Towards A Precision-Oriented Multi-Lingual Semantics-Based Cultural Heritage Recommender System

Project Summary: 

With the explosive growth of smartphones and other handheld devices, and the advancement of the Internet, the cultural heritage sector and the associated tourism services have been notably affected. These days, visitors have access to reliable and trusted content related to cultural heritage information world-wide. They can access this information either using the Internet (via Web interfaces) or by using their handheld devices. Considering the latter approach, a user can search for any desired information, and details that pertain to it will be presented in a timely and neat interface. However, conventional cultural heritage information systems lack the ability to adapt their behavior to the preferences, tasks, interests and other features of users (tourists and tourism groups). This research project addresses the issue of designing a precision-oriented multi-lingual and multi-criteria semantics-based mobile recommender system in the cultural heritage domain. We aim to better facilitate users’ access to cultural heritage information by providing them with multiple search functionalities. In this context, a user can search for cultural heritage sites or topics via a query-by-example interface; wherein the system takes a given image as input and retrieves all relevant images based on their content similarity (between the low-level features of the compared images). In the second approach, users can express their information needs using keywords (a.k.a. tags) to describe cultural heritage information. In this context, the proposed system will process users’ queries by using Natural Language Processing Techniques (NLP), Multi-lingual ontologies and other statistical-based concept-relatedness measures. Moreover, the proposed system is aimed to adapt itself to the user preferences and information needs, for a more effective and efficient interaction. In other words, the system is meant to be able to automatically and progressively tune its output to satisfy the user’s information needs and preferences. A prototype of the proposed system will be developed and tested using Android smartphones and state-of-the-art corpora about cultural heritage information.