In this paper we discuss the basic architecture of a Web based information retrieval application using natural language question-answering system. The application is designed to improve the inclusiveness process. We focus on the production of audio-textual guides to make the exhibition experience accessible even by people with disabilities.

This paper proposes an Opinion Mining model, parameterized according to the reviewer profile. The work aims to highlight and resolve some issues resulting from previous activities in evaluating the goodness of the results obtained by the analysis of the reviews. A user profiling system provides the set of parameters to associate with the aspects and allows, working with the Opinion Mining system, to configure itself according to the user preferences.

No abstract