Abstract

The key element of Facebook social network platform is the status updates, in which the user can upload text or other media such as pictures and videos. In this study, we manually classified more than 3500 Facebook status updates (FSUs) by the subject, the emotional activation, the medium used, the originality and the degree of self-referential content. We then cross-tabulated that information with demographic factors such as gender and occupation. Thirty students participated in the categorization task, each annotating more than 100 FSUs of their Facebook friends' FSUs. Statistical and supervised machine learning analysis was then applied to the categorized features. The text itself was not analyzed further after the annotation for the purpose of preserving the privacy and anonymity of the FSU authors. Results show that FSUs vary in subject, emotional connotation and structure as a function of demographic factors like gender and occupation of the poster. Statistical analysis and supervised machine learning are able to predict the demographic and emotional expressions based on the other features annotated by the participants.

Highlights

  • The Online Social Network (OSN) of Facebook has over 1,39 billion monthly active users, with approximately 20% of its users residing in United States [6]

  • The statistical analysis of the behavioral classification showed that, concerning the emotional content, women were more positive than men, F(1, 3534)=13.756, p=.00021 and workers were more positive than students, F(1, 3534)=7.02, p=

  • The Facebook status updates (FSUs) functionality is the key element of Facebook, in which users typically share interests and life experiences under the formats of text, pictures and videos

Read more

Summary

Introduction

The Online Social Network (OSN) of Facebook has over 1,39 billion monthly active users, with approximately 20% of its users residing in United States [6]. Studying Facebook allows social scientists to study a wealth of measureable behavior versus the traditional gathering of selfreports that they are used to relying upon [9]. Facebook identity is a study of online behavior; it has permeated offline reality so that the two are partially integrated [3,10]. This reality extends out to networks from high school, college, workplaces and professional networks, special interest groups, and regions. It extends out to Facebook real-estate that is integrated with other websites and applications

Methods
Results
Conclusion
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call