C4.5: programs for machine learning
C4.5: programs for machine learning
Social networks, gender, and friending: An analysis of MySpace member profiles
Journal of the American Society for Information Science and Technology
The convergence of social and technological networks
Communications of the ACM - Remembering Jim Gray
Proceedings of the fourth international conference on Communities and technologies
The WEKA data mining software: an update
ACM SIGKDD Explorations Newsletter
Data mining emotion in social network communication: Gender differences in MySpace
Journal of the American Society for Information Science and Technology
Analysis of privacy in online social networks of runet
Proceedings of the 3rd international conference on Security of information and networks
Imagined communities: awareness, information sharing, and privacy on the facebook
PET'06 Proceedings of the 6th international conference on Privacy Enhancing Technologies
| Hi-index | 0.03 |
Online communities such as forums, general purpose social networking and dating sites, have rapidly become one of the important data sources for analysis of human behavior fostering research in different scientific domains such as computer science, psychology, anthropology, and social science. The key component of most of the online communities and Social Networking Sites (SNS) in particular, is the user profile, which plays a role of a self-advertisement in the aggregated form. While some scientists investigate privacy implications of information disclosure, others test or generate social and behavioral hypotheses based on the information provided by users in their profiles or by interviewing members of these SNS. In this paper, we apply a number of analytical procedures on a large-scale SNS dataset of 10 million public profiles with more than 40 different attributes from one of the largest dating sites in the Russian segment of the Internet to explore similarities and differences in patterns of self-disclosure. Particularly, we build gender classification models for the residents of the 35 most active countries, and investigate differences between genders within and across countries. The results show that while Russian language and culture are unifying factors for people's interaction on the dating site, the patterns of self-disclosure are different across countries. Some geographically close countries exhibit higher similarity between patterns of self-disclosure which was also confirmed by studies on cross-cultural differences and personality traits. To the best of our knowledge, this is the first attempt to conduct a large-scale analysis of SNS profiles, emphasize gender differences on a country level, investigate patterns of self-disclosure and to provide exact rules that characterize genders within and across countries.