Understanding US regional linguistic variation with Twitter data analysis

Research output: Contribution to journalArticlepeer-review

Standard

Understanding US regional linguistic variation with Twitter data analysis. / Huang, Yuan; Guo, Diansheng; Grieve, Jack; Kasakoff, Alice.

In: Computers, Environment and Urban Systems, Vol. 59, 09.2016, p. 244-255.

Research output: Contribution to journalArticlepeer-review

Harvard

APA

Vancouver

Author

Huang, Yuan ; Guo, Diansheng ; Grieve, Jack ; Kasakoff, Alice. / Understanding US regional linguistic variation with Twitter data analysis. In: Computers, Environment and Urban Systems. 2016 ; Vol. 59. pp. 244-255.

Bibtex

@article{110dc07ee9534a3ebf99729cc7b7b40f,
title = "Understanding US regional linguistic variation with Twitter data analysis",
abstract = "We analyze a Big Data set of geo-tagged tweets for a year (Oct. 2013–Oct. 2014) to understand the regional linguistic variation in the U.S. Prior work on regional linguistic variations usually took a long time to collect data and focused on either rural or urban areas. Geo-tagged Twitter data offers an unprecedented database with rich linguistic representation of fine spatiotemporal resolution and continuity. From the one-year Twitter corpus, we extract lexical characteristics for twitter users by summarizing the frequencies of a set of lexical alternations that each user has used. We spatially aggregate and smooth each lexical characteristic to derive county-based linguistic variables, from which orthogonal dimensions are extracted using the principal component analysis (PCA). Finally a regionalization method is used to discover hierarchical dialect regions using the PCA components. The regionalization results reveal interesting linguistic regional variations in the U.S. The discovered regions not only confirm past research findings in the literature but also provide new insights and a more detailed understanding of very recent linguistic patterns in the U.S.",
keywords = "US regions, Spatial data mining, Social media, Linguistic, Twitter, American dialects, Regionalization",
author = "Yuan Huang and Diansheng Guo and Jack Grieve and Alice Kasakoff",
year = "2016",
month = sep,
language = "English",
volume = "59",
pages = "244--255",
journal = "Computers, Environment and Urban Systems",
issn = "0198-9715",
publisher = "Elsevier",

}

RIS

TY - JOUR

T1 - Understanding US regional linguistic variation with Twitter data analysis

AU - Huang, Yuan

AU - Guo, Diansheng

AU - Grieve, Jack

AU - Kasakoff, Alice

PY - 2016/9

Y1 - 2016/9

N2 - We analyze a Big Data set of geo-tagged tweets for a year (Oct. 2013–Oct. 2014) to understand the regional linguistic variation in the U.S. Prior work on regional linguistic variations usually took a long time to collect data and focused on either rural or urban areas. Geo-tagged Twitter data offers an unprecedented database with rich linguistic representation of fine spatiotemporal resolution and continuity. From the one-year Twitter corpus, we extract lexical characteristics for twitter users by summarizing the frequencies of a set of lexical alternations that each user has used. We spatially aggregate and smooth each lexical characteristic to derive county-based linguistic variables, from which orthogonal dimensions are extracted using the principal component analysis (PCA). Finally a regionalization method is used to discover hierarchical dialect regions using the PCA components. The regionalization results reveal interesting linguistic regional variations in the U.S. The discovered regions not only confirm past research findings in the literature but also provide new insights and a more detailed understanding of very recent linguistic patterns in the U.S.

AB - We analyze a Big Data set of geo-tagged tweets for a year (Oct. 2013–Oct. 2014) to understand the regional linguistic variation in the U.S. Prior work on regional linguistic variations usually took a long time to collect data and focused on either rural or urban areas. Geo-tagged Twitter data offers an unprecedented database with rich linguistic representation of fine spatiotemporal resolution and continuity. From the one-year Twitter corpus, we extract lexical characteristics for twitter users by summarizing the frequencies of a set of lexical alternations that each user has used. We spatially aggregate and smooth each lexical characteristic to derive county-based linguistic variables, from which orthogonal dimensions are extracted using the principal component analysis (PCA). Finally a regionalization method is used to discover hierarchical dialect regions using the PCA components. The regionalization results reveal interesting linguistic regional variations in the U.S. The discovered regions not only confirm past research findings in the literature but also provide new insights and a more detailed understanding of very recent linguistic patterns in the U.S.

KW - US regions

KW - Spatial data mining

KW - Social media

KW - Linguistic

KW - Twitter

KW - American dialects

KW - Regionalization

M3 - Article

VL - 59

SP - 244

EP - 255

JO - Computers, Environment and Urban Systems

JF - Computers, Environment and Urban Systems

SN - 0198-9715

ER -