Big data, computational social science, and other recent innovations in social network analysis

Area of Science:

• Social Sciences, Computer Science, Data Science

Background:

• Social network analysis (SNA) has a century-long history in sociology.
• Recent advancements in data, technology, and analytical methods position SNA for significant impact in big data and computational social science (CSS).

Purpose of the Study:

• To review key developments and emerging areas in computational social network analysis.
• To highlight opportunities for SNA in the context of big data and CSS.

Main Methods:

• Review of literature focusing on four core topics: data collection, network types, statistical inference, and ethics.
• Analysis of recent trends in web data collection for social networks.
• Examination of non-traditional network structures (bipartite, multi-mode, discourse, semantic, social-ecological).
• Overview of recent statistical inference techniques for network data.
• Discussion of ethical challenges in computational network research.

Main Results:

• Social network data collection from the web is increasingly feasible.
• New network types like bipartite, discourse, semantic, and social-ecological networks offer expanded analytical possibilities.
• Significant progress has been made in statistical inference methods for network analysis.
• Ethical considerations are paramount in computational network research.

Conclusions:

• Computational social network analysis is a rapidly growing field with substantial potential.
• The integration of big data and CSS methodologies is transforming SNA.
• Future research should address data collection, advanced network modeling, statistical rigor, and ethical guidelines.