Georeferencing Flickr resources based on textual meta-data

Laere, Olivier Van; Schockaert, Steven; Dhoedt, Bart

doi:10.1016/j.ins.2013.02.045

Cited by 28 publications

(21 citation statements)

References 31 publications

(39 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In geographical information science, the primary focus has been on recognising location mentions in text (Leidner & Lieberman, 2011), with named entity recognition tools typically employed to detect and extract such mentions (Quercini, Samet, Sankaranarayanan, & Lieberman, 2010;Gelernter & Mushegian, 2011). Within the social media realm, geolocation methods have been applied to images on Flickr (Crandall, Backstrom, Huttenlocher, & Kleinberg, 2009;Serdyukov, Murdock, & van Zwol, 2009;Hauff & Houben, 2012;O'Hare & Murdock, 2013;Laere, Schockaert, & Dhoedt, 2013), Wikipedia articles (Lieberman & Lin, 2009), individual tweets (Kinsella et al, 2011), Twitter users (Eisenstein et al, 2010;Cheng et al, 2010;Kinsella et al, 2011;Wing & Baldridge, 2011;Roller et al, 2012;Han et al, 2012b), and for identifying words and topics on Twitter that are salient in particular regions (Eisenstein et al, 2010;Yin, Cao, Han, Zhai, & Huang, 2011;Hong, Ahmed, Gurumurthy, Smola, & Tsioutsiouliklis, 2012;Dalvi, Kumar, & Pang, 2012).…”

Section: Related Workmentioning

confidence: 99%

Text-Based Twitter User Geolocation Prediction

Han¹,

Cook²,

Baldwin³

2014

jair

241

286

View full text Add to dashboard Cite

Geographical location is vital to geospatial applications like local search and event detection. In this paper, we investigate and improve on the task of text-based geolocation prediction of Twitter users. Previous studies on this topic have typically assumed that geographical references (e.g., gazetteer terms, dialectal words) in a text are indicative of its author's location. However, these references are often buried in informal, ungrammatical, and multilingual data, and are therefore non-trivial to identify and exploit. We present an integrated geolocation prediction framework and investigate what factors impact on prediction accuracy. First, we evaluate a range of feature selection methods to obtain "location indicative words". We then evaluate the impact of nongeotagged tweets, language, and user-declared metadata on geolocation prediction. In addition, we evaluate the impact of temporal variance on model generalisation, and discuss how users differ in terms of their geolocatability.We achieve state-of-the-art results for the text-based Twitter user geolocation task, and also provide the most extensive exploration of the task to date. Our findings provide valuable insights into the design of robust, practical text-based geolocation prediction systems.

show abstract

Section: Related Workmentioning

confidence: 99%

Text-Based Twitter User Geolocation Prediction

Han¹,

Cook²,

Baldwin³

2014

jair

241

286

View full text Add to dashboard Cite

show abstract

“…This analysis was shown to have several challenges. First, the consistent and accurate geographical allocation of the Twitter messages is complex [24,47,48]. In assessing the geographical location, we are looking for the impact location, rather than the geographical location of reporting, by analyzing place indications in the body of the tweet text.…”

Section: Twitter Analysismentioning

confidence: 99%

Early Flood Detection for Rapid Humanitarian Response: Harnessing Near Real-Time Satellite and Twitter Signals

Jongman

Wagemaker²,

Revilla-Romero

et al. 2015

IJGI

113

View full text Add to dashboard Cite

Humanitarian organizations have a crucial role in response and relief efforts after floods. The effectiveness of disaster response is contingent on accurate and timely information regarding the location, timing and impacts of the event. Here we show how two near-real-time data sources, satellite observations of water coverage and flood-related social media activity from Twitter, can be used to support rapid disaster response, using case-studies in the Philippines and Pakistan. For these countries we analyze information from disaster response organizations, the Global Flood Detection System (GFDS) satellite flood signal, and flood-related Twitter activity analysis. The results demonstrate that these sources of near-real-time information can be used to gain a quicker understanding of the location, the timing, as well as the causes and impacts of floods. In terms of location, we produce daily impact maps based on both satellite information and social media, which can dynamically and rapidly outline the affected area during a disaster. In terms of timing, the results show that GFDS and/or Twitter signals flagging ongoing or upcoming flooding are regularly available one to several days before the event was reported to humanitarian organizations. 2247In terms of event understanding, we show that both GFDS and social media can be used to detect and understand unexpected or controversial flood events, for example due to the sudden opening of hydropower dams or the breaching of flood protection. The performance of the GFDS and Twitter data for early detection and location mapping is mixed, depending on specific hydrological circumstances (GFDS) and social media penetration (Twitter). Further research is needed to improve the interpretation of the GFDS signal in different situations, and to improve the pre-processing of social media data for operational use.

show abstract

“…In other words, an event location and thus its nearest events and documents features can be estimated for only 35% of the considered events. Therefore, we also experimented with automated methods for estimating the coordinates of Flickr photos in De for each considered event e based on their tags [14]. However, initial experiments did not yield better results.…”

Section: Locations Of Eventsmentioning

confidence: 99%

Estimating the semantic type of events using location features from Flickr

Canneyt

Schockaert

Dhoedt

2014

Proceedings of the 8th Workshop on Geographic Information Retrieval

Self Cite

View full text Add to dashboard Cite

Various methods for automatically detecting events from social media have been developed in recent years. However, little progress has been made towards extracting structured representations of such events, which severely limits the way in which the resulting event databases can be queried. As a first step to address this issue, we focus on the problem of discovering the semantic type of events. While current methods are almost exclusively based on bag-of-words methods, we show that additionally using location features can substantially improve the results. In particular, we use the tags associated with Flickr photos and the types of the known events near the venue of the event as context information.

show abstract

Georeferencing Flickr resources based on textual meta-data

Cited by 28 publications

References 31 publications

Text-Based Twitter User Geolocation Prediction

Text-Based Twitter User Geolocation Prediction

Early Flood Detection for Rapid Humanitarian Response: Harnessing Near Real-Time Satellite and Twitter Signals

Estimating the semantic type of events using location features from Flickr

Contact Info

Product

Resources

About