Geolocated Social Media Posts are Happier: Understanding the Characteristics of Check-in Posts on Twitter

被引:2
作者
Jiang, Julie [1 ]
Thomason, Jesse [2 ]
Barbieri, Francesco [3 ]
Ferrara, Emilio [4 ]
机构
[1] Univ Southern Calif, Inst Informat Sci, Viterbi Sch Engn, Los Angeles, CA 90007 USA
[2] Univ Southern Calif, Inst Informat Sci, Los Angeles, CA 90007 USA
[3] Snap Inc, Santa Monica, CA 90405 USA
[4] Univ Southern Calif, Annenberg Sch Commun, Viterbi Sch Engn, Inst Informat Sci, Los Angeles, CA 90007 USA
来源
PROCEEDINGS OF THE 15TH ACM WEB SCIENCE CONFERENCE, WEBSCI 2023 | 2023年
关键词
geotagging; check-in; twitter; social media; location sharing; LOCATION; DISCLOSURE; BEHAVIOR;
D O I
10.1145/3578503.3583596
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
The increasing prevalence of location sharing features on social media has enabled researchers to ground computational social science research using geolocated data, affording opportunities to study human mobility, the impact of real-world events, and more. This paper analyzes what crucially separates tweets with geotags from tweets without. Our findings show that geotagged tweets are not representative of Twitter data at large, limiting the generalizability of research that uses only geolocated data. We collected 1.3M geotagged tweets on Twitter (most of which came from Instagram), and compared them with a random dataset of tweets on three aspects: affect, content, and audience engagement. We show that geotagged tweets on Twitter exhibit significantly more positivity, often citing joyous and special events such as weddings, graduations, and vacations. They also convey more collectivism by using more first-person plural pronouns and contain more additional features such as hashtags or objects in images. However, geotagged tweets generate less engagement. These findings suggest there exist significant differences in the messages conveyed in geotagged posts. Our research carries important implications for future research utilizing geolocation social media data.
引用
收藏
页码:136 / 146
页数:11
相关论文
共 63 条
[1]   A survey of location inference techniques on Twitter [J].
Ajao, Oluwaseun ;
Hong, Jun ;
Liu, Weiru .
JOURNAL OF INFORMATION SCIENCE, 2015, 41 (06) :855-864
[2]  
[Anonymous], 2013, MOBILEHCI 13, DOI DOI 10.1145/2493190.2493209
[3]  
[Anonymous], 2010, Em: A Journal of Law and Policy for the Information Society
[4]  
[Anonymous], 2013, P 1 ACM C ONLINE SOC, DOI [DOI 10.1145/2512938.2512956, 10.1145/2512938.2512956]
[5]  
Barbieri F, 2020, FINDINGS OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, EMNLP 2020, P1644
[6]  
Benton Joshua, 2019, Twitter is removing precise-location tagging on tweets-a small win for privacy but a small loss for journalists and researchers
[7]   Quantifying crowd size with mobile phone and Twitter data [J].
Botta, Federico ;
Moat, Helen Susannah ;
Preis, Tobias .
ROYAL SOCIETY OPEN SCIENCE, 2015, 2 (05)
[8]   College students' disclosure of location-related information on Facebook [J].
Chang, Chen-Wei ;
Chen, Gina Masullo .
COMPUTERS IN HUMAN BEHAVIOR, 2014, 35 :33-38
[9]  
Cho Eunjoon, 2011, P 17 ACM SIGKDD INT, P1082
[10]   The Geospatial Characteristics of a Social Movement Communication Network [J].
Conover, Michael D. ;
Davis, Clayton ;
Ferrara, Emilio ;
McKelvey, Karissa ;
Menczer, Filippo ;
Flammini, Alessandro .
PLOS ONE, 2013, 8 (03)