UWIRS-REC: integrating web information retrieval with recommendation services

Purpose - The purpose of this paper is to describe UWIRS (Ubiquitous Web Information Retrieval Solution), an agent-based Web Information Retrieval (WIR) solution designed taking into account the unique features of the World Wide Web (WWW) and the limitations of existing WIR solutions for ubiquitous environments. Design/methodology/approach - UWIRS can offer recommendation services by using the Multi- Agent Vizier Recommendation Framework (Vizier). Vizier was designed under a generic approach and therefore can provide services to information retrieval applications so these may offer product recommendations that consider several adaptation/personalization dimensions (e.g. user dimension, context, among others). Findings - Overall, the main challenge resides on: location, retrieval, integration and presentation of information from the WWW, quickly and accurately, to satisfy a user's singular information needs. Originality/value - In UWIRS, agents cooperate in order to retrieve personalized information, considering user needs, goals, preferences and contextual features. UWIRS's agents are responsible for: interpreting user input and adding adaptation information by means of a query enrichment process; identifying and selecting the appropriate data sources taking into consideration the Profile Set (composed of User, Device and Information-Provider Profiles); executing query routing and the information retrieval process; integrating and filtering the retrieved results; and lastly, coherent presentation of quality and relevant ubiquitous information (anytime, anywhere and anyhow) that satisfies the user's particular information needs and constraints associated to his/her access device.