Where Chicagoans tweet the most: Semantic analysis of preferential return locations of Twitter users

Aiman Soliman, Anand Padmanabhan, Junjun Yin, Kiumars Soltani, Shaowen Wang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Recent studies on human mobility show that human movements are not random and tend to be clustered. In this connection, the movements of Twitter users captured by geo-located tweets were found to follow similar patterns, where a few geographic locations dominate the tweeting activity of individual users. However, little is known about the semantics (landuse types) and temporal tweeting behavior at those frequently-visited locations. Furthermore, it is generally assumed that the top two visited locations for most of the users are home and work locales (Hypothesis A) and people tend to tweet at their top locations during a particular time of the day (Hypothesis B). In this paper, we tested these two frequently cited hypotheses by examining the tweeting patterns of more than 164,000 unique Twitter users whom were residents of the city of Chicago during 2014. We extracted landuse attributes for each geo-located tweet from the detailed inventory of the Chicago Metropolitan Agency for Planning. Top-visited locations were identified by clustering semantic enriched tweets using a DBSCAN algorithm. Our results showed that although the top two locations are likely to be residential and occupational/educational, a portion of the users deviated from this case, suggesting that the first hypothesis oversimplify real-world situations. However, our observations indicated that people tweet at specific times and these temporal signatures are dependent on landuse types. We further discuss the implication of confounding variables, such as clustering algorithm parameters and relative accuracy of tweet coordinates, which are critical factors in any experimental design involving Twitter data.

Original languageEnglish (US)
Title of host publicationProceedings of the 1st International ACM SIGSPATIAL Workshop on Smart Cities and Urban Analytics, UrbanGIS 2015
PublisherAssociation for Computing Machinery, Inc
Pages55-58
Number of pages4
ISBN (Electronic)9781450339735
DOIs
StatePublished - Nov 3 2015
Event1st International ACM SIGSPATIAL Workshop on Smart Cities and Urban Analytics, UrbanGIS 2015 - Bellevue, United States
Duration: Nov 3 2015Nov 6 2015

Publication series

NameProceedings of the 1st International ACM SIGSPATIAL Workshop on Smart Cities and Urban Analytics, UrbanGIS 2015

Other

Other1st International ACM SIGSPATIAL Workshop on Smart Cities and Urban Analytics, UrbanGIS 2015
CountryUnited States
CityBellevue
Period11/3/1511/6/15

Fingerprint

Semantics
Clustering algorithms
Design of experiments
Planning

Keywords

  • Big data
  • Human mobility
  • Semantic trajectories
  • Social media
  • Twitter
  • Urban activity

ASJC Scopus subject areas

  • Civil and Structural Engineering
  • Building and Construction

Cite this

Soliman, A., Padmanabhan, A., Yin, J., Soltani, K., & Wang, S. (2015). Where Chicagoans tweet the most: Semantic analysis of preferential return locations of Twitter users. In Proceedings of the 1st International ACM SIGSPATIAL Workshop on Smart Cities and Urban Analytics, UrbanGIS 2015 (pp. 55-58). [2835032] (Proceedings of the 1st International ACM SIGSPATIAL Workshop on Smart Cities and Urban Analytics, UrbanGIS 2015). Association for Computing Machinery, Inc. https://doi.org/10.1145/2835022.2835032

Where Chicagoans tweet the most : Semantic analysis of preferential return locations of Twitter users. / Soliman, Aiman; Padmanabhan, Anand; Yin, Junjun; Soltani, Kiumars; Wang, Shaowen.

Proceedings of the 1st International ACM SIGSPATIAL Workshop on Smart Cities and Urban Analytics, UrbanGIS 2015. Association for Computing Machinery, Inc, 2015. p. 55-58 2835032 (Proceedings of the 1st International ACM SIGSPATIAL Workshop on Smart Cities and Urban Analytics, UrbanGIS 2015).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Soliman, A, Padmanabhan, A, Yin, J, Soltani, K & Wang, S 2015, Where Chicagoans tweet the most: Semantic analysis of preferential return locations of Twitter users. in Proceedings of the 1st International ACM SIGSPATIAL Workshop on Smart Cities and Urban Analytics, UrbanGIS 2015., 2835032, Proceedings of the 1st International ACM SIGSPATIAL Workshop on Smart Cities and Urban Analytics, UrbanGIS 2015, Association for Computing Machinery, Inc, pp. 55-58, 1st International ACM SIGSPATIAL Workshop on Smart Cities and Urban Analytics, UrbanGIS 2015, Bellevue, United States, 11/3/15. https://doi.org/10.1145/2835022.2835032
Soliman A, Padmanabhan A, Yin J, Soltani K, Wang S. Where Chicagoans tweet the most: Semantic analysis of preferential return locations of Twitter users. In Proceedings of the 1st International ACM SIGSPATIAL Workshop on Smart Cities and Urban Analytics, UrbanGIS 2015. Association for Computing Machinery, Inc. 2015. p. 55-58. 2835032. (Proceedings of the 1st International ACM SIGSPATIAL Workshop on Smart Cities and Urban Analytics, UrbanGIS 2015). https://doi.org/10.1145/2835022.2835032
Soliman, Aiman ; Padmanabhan, Anand ; Yin, Junjun ; Soltani, Kiumars ; Wang, Shaowen. / Where Chicagoans tweet the most : Semantic analysis of preferential return locations of Twitter users. Proceedings of the 1st International ACM SIGSPATIAL Workshop on Smart Cities and Urban Analytics, UrbanGIS 2015. Association for Computing Machinery, Inc, 2015. pp. 55-58 (Proceedings of the 1st International ACM SIGSPATIAL Workshop on Smart Cities and Urban Analytics, UrbanGIS 2015).
@inproceedings{ba4ba04ebf424915bc2b765a9fc3896b,
title = "Where Chicagoans tweet the most: Semantic analysis of preferential return locations of Twitter users",
abstract = "Recent studies on human mobility show that human movements are not random and tend to be clustered. In this connection, the movements of Twitter users captured by geo-located tweets were found to follow similar patterns, where a few geographic locations dominate the tweeting activity of individual users. However, little is known about the semantics (landuse types) and temporal tweeting behavior at those frequently-visited locations. Furthermore, it is generally assumed that the top two visited locations for most of the users are home and work locales (Hypothesis A) and people tend to tweet at their top locations during a particular time of the day (Hypothesis B). In this paper, we tested these two frequently cited hypotheses by examining the tweeting patterns of more than 164,000 unique Twitter users whom were residents of the city of Chicago during 2014. We extracted landuse attributes for each geo-located tweet from the detailed inventory of the Chicago Metropolitan Agency for Planning. Top-visited locations were identified by clustering semantic enriched tweets using a DBSCAN algorithm. Our results showed that although the top two locations are likely to be residential and occupational/educational, a portion of the users deviated from this case, suggesting that the first hypothesis oversimplify real-world situations. However, our observations indicated that people tweet at specific times and these temporal signatures are dependent on landuse types. We further discuss the implication of confounding variables, such as clustering algorithm parameters and relative accuracy of tweet coordinates, which are critical factors in any experimental design involving Twitter data.",
keywords = "Big data, Human mobility, Semantic trajectories, Social media, Twitter, Urban activity",
author = "Aiman Soliman and Anand Padmanabhan and Junjun Yin and Kiumars Soltani and Shaowen Wang",
year = "2015",
month = "11",
day = "3",
doi = "10.1145/2835022.2835032",
language = "English (US)",
series = "Proceedings of the 1st International ACM SIGSPATIAL Workshop on Smart Cities and Urban Analytics, UrbanGIS 2015",
publisher = "Association for Computing Machinery, Inc",
pages = "55--58",
booktitle = "Proceedings of the 1st International ACM SIGSPATIAL Workshop on Smart Cities and Urban Analytics, UrbanGIS 2015",

}

TY - GEN

T1 - Where Chicagoans tweet the most

T2 - Semantic analysis of preferential return locations of Twitter users

AU - Soliman, Aiman

AU - Padmanabhan, Anand

AU - Yin, Junjun

AU - Soltani, Kiumars

AU - Wang, Shaowen

PY - 2015/11/3

Y1 - 2015/11/3

N2 - Recent studies on human mobility show that human movements are not random and tend to be clustered. In this connection, the movements of Twitter users captured by geo-located tweets were found to follow similar patterns, where a few geographic locations dominate the tweeting activity of individual users. However, little is known about the semantics (landuse types) and temporal tweeting behavior at those frequently-visited locations. Furthermore, it is generally assumed that the top two visited locations for most of the users are home and work locales (Hypothesis A) and people tend to tweet at their top locations during a particular time of the day (Hypothesis B). In this paper, we tested these two frequently cited hypotheses by examining the tweeting patterns of more than 164,000 unique Twitter users whom were residents of the city of Chicago during 2014. We extracted landuse attributes for each geo-located tweet from the detailed inventory of the Chicago Metropolitan Agency for Planning. Top-visited locations were identified by clustering semantic enriched tweets using a DBSCAN algorithm. Our results showed that although the top two locations are likely to be residential and occupational/educational, a portion of the users deviated from this case, suggesting that the first hypothesis oversimplify real-world situations. However, our observations indicated that people tweet at specific times and these temporal signatures are dependent on landuse types. We further discuss the implication of confounding variables, such as clustering algorithm parameters and relative accuracy of tweet coordinates, which are critical factors in any experimental design involving Twitter data.

AB - Recent studies on human mobility show that human movements are not random and tend to be clustered. In this connection, the movements of Twitter users captured by geo-located tweets were found to follow similar patterns, where a few geographic locations dominate the tweeting activity of individual users. However, little is known about the semantics (landuse types) and temporal tweeting behavior at those frequently-visited locations. Furthermore, it is generally assumed that the top two visited locations for most of the users are home and work locales (Hypothesis A) and people tend to tweet at their top locations during a particular time of the day (Hypothesis B). In this paper, we tested these two frequently cited hypotheses by examining the tweeting patterns of more than 164,000 unique Twitter users whom were residents of the city of Chicago during 2014. We extracted landuse attributes for each geo-located tweet from the detailed inventory of the Chicago Metropolitan Agency for Planning. Top-visited locations were identified by clustering semantic enriched tweets using a DBSCAN algorithm. Our results showed that although the top two locations are likely to be residential and occupational/educational, a portion of the users deviated from this case, suggesting that the first hypothesis oversimplify real-world situations. However, our observations indicated that people tweet at specific times and these temporal signatures are dependent on landuse types. We further discuss the implication of confounding variables, such as clustering algorithm parameters and relative accuracy of tweet coordinates, which are critical factors in any experimental design involving Twitter data.

KW - Big data

KW - Human mobility

KW - Semantic trajectories

KW - Social media

KW - Twitter

KW - Urban activity

UR - http://www.scopus.com/inward/record.url?scp=84980377965&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84980377965&partnerID=8YFLogxK

U2 - 10.1145/2835022.2835032

DO - 10.1145/2835022.2835032

M3 - Conference contribution

AN - SCOPUS:84980377965

T3 - Proceedings of the 1st International ACM SIGSPATIAL Workshop on Smart Cities and Urban Analytics, UrbanGIS 2015

SP - 55

EP - 58

BT - Proceedings of the 1st International ACM SIGSPATIAL Workshop on Smart Cities and Urban Analytics, UrbanGIS 2015

PB - Association for Computing Machinery, Inc

ER -