Introduction
TourPedia is the Wikipedia of Tourism. It contains information about accommodations, restaurants, points of interest and attractions of different places in Europe. At the moment only eight places are covered: Amsterdam, Barcelona, Berlin, Dubai, London, Paris, Rome and Tuscany. However, the idea is to extend the service to all the world.
Data are extracted from four social media: Facebook, Foursquare, Google Places and Booking. They were elaborated and integrated in order to build a unique catalogue.
OpeNER
TourPedia was developed within the OpeNER Project. OpeNER (Open Polarity Enhanced Name Entity Recognition) is a project funded under the 7th Framework Program of the European Commission. Its main objective is to implement a pipeline for the processing of natural language. More specifically, OpeNER focuses on building a linguistic pipeline supporting six languages (English, Spanish, German, French, Italian, Dutch) that enables the identification and disambiguation of named entities and the analysis of sentiment in opinionated texts.
Web API
Places and elaborations on reviews can be accessed also through a Web API, which allows a developer to get their JSON version and some useful statistics.
Documentation
Documentation describes the architecture of TourPedia within OpeNER. TourPedia is composed of a Named Entity Repository, a Web API and a Linked Data node, accessible as a SPARQL endpoint.
Datasets
TourPedia provides two main datasets: Places and Reviews. Places can be downloaded as a dump. Each place contains useful information such as the name, the address and its URI to Facebook, Foursquare, GooglePlaces and Booking.
Online Access
TourPedia provides two methods to access data: through a Web API and a SPARQL engine.
Linked Data
TourPedia is exposed as a linked data node, which provides access to places.
GUI
TourPedia provides also a Web application, which exploits the OpeNER pipeline in order to extract the sentiment of places related to tourism domain.
In details, each place is associated to zero or more reviews extracted from social media (i.e. Facebook, Foursquare and Google Places). Each review is processed by the OpeNER pipeline and is associated to a rate, in order to extract its specific sentiment. The sentiment of a place is calculated as a function of all the sentiments of the reviews on that place.
Statistics
TourPedia data statistics wants to provide an overview of the places distribution in the available cities (Amsterdam, Barcelona, Berlin, Dubai, London, Paris, Rome, Tuscany) for the each venue category (accommodation, attraction, point of interest and restaurant).