OEG papers submitted to the TourismKG workshop

Disclaimer

This site contains the data and materials associated to the papers submitted, currently under review, to the TourismKG workshop. These papers as well as the materials included in this site are original and have been not publised before. You are not allowed to keep any dataset(s). Only the papers published will make public their dataset(s) under a Creative Commons license.

Abstract DBtravel (Calleja et al.)

We present DBtravel, a tourism-oriented knowledge graph generated from the collaborative travel site Wikitravel. Our approach takes advantage of the recommended guideline for contributors provided by Wikitravel and extracts the named entities available in Wikitravel Spanish entries by using a NLP pipeline. Compared to a manually annotated gold standard, results show that our approach reaches values for precision and recall around 80\% for some sections of Wikitravel for the Spanish language.

Abstract TourismCube (Mihindukulasooriya et al.)

Tourism is a crucial component of Sri Lanka's economy. Intelligent business decisions by means of thorough analysis of relevant data can help the Sri Lankan tourism industry to be competitive. To this end, Sri Lanka Tourism Development Authority makes tourism statistics publicly available. However, they are published as PDF files hindering their reuse. In this paper, we present how to transform such data into 5-star Linked Open Data by extracting the statistics as structured data; modelling them using the W3C RDF Data Cube vocabulary and transforming them to RDF using W3C R2RML mappings. Furthermore, we demonstrate the benefits of such transformation using two real-world use cases.

Abstract LinkedFiestas (Cimmino et al.)

Spain is a hot-spot for the European tourism that conforms an important part of its economy. Large cities tend to monopolize this sector unbalancing the outcome of the tourism in Spain. Promoting festivals from less-known regions that belong to the Spanish cultural heritage has been proposed as a solution to balance the economy of this sector. Unfortunately there is a lack of visibility of such festivals that hinders the feasibility of such approach. In this paper we introduce the Linked-Fiestas dataset that aims at providing data of festivals and events from not so well-known regions, so spreading their cultural heritage, bringing visibility to them, and thus, increasing tourists interest. Linked-Fiestas gathers data from well-known datasets, such as DBpedia and Wikidata, and from other datasets outside the Web of Data community.

Data

In this section we include the files containing the data used in our experimental setup.

DBtravel

The dataset for this experiment is found in the file CorpusGoldWikitravel.rar (6,91MB) which comprises a set of Wikitravel HTML pages of cities and the gold standard for sections See and Get Out. The gold stardard are tsv files for each section and they reflect : the document id, the offsets of the entity in the document, the span text and the type of entity.

Linekd Fiestas

The Linked Fiesta dataset can be downloaded from linked--fiesta-dataset.tar.gz which contains the all the festivals extracted from structured and unstructured sources and the sameAs links between them.

Code

The source code is not provided.

About the authors

Pablo Calleja	(pcalleja@fi.upm.es). Ontology Engineering Group, UPM.
Andrea Cimmino	(cimmino@fi.upm.es). Ontology Engineering Group, UPM.
Nandana Mihindukulasooriya	(nmihindu@fi.upm.es). Ontology Engineering Group, UPM.
Freddy Priyatna	(fpriyatna@fi.upm.es). Ontology Engineering Group, UPM.
Mariano Rico	(mariano.rico@upm.es). Ontology Engineering Group, UPM.

Acknowledgements

This work was partially funded by the Spanish MINECO Ministry (projects RTC-2016-4952-7 (esTextAnalytics) and TIN2013-46238-C4-2-R (4V)), the BES-2014-068449 grant, and grants from the EU’s H2020 Programmes for the ALIGNED project (GA 644055). Also, this work has been partially funded by the project Data 4.0 (TIN2016-78011-C4-4-R), from the Spanish State Investigation Agency of the MINECO and FEDER Funds.