Proceedings of the 2016 CHI Conference on Human Factors in Computing Systems 2016
DOI: 10.1145/2858036.2858122
|View full text |Cite
|
Sign up to set email alerts
|

The Geography and Importance of Localness in Geotagged Social Media

Abstract: Geotagged tweets and other forms of social media volunteered geographic information (VGI) are becoming increasingly critical to many applications and scientific studies. An important assumption underlying much of this research is that social media VGI is "local", or that its geotags correspond closely with the general home locations of its contributors. We demonstrate through a study on three separate social media communities (Twitter, Flickr, Swarm) that this localness assumption holds in only about 75% of ca… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

1
31
0

Year Published

2016
2016
2024
2024

Publication Types

Select...
8
2

Relationship

2
8

Authors

Journals

citations
Cited by 45 publications
(32 citation statements)
references
References 40 publications
1
31
0
Order By: Relevance
“…After pre-processing (noises, void records, and bogus users) of 903,008 anonymized check-in records, 852,560 check-in records associated with the geographical area are picked up between January to May, 2016. Lastly, the task in the data insight stage is to analyze and investigate the features of LBSN check-in data by considering location, time, and gender and visualize data by using ArcGIS [136] to produce density maps [137] and trends [138,139]. 2016 denotes "day, month, date, time and year," m denotes "gender" and 113.854085, 23.527322 denotes geo-location.…”
Section: Methodsmentioning
confidence: 99%
“…After pre-processing (noises, void records, and bogus users) of 903,008 anonymized check-in records, 852,560 check-in records associated with the geographical area are picked up between January to May, 2016. Lastly, the task in the data insight stage is to analyze and investigate the features of LBSN check-in data by considering location, time, and gender and visualize data by using ArcGIS [136] to produce density maps [137] and trends [138,139]. 2016 denotes "day, month, date, time and year," m denotes "gender" and 113.854085, 23.527322 denotes geo-location.…”
Section: Methodsmentioning
confidence: 99%
“…More generally, social media content biases have been observed across datasets. In a study of Twitter, Flickr, and Swarm, it was shown that volunteered geographic information is "local" (geotags correspond closely with the home locations of its contributors) in only about 75% of cases [27], and compounded by how localness is defined [28]. This effect influences the design of geolocation inference algorithms, which have been shown to exhibit significantly worse performance for underrepresented populations (i.e.…”
Section: Media Bias In Communication and Social Mediamentioning
confidence: 99%
“…Another issue with traditional LBSNs is the uncertainty of localness. For example, LBSN users can write about a place while being physically at another place, which may violate the localness assumption of volunteered geographic information and generate inaccurate spatial data (Johnson, Sengupta, Schöning, & Hecht, ). With AR‐integrated LBSNs, the impact would be mitigated as most people are encouraged to create content in situ.…”
Section: The Fusion Of Ar and Lbsnsmentioning
confidence: 99%