TY - JOUR
T1 - Toward travel pattern aware tourism region planning
T2 - a big data approach
AU - Han, Qiwei
AU - Abreu Novais, Margarida
AU - Zejnilovic, Leid
N1 - Funding agency#
FCT-Fundação para a Ciência e Tecnologia #
UID/ECO/00124/2019#
LISBOA-01-0145-FEDER007722#
and Social Sciences Data Lab#
PINFRA/22209/2016#
Data Science for Social Good Summer Fellowship 2018 at Nova School of Business and Economics#
PY - 2021/8/9
Y1 - 2021/8/9
N2 - Purpose: The purpose of this paper is to propose and demonstrate how Tourism2vec, an adaptation of a natural language processing technique Word2vec, can serve as a tool to investigate tourism spatio-temporal behavior and quantifying tourism dynamics. Design/methodology/approach: Tourism2vec, the proposed destination-tourist embedding model that learns from tourist spatio-temporal behavior is introduced, assessed and applied. Mobile positioning data from international tourists visiting Tuscany are used to construct travel itineraries, which are subsequently analyzed by applying the proposed algorithm. Locations and tourist types are then clustered according to travel patterns. Findings: Municipalities that are similar in terms of their scores of their neural embeddings tend to have a greater number of attractions than those geographically close. Moreover, clusters of municipalities obtained from the K-means algorithm do not entirely align with the provincial administrative segmentation.
AB - Purpose: The purpose of this paper is to propose and demonstrate how Tourism2vec, an adaptation of a natural language processing technique Word2vec, can serve as a tool to investigate tourism spatio-temporal behavior and quantifying tourism dynamics. Design/methodology/approach: Tourism2vec, the proposed destination-tourist embedding model that learns from tourist spatio-temporal behavior is introduced, assessed and applied. Mobile positioning data from international tourists visiting Tuscany are used to construct travel itineraries, which are subsequently analyzed by applying the proposed algorithm. Locations and tourist types are then clustered according to travel patterns. Findings: Municipalities that are similar in terms of their scores of their neural embeddings tend to have a greater number of attractions than those geographically close. Moreover, clusters of municipalities obtained from the K-means algorithm do not entirely align with the provincial administrative segmentation.
KW - Big Data
KW - Mobile positioning data
KW - Tourism region planning
KW - Tourism spatio-temporal behavior
KW - Tourism2vec
KW - Travel patterns
UR - http://www.scopus.com/inward/record.url?scp=85102949817&partnerID=8YFLogxK
U2 - 10.1108/IJCHM-07-2020-0673
DO - 10.1108/IJCHM-07-2020-0673
M3 - Article
AN - SCOPUS:85102949817
SN - 0959-6119
VL - 33
SP - 2157
EP - 2175
JO - International Journal of Contemporary Hospitality Management
JF - International Journal of Contemporary Hospitality Management
IS - 6
ER -