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

PROCEEDINGS OF THE 15TH ACM WEB SCIENCE CONFERENCE, WEBSCI 2023(2023)

引用 0|浏览42
暂无评分
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.
更多
查看译文
关键词
geotagging,check-in,twitter,social media,location sharing
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要