fbpx Multi-modality Search and Recommendation on Palestinian Cultural Heritage Based on the Holy-Land Ontology and Extrinsic Semantic Resources |ARAB AMERICAN UNIVERSITY
Contact information for Technical Support and Student Assistance ... Click here

Multi-modality Search and Recommendation on Palestinian Cultural Heritage Based on the Holy-Land Ontology and Extrinsic Semantic Resources

Authors: 
Mohammed Maree
Amjad Rattrout
Muhanad Altawil
Mohammed Belkhatir
ISSN: 
1556-4673
Journal Name: 
Journal on Computing and Cultural Heritage
Volume: 
14
Issue: 
3
Pages From: 
1
To: 
23
Date: 
Friday, July 2, 2021
Keywords: 
Cultural heritage, Semantic Similarity, Knowledge-based Search, Hybrid Recommendation, Content-based Image Retrieval, Manually Constructed Ontology
Abstract: 
The Cultural Heritage (CH) sector and its associated tourism services have been affected notably by the advancement of the Internet as well as the explosive growth of smartphones and other handheld devices. These days, visitors can access reliable CH content using Web and mobile-based interfaces. However, conventional CH systems still lack the ability to provide meaningful semantically overt results that precisely meet user information needs in this domain. In addition, they often ignore the user search context and experience, which hinders their ability to adapt their behavior to the preferences, tasks, interests, and other user functionalities. In this article, we aim to address the issue of designing a precision-oriented multilingual and multi-criteria semantic-based mobile recommender system specifically targeting Palestine's CH, a country with great historical and cultural importance. We aim to better facilitate users’ access to CH content by providing them with multiple search functionalities. In this context, a user can search for relevant information using keywords (a.k.a. tags) or sentence-like queries and the system retrieves all relevant documents based on their semantic similarity. A second option is to search using current location information to retrieve correlated historical places and events. Finally, starting from a picture of interest, a third option makes it possible to extract captions describing its content that can be used to search for additional contextually relevant information. Additionally, the proposed system aims at personalizing users’ experience through progressively delivering output that meets their information needs based on a number of parameters such as users' logging data, interests, previous searches, and location-based information. A prototype of the proposed system has been developed and tested using Android smartphones and a manually constructed ontology enriched with CH links to the Art & Architecture Thesaurus (AAT) and DBpedia. By comparing our system with similar systems in this domain, findings demonstrate that it provides additional search features and functionalities to users. The proposed Holy-Land ontology is the first of its kind attempting to encode knowledge about Palestine's CH. It plays a crucial role in our proposal, serving as a pivotal entity in the combination of language-based, location-based, and visual-based retrieval strategies.