Understanding user’s identifiability on social media: a supervised machine learning and self-reporting investigation

Abstract

The identifiability of users as they interact in the digital world is fundamentally linked to privacy and security issues. Identifiability can be divided into two: subjective identifiability, which is based on psychological perceptions (i.e., mental space), and objective identifiability, which is based on social media data (i.e., information space). This study constructs a prediction model for social media data identifiability of users based on a supervised machine learning technique. The findings, based on data from Weibo, a Chinese social media platform, indicate that the top seven features and values for predicting social media identifiability include blog pictures (0.21), blog location (0.14), birthdate (0.12), location (0.10), blog interaction (0.10), school (0.08), and interests and hobbies (0.07). The relationship between machine-predicted and self-reported identifiability was tested using data from 91 participants. Based on the degree of deviation between the two, users can be divided into four categories—normal, conservative, active, and atypical—which reflect their sensitivity to privacy concerns and preferences regarding information disclosure. This study provides insights into the development of privacy protection strategies based on social media data classification.