=Paper=
{{Paper
|id=None
|storemode=property
|title=Towards a DBpedia of Tourism: The Case of Tourpedia
|pdfUrl=https://ceur-ws.org/Vol-1272/paper_106.pdf
|volume=Vol-1272
|dblpUrl=https://dblp.org/rec/conf/semweb/CresciDGDMT14
}}
==Towards a DBpedia of Tourism: The Case of Tourpedia==
https://ceur-ws.org/Vol-1272/paper_106.pdf
Towards a DBpedia of Tourism: the case of
Tourpedia
Stefano Cresci, Andrea D’Errico, Davide Gazzé, Angelica Lo Duca,
Andrea Marchetti, Maurizio Tesconi
Institute of Informatics and Telematics, National Research Council,
via Moruzzi 1, 56124 Italy
email: [name].[surname]@iit.cnr.it
Abstract. In this paper we illustrate Tourpedia, which would be the
DBpedia of tourism. Tourpedia contains more than half a million places,
divided in four categories: accommodations, restaurants, points of in-
terests and attractions. They are related to eight locations: Amsterdam,
Barcelona, Berlin, Dubai, London, Paris, Rome and Tuscany, but new lo-
cations are continuously added. Information about places were extracted
from four social media: Facebook, Foursquare, GooglePlaces and Book-
ing and were integrated in order to build a unique catalogue. Tourpedia
provides also a Web API and a SPARQL endpoint to access data.
1 Introduction
The concept of Semantic Web was introduced by Tim Berners Lee in 2001[2].
His main idea consisted in migrating from the Web of documents to the Web
of data. The purpose of the Web of data is to connect concepts and contents
to each other, instead of simply connecting documents. Thus the Web of data
has led to the conversion of existing documents to linked data [6], and to the
creation of new datasets1 . Among them, one of the most exploited datasets is
DBpedia2 , which is the linked data version of Wikipedia3 .
DBpedia is available in different languages. Its English version contains about
4.0 million things, classified in different categories, including people, places, cre-
ative works, organizations, species and deseases. However, DBpedia, as well
as Wikipedia, contains only a small number of things related to the tourism
domain, such as accommodations and restaurants. In addition, to the best of
our knowledge, only few linked datasets have been implemented in the field
of tourism. Among them, the case of El Viajero4 , which provides information
about more than 20.000 travel guides, pictures, videos and posts, and that of
Accommodations in Tuscany5 , which contains the list of accommodations in
1
For a list of shared datasets, please look at: http://datahub.io.
2
http://dbpedia.org
3
http://wikipedia.org
4
http://datahub.io/dataset/elviajero
5
http://datahub.io/dataset/grrt
Tuscany, Italy. For more details about datasets about tourism, please refer to:
http://datahub.io/dataset?q=tourism.
In this paper we illustrate Tourpedia, which would be the DBpedia of Tourism.
Tourpedia is reachable through its portal6 and is available also in the datahub.io
platform7 .
Tourpedia was developed within the OpeNER Project8 (Open Polarity En-
hanced Name Entity Recognition), whose main objective is to implement a
pipeline to process natural language.
The usage of Tourpedia could be very various. For example, it could be used
to perform named entity disambiguation in tourism domain, or to extract the
most appreciated points of interest in a town.
2 Tourpedia
Figure 1 illustrates the Tourpedia architecture. The Data Extraction module
consists of four ad-hoc scrapers, which extract data from four social media:
Facebook9 , Foursquare10 , Google Places11 and Booking12 . We chose these social
media firstly because they are very popular and secondly because they pro-
vide an easy way to extract data. The scrapers of Facebook, GooglePlaces and
Foursquare exploit the RESTful APIs the social media provide, while the Book-
ing scraper extracts information from each accommodation page.
The Named Entity repository contains two main datasets, which belong to
the specific domain of tourism: Places and Reviews about places. The dataset of
Places contains more than 500.000 places in Europe divided in four categories: ac-
commodations, restaurants, points of interest and attractions13 . At the moment
the following locations are covered: Amsterdam, Barcelona, Berlin, Dubai, Lon-
don, Paris, Rome and Tuscany. Places were elaborated and integrated through
the Data Integration module in order to build a unique catalogue. Data Integra-
tion was performed by using a merging algorithm based on distance and string
similarity.
The dataset of Reviews contains about 600.000 reviews about places. Reviews
were analysed through the OpeNER pipeline in order to extract their sentiment.
2.1 Web application
Tourpedia provides also a Web application14 [5], which shows the sentiment
about places on an interactive map, which is Google Maps-like.
6
http://tour-pedia.org
7
http://datahub.io/dataset/tourpedia
8
http://www.opener-project.eu
9
http://www.facebook.com
10
http://foursquare.com
11
https://plus.google.com/u/0/local
12
http://www.booking.com
13
http://tour-pedia.org/about/statistics.html
14
http://tour-pedia.org/gui/demo/
Social Media
Linked
Dataset
SPARQL
Data Extraction endpoint
D2R server
OpeNER Data
pipeline Integration
Web API
Reviews Places
NE Repository
Web Application
Fig. 1. The architecture of Tourpedia.
The sentiment of a place is calculated as a function of all the sentiments
of the reviews about that place. In order to retrieve the sentiment of a review,
the OpeNER pipeline was used. In particular, each place is associated to zero
or more reviews extracted from social media (i.e. Facebook, Foursquare and
Google Places). Each review is processed through the OpeNER pipeline and is
associated to a rate, which expresses its specific sentiment.
2.2 Linked Data
Tourpedia is exposed as a linked data node and provides a SPARQL endpoint15 .
The service is implemented through the use of a D2R server16 . For each place, the
following ontologies are used to represent it: VCARD [9] and DBpedia OWL17 ,
for generic properties; Acco [8], Hontology [4] and GoodRelations [7] for domain-
specific properties. In a previous work [1], we illustrated the employed ontologies
and structures of accommodations as linked data. In order to fulfill the principles
of linked data [3], each location is linked to the same location in DBpedia.
2.3 Web API
Tourpedia provides a RESTful API18 to access places and statistics. The output
of each request can be JSON, CSV and XML. For example, a search request
about Places is an HTTP URL of the following form:
http://tour-pedia.org/api/getPlaces?parameters
where parameters must be at least one one of the following: location (the
location of the places), category (the type of the places such as accomodation),
attraction, restaurant, poi), and name (the keyword to be searched).
15
http://tour-pedia.org/sparql
16
http://d2rq.org/
17
http://wiki.dbpedia.org/Ontology
18
http://tour-pedia.org/api
3 Conclusions and Future Work
In this paper we have illustrated Tourpedia, which would be the DBpedia of
Tourism. It could be interesting a deeper connection between Tourpedia and
DBpedia. At the moment, in fact, only locations are connected to DBpedia.
As future work, we are going to align also attractions and points of interest
contained in Tourpedia to DBpedia.
Tourpedia could be exploited both by tourism stackholders to get the senti-
ment about touristic places and by common users.
At the moment, the procedure to update datasets is manual. As future work,
we are going to define a semi-automatic procedure to update them and to add
new locations.
Acknowledgements
This work has been carried out within OpeNER project, co-funded by the Euro-
pean Commission under the FP7 (7th Framework Programs Grant Agreement
n. 296451).
References
1. Bacciu, C., Lo Duca, A., Marchetti, A., Tesconi, M.: Accommodations in Tuscany
as Linked Data. In: Proceedings of The 9th edition of the Language Resources and
Evaluation Conference (LREC 2014). pp. 3542–3545 (May, 26-31 2014)
2. Berners-Lee, T., Hendler, J., Lassila, O.: The semantic web. Scientific Ameri-
can 284(5), 34–43 (May 2001), http://www.sciam.com/article.cfm?articleID=
00048144-10D2-1C70-84A9809EC588EF21
3. Bizer, C., Heath, T., Berners-Lee, T.: Linked data - the story so far. Int. J. Semantic
Web Inf. Syst. 5(3), 1–22 (2009)
4. Chaves, M.S., de Freitas, L.A., Vieira, R.: Hontology: A multilingual ontology for
the accommodation sector in the tourism industry. In: Filipe, J., Dietz, J.L.G. (eds.)
KEOD. pp. 149–154. SciTePress (2012)
5. Cresci, S., D’Errico, A., Gazzé, D., Lo Duca, A., Marchetti, A., Tesconi, M.: Tour-
pedia: a Web Application for Sentiment Visualization in Tourism Domain. In: Pro-
ceedings of The OpeNER Workshop in The 9th edition of the Language Resources
and Evaluation Conference (LREC 2014). pp. 18–21 (May, 26 2014)
6. Heath, T., Bizer, C.: Linked Data: Evolving the Web into a Global Data Space.
Morgan & Claypool, 1st edn. (2011), http://linkeddatabook.com/
7. Hepp, M.: Goodrelations language reference. Tech. rep., Hepp Research GmbH,
Innsbruck (2011)
8. Hepp, M.: Accommodation ontology language reference. Tech. rep., Hepp Research
GmbH, Innsbruck (2013)
9. Iannella, R., McKinney, J.: VCARD ontology. Available at:
http://www.w3.org/TR/vcard-rdf/. Tech. rep. (2013)