of the questioner's neighborhood. As outlined in previous work related to community Q&A, we believe that question-answering is a collaborative process and that the relevant answer to a question post is an aggregation of answer nuggets posted by a group of relevant users. Thus, the problem of identifying the relevant answer turns into the problem of identifying the right group of users who would provide useful answers and would possibly be willing to collaborate together in the long-term. Accordingly, we present a novel method, called CRAQ, that is built on the collaboration paradigm and formulated as a group entropy optimization problem. To optimize the quality of the group, an information gain measure is used to select the most likely " informative " users according to topical and collaboration likelihood predictive features. Crowd-based experiments performed on two crisis-related Twitter datasets demonstrate the effectiveness of our collaborative-based answering approach.
Fichier principal
Vignette du fichier
cameraready.pdf (642.59 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01353587 , version 1 (12-08-2016)

Identifiers

Cite

Laure Soulier, Lynda Tamine, Gia-Hung Nguyen. Answering Twitter Questions: a Model for Recommending Answerers through Social Collaboration. CIKM 2016 - 25th ACM International Conference on Information and Knowledge Management, Oct 2016, Indianapolis, United States. pp.267-276, ⟨10.1145/2983323.2983771⟩. ⟨hal-01353587⟩
325 View
461 Download

Altmetric

Share

Gmail Facebook X LinkedIn More