Extracting Touristic Information from Online Image Collections

Abstract

In this paper, we present a Geographical Information Retrieval system, which aims to automatically extract and analyze touristic information from photos of online image collections (in our case of study Flickr). Our system collect all the photos, and the related information, that are associated to a specific city. We then use Google Maps service to geolocate the retrieved photos, and finally we analyze geo-referenced data to obtain our goals: 1) determining and locating the most interesting places of the city, i.e. the most visited locations, and 2) reconstructing touristic routes of the users visiting the city. Information is filtered by using a set of constraints, which we apply to select only the users that reasonably are tourists visiting the city. Tests were performed on an Italian city, Palermo, that is rich in artistic and touristic attractions, but preliminary tests showed that our technique could successfully be applied to any city in the world with a reasonable number of touristic landmarks.

Flickr data for analysing tourists’ spatial behaviour and movement patterns

“…Especially, photo-sharing platforms (e.g. Instagram or Flickr) gain increasing interest by researchers and practitioners, as photo uploads are typically closely related to tourist attractions or POIs (Ardizzone et al, 2012). Additionally, most photo upload platforms are offering metadata, such as GPS coordinates, photo taken and upload time, as well as user profile data, thus constituting perfect conditions for powerful analyses of tourists' movement patterns (Ardizzone et al, 2012;Comito et al, 2016).…”

“…Flickr is one of the leading photo-sharing platforms worldwide and attracts extensive research attention. Ardizzone et al (2012) present a geographic information retrieval system, extracting the above-described metadata from Flickr, thereby enabling the identification of POIs within a specific destination and the reconstruction of tourists' spatial movement patterns. Moreover, Crandall et al (2009) present an approach to organising a large collection of geo-tagged photos, extracting a data set of about 35 million photos from 307,449 users from Flickr.…”

“…In general terms, separating tourists from non-tourism users is usually based on time heuristics, which assume that tourists visit a destination for a limited period of time (Ratti et al, 2008;De Choudhury et al, 2010;Ardizzone et al, 2012;Sun et al, 2015;Önder et al, 2016). While De Choudhury et al (2010) and Önder et al (2016), to identify tourists, define an upper limit of 21 days between the first and last dates of photo upload, Ratti et al (2008) use a 30-day period as separation threshold.…”

A proposal for measuring hotels’ managerial responses to User-Generated-Content Reviews

“…Since the emergence of this phenomenon, there has been an exponential increase in UGC literature and, in particular, studies that examine online reviews. In recent years, UGC reviews have been extensively studied in regard to service quality (Li, Ye, & Law, 2012;Magnini, Crotts, & Zehrer, 2011), experiences and behavior (Axup & Viller 2005;Berger & Greenspan, 2008;Pan et al, 2007;Marine-Roig & Anton, 2015;Marchiori & Cantoni, 2015; Paris & Rubin 2013), destination image and reputation (Choi, Lehto, & Morrison, 2007;Dwivedi, Yadav, & Patel, 2009;Law & Cheung, 2010;Schmallegger & Carson, 2009;Wenger, 2008), influence on travel decisions (Arsal, Wosnam, Baldwin, & Backman, 2010;Baka, 2016;Cheng & Loi, 2014;Magnini et al, 2011;Duffy, 2015;Filieri & McLeay, 2013;Hvass & Munar, 2012;Herrero, Martin, & Hernandez, 2015;Jin & Phua, 2016;Leung, Schuckert, & Yeung, 2013;Liu, 2012;Jani, Jeong, & Hwang, 2011;Kwok & Yu, 2013;Lu & Stepchenkova, 2012;O'Connor, 2011;Sparks, Perkins, & Buckley, 2013;Xiang & Gretzel, 2010) and mobility patterns (Ardizzone, Di Miceli, La Cascia, & Mazzola, 2012;Girardin, Dal Fiore, Blat, & Ratti, 2007;Girardin, Calabrese, Fiore, Ratti, & Blat, 2008;Kurashima, Tezuka, & Tanaka, 2005;Lu, Wang, Yang, Pang, & Zhang, 2010). In terms of the methodol...…”