Abstract
This paper argues that the basic premise of Social Network Analysis (SNA) -- namely that social reality is constituted by dyadic relations and that social interactions are determined by structural properties of networks-- is neither necessary nor sufficient, for Big Social Data analytics of Facebook or Twitter data. However, there exist no other holistic computational social science approach beyond the relational sociology and graph theory of SNA. To address this limitation, this paper presents an alternative holistic approach to Big Social Data analytics called Social Set Analysis (SSA). Based on the sociology of associations and the mathematics of classical, fuzzy and rough set theories, this paper proposes a research program. The function of which is to design, develop and evaluate social set analytics in terms of fundamentally novel formal models, predictive methods and visual analytics tools for Big Social Data. Four demonstrative case studies, employing SSA, covering the range of descriptive, predictive, visual and prescriptive analytics are presented and briefly discussed.
Original language | English |
---|---|
Title of host publication | Proceedings of the 2015 International Conference on Social Media & Society : SMSociety '15 |
Editors | Anatoliy Gruzd, Jenna Jacobson, Philip Mai, Barry Wellman |
Number of pages | 8 |
Place of Publication | New York |
Publisher | Association for Computing Machinery |
Publication date | 2015 |
Article number | 3 |
ISBN (Print) | 9781450339230 |
ISBN (Electronic) | 9781450339230 |
DOIs | |
Publication status | Published - 2015 |
Event | The 6th International Conference on Social Media & Society. SMSociety 2015 - Toronto, Canada Duration: 27 Jul 2015 → 29 Jul 2015 Conference number: 6 http://smsociety15.sched.org/ |
Conference
Conference | The 6th International Conference on Social Media & Society. SMSociety 2015 |
---|---|
Number | 6 |
Country/Territory | Canada |
City | Toronto |
Period | 27/07/2015 → 29/07/2015 |
Internet address |
Series | ACM International Conference Proceeding Series |
---|