Discovering and Characterizing Places of Interest Using Flickr and Twitter

Abstract

Databases of places have become increasingly popular to identify places of a given type that are close to a user-specified location. As it is important for these systems to use an up-to-date database with a broad coverage, there is a need for techniques that are capable of expanding place databases in an automated way. In this paper the authors discuss how geographically annotated information obtained from social media can be used to discover new places. In particular, the authors first determine potential places of interest by clustering the locations where Flickr photos have been taken. The tags from the Flickr photos and the terms of the Twitter messages posted in the vicinity of the obtained candidate places of interest are then used to rank them based on the likelihood that they belong to a given type. For several place types, their methodology finds places that are not yet contained in the databases used by Foursquare, Google, LinkedGeoData and Geonames. Furthermore, the authors' experimental results show that the proposed method can successfully identify errors in existing place databases such as Foursquare.

Predicting environmental features by learning spatiotemporal embeddings from social media

“…The use of Flickr for modelling urban environments has already received considerable attention. For instance, various approaches have been proposed for modelling urban regions (Cunha and Martins, 2014), and for identifying points-of-interest (Van Canneyt et al, 2013a) and itineraries (De Choudhury et al, 2010;Quercia et al, 2014). However, using Flickr for modelling the natural environment has so far received only limited attention.…”

Embedding Geographic Locations for Modelling the Natural Environment Using Flickr Tags and Structured Data

“…The use of Flickr for modelling urban environments has already received considerable attention. For instance, various approaches have been proposed for modelling urban regions [5], and for identifying points-of-interest [45] and itineraries [7,36]. However, the usefulness of Flickr for characterizing the natural environment, which is the focus of this paper, is less well-understood.…”

Incremental Tag Suggestion for Landmark Image Collections

“…Tags for objects in social media must be related to keywords as most queries to the system are still text based [1]- [4]. Keyword tags such as "Tokyo Tower", "Big Ben", and "Taj Mahal" are common queries.…”