The Web Science Trust

Peer-to-Peer Human Computation & “Help Me Decide”: Enabling search users to help other users make purchase decisions

Chandrasekar, Raman and Jain, Kamal (2010) Peer-to-Peer Human Computation & “Help Me Decide”: Enabling search users to help other users make purchase decisions. In: Proceedings of the WebSci10: Extending the Frontiers of Society On-Line, April 26-27th, 2010, Raleigh, NC: US.

[img] PDF (preprint) - Repository staff only - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
62Kb
[img]
Preview
PDF (Final Version) - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
681Kb

Abstract

In this paper, we propose the notion of Peer-to-Peer Human Computation, where users help each other, mediated by a platform that connects people who request help to people who offer help, acts as a repository of acquired information, and learns from users’ questions and advice. We compare this idea to related ideas such as human computation and social search. As an example, we describe a peer-to-peer human computation system named Help Me Decide, designed to assist search users make complex purchase decisions. We list design goals for such a system. We describe the architecture of this system, and detail a prototype of a subset of the Help Me Decide system that was developed and deployed to several hundred users in Microsoft. We discuss the incentive system we developed. We summarize the statistics collected on the usage of the Help Me Decide prototype and the results from a survey of the users. We contrast this system with other related systems. We conclude with some thoughts about next steps.

Item Type:Conference or Workshop Item (Paper)
Uncontrolled Keywords:purchase decisions, shopping, incentives, peer-to-peer human computation, search engines
Subjects:Web Science Events > Web Science 2010
ID Code:318
Deposited By: W S T Administrator
Deposited On:15 Mar 2010 10:09
Last Modified:25 Oct 2011 16:57

Repository Staff Only: item control page

EPrints Logo
Web Science Repository is powered by EPrints 3 which is developed by the School of Electronics and Computer Science at the University of Southampton. More information and software credits.