Place-aware content selection from dynamic web sources for public displays

• Author(s): Ribeiro, F. Reinaldo ; José, Rui
• Date: 2009
• Persistent ID: http://hdl.handle.net/10400.11/574
• Origin: Repositório Científico do Instituto Politécnico de Castelo Branco
• Subject(s): Dynamic sources; Information integration; Public displays; Situated displays; Social information systems; Web information filtering and retrieval; Web 2.0.
• Document Type: Article
• Language: English

Description

“Copyright © [2009] IEEE. Reprinted from 5th International Conference on Signal-Image Technology & Internet-Based Systems. ISBN:978-1-4244-5740-3. This material is posted here with permission of the IEEE. Internal or personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution must be obtained from the IEEE by writing to [e-mail]. By choosing to view this document, you agree to all provisions of the copyright laws protecting it.” Public digital displays could greatly benefit from the ability to dynamically select from the Internet content items that would be strongly related with the place where each display is installed. Generically, this is similar to the type of problem addressed by recommender systems. However, the usage context of a public display raises specific challenges that may limit the applicability of existing recommender systems. In this paper, we explore the creation of a recommender system for public situated displays that is able to autonomously select relevant content from Internet sources using keywords as input. This type of recommender system should enable public displays to become devices for Internet information delivery in public spaces, while also making them more situated in the social settings in which they are installed. We have created a recommender system based on these principles and we have conducted two studies to evaluate the perceived performance of the system. The results have shown that keywords can be very effective in driving user-generated content, but they often need to be complemented with contextual information that disambiguates their semantics.