Why? Many workshops especially at WWW focus on the content analysis of social media, the big data mining of user-generated content or the social structure analysis of the users’ network. This workshop focuses on the very specific problem of managing Q&A sites and services that provide an important part of the content and interactions searched by users today to solve problems and make decisions.
The growth of Q&A web sites is challenging the automation and efficiency of the tools to manage them, moderate them, and search them. The growth of data and the diversity of users is challenging the automation of answer provision. These challenges are core to the sustainability of question-answering sites and services and to avoid these application collapse on themselves.
This kind of sites and services is now the reason why many people come to the Web and there specificities raise research questions for the WWW community in terms of efficient mining and searching of their structures (question threads, tags) and contributions (questions, answers, edits, votes) with dedicated approaches exploiting their specificities.
Audience and presentations? The workshop is directed to people that work on Natural Language Processing, Social Web, Knowledge Representation and Reasoning, Semantic Web and Linked Data, Conversational Agents, and Social Sciences. In particular, we want to reinforce the links existing between these different communities and supply new research opportunities to people that address question answering and activity analysis in participatory sites. We thus expect to attract attention from people having different profiles and we expect around 25 participants.
Workshop format: A full-day workshop organized into three sessions where papers selected by the workshop program committee will be presented and one session for an invited talk. Each session will be chaired with the aim of provoking discussion among all the participants, as we intend to keep the workshop spirit with time for discussion and questions. Discussions sessions will be led by the workshop organizers and the invited speaker. Based on the number of accepted papers, we plan to propose a special issue in a scientific journal of the field. We target 15 minute talks with 10 minutes questions. We will have 9 (=3*3) presentations and one invited talk synchronized with the four daily sessions and breaks of WWW workshops.
Submissions evaluation? The submission and reviews will follow a classical peer-review process using EasyChair. Each paper will be reviewed by at least three PC members.
Agenda of the Workshop – Monday 11th April 2016 :
Invited talk : Xavier Amatriain “Machine Learning for Q&A sites: state of the art and research directions”
“Enriching Topic Modelling with Users’ histories for Improving Tag Prediction in Q&A Systems” Johan Loeckx and Glenn Boudaer
“Which Answer is Best? Predicting Accepted Answers in MOOC Forums” Maximilian Jenders, Ralf Krestel and Felix Naumann
“Structural Normalisation Methods for Improving Best Answer Identification in Question Answering Communities” Gregoire Burel, Paul Mulholland and Harith Alani
“Identifying user issues and request types in forum question posts based on discourse analysis” Ágnes Sándor, Nikolaos Lagos, Ngoc-Phuoc-An Vo and Caroline Brun
“Using Semantics to Search Answers for Unanswered Questions in Q&A Forums” Priyanka Singh and Dr. Elena Simperl
“Question Answering on Linked Data: Challenges and Future Directions” Saeedeh Shekarpour, Denis Lukovnikov, Ashwini Jaya Kuma, Kemele M. Endris, Kuldeep Singh, Harsh Thakkar and Christoph Lange
16:00-17:30 OCKTOPUS ANR Project overview & Panel discussions