Collaborative Information Retrieval: Frameworks, Theoretical Models, and Emerging Topics

Abstract

A great amount of research in the IR domain mostly dealt with both the design of enhanced document ranking models allowing search improvement through user-to-system collaboration. However, in addition to user-to-system form of collaboration, user-to-user collaboration is increasingly acknowledged as an effective mean for gathering the complementary skills and/or knowledge of individual users in order to solve complex search tasks. This tutorial will first give an overview of the ways into collaboration has been implemented in IR models with the attempt of improving the search outcomes with respect to several tasks and related frameworks (ad-hoc search, group-based recommendation, social search, collaborative search). Second, as envisioned in collaborative IR domain (CIR), we will focus on the theoretical models that support and drive user-to-user collaboration in order to perform shared IR tasks. Third, we will develop a road map on emerging and relevant topics addressing issues related to collaboration design. Our goal is to provide participants with concepts and motivation allowing them to investigate this emerging IR domain as well as giving them some clues on how to tackle issues related to the optimization of collaborative tasks. More specifically, the tutorial aims to: (a) Give an overview of the key concept of collaboration in IR and related research topics; (b) Present state-of-the art CIR techniques and models; (c) Discuss about the emerging topics that deal with collaboration; (d) Point out some challenges ahead.