What (or Who) Is Public? Privacy Settings and Social Media Content Sharing

被引：43

作者：

Fiesler, Casey ^{[1
]}

Dye, Michaelanne ^{[2
]}

Feuston, Jessica L. ^{[3
]}

Hiruncharoenvate, Chaya ^{[2
]}

Hutto, C. J. ^{[2
]}

Morrison, Shannon ^{[4
]}

Roshan, Parisa Khanipour ^{[2
]}

Pavalanathan, Umashanthi ^{[2
]}

Bruckman, Amy S. ^{[2
]}

De Choudhury, Munmun ^{[2
]}

Gilbert, Eric ^{[2
]}

机构：

[1] Univ Colorado, Boulder, CO 80309 USA

[2] Georgia Inst Technol, Atlanta, GA 30332 USA

[3] Northwestern Univ, Evanston, IL 60208 USA

[4] Syracuse Univ, Syracuse, NY 13244 USA

来源：

CSCW'17: PROCEEDINGS OF THE 2017 ACM CONFERENCE ON COMPUTER SUPPORTED COOPERATIVE WORK AND SOCIAL COMPUTING | 2017年

关键词：

privacy; content analysis; Facebook; dataset; machine learning; Mechanical Turk; mixed methods; prediction; research methods; social media; NETWORK;

D O I：

10.1145/2998181.2998223

中图分类号：

TP39 [计算机的应用];

学科分类号：

081203 ; 0835 ;

摘要：

When social networking sites give users granular control over their privacy settings, the result is that some content across the site is public and some is not. How might this content-or characteristics of users who post publicly versus to a limited audience-be different? If these differences exist, research studies of public content could potentially be introducing systematic bias. Via Mechanical Turk, we asked 1,815 Facebook users to share recent posts. Using qualitative coding and quantitative measures, we characterize and categorize the nature of the content. Using machine learning techniques, we analyze patterns of choices for privacy settings. Contrary to expectations, we find that content type is not a significant predictor of privacy setting; however, some demographics such as gender and age are predictive. Additionally, with consent of participants, we provide a dataset of nearly 9,000 public and non-public Facebook posts.

引用

页码：567 / 580

页数：14

共 51 条

[1] Privacy and human behavior in the age of information [J].