Today georeferenced images posted on the social network provide a lot of information about people behaviours and movements. Using social media platforms users upload photos, share locations and post comments about their activities, influencing other people. In this research, we examine the relationship between human mobility and touristic attractions through geo-located images provided by Flickr users. A sample of 26,392 pictures related to 6 Italian cities has been collected and analysed applying cluster analysis. In our work, the function of the clustering analysis, employed in Wolfram Mathematica Machine Learning, allows one to automatically identify clusters surrounding points of interest (POIs). Findings show that social media datasets are valuable data to understand tourist behaviour and mobility within a location. The scope is to delineate famous or unpopular places and propose new touristic scenarios, highlighting how the social part covers the main role in the POIs’ recommendation process in the touristic field. Furthermore, we aim to promote the machine learning approach as a useful support in human behaviour research.

Machine learning and points of interest: typical tourist Italian cities

Giglio S.;Bertacchini F.;Bilotta E.;Pantano P.
2019

Abstract

Today georeferenced images posted on the social network provide a lot of information about people behaviours and movements. Using social media platforms users upload photos, share locations and post comments about their activities, influencing other people. In this research, we examine the relationship between human mobility and touristic attractions through geo-located images provided by Flickr users. A sample of 26,392 pictures related to 6 Italian cities has been collected and analysed applying cluster analysis. In our work, the function of the clustering analysis, employed in Wolfram Mathematica Machine Learning, allows one to automatically identify clusters surrounding points of interest (POIs). Findings show that social media datasets are valuable data to understand tourist behaviour and mobility within a location. The scope is to delineate famous or unpopular places and propose new touristic scenarios, highlighting how the social part covers the main role in the POIs’ recommendation process in the touristic field. Furthermore, we aim to promote the machine learning approach as a useful support in human behaviour research.
Big Data analytics; machine learning techniques; points of interest; tourist attractiveness; users’ behaviour
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/20.500.11770/294607
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 14
  • ???jsp.display-item.citation.isi??? ND
social impact