Collaborative Online Social Media Observatory (COSMOS): Social Media and Data Mining
The Collaborative Online Social Media Observatory (COSMOS) is an Economic and Social Research Council (ESRC) strategic “Big Data” investment that brings together social, computer, political, health, statistical and mathematical scientists to study the methodological, theoretical, empirical and technical dimensions of social media data in social and policy contexts. This empirical data science programme is complemented by a focus on the ethical impact of big social data and the development of new methodological tools and technical/data solutions for the UK academic and public sectors. Our £1.5M research programme has been funded by the Economic and Social Research Council, Engineering and Physical Sciences Research Council, Partnership for Conflict, Crime and Security Research Programme (Global Uncertainties Programme), Joint Information Systems Committee, Department of Health, Food Standards Agency, High Performance Computing Wales/Fujitsu, Welsh Government and Airbus Group.
As part of our programme of research we have developed the COSMOS software platform that reduces the technical and methodological barriers to accessing and analysing social media and other forms of open digital data. The COSMOS platform is set apart from all other existing social media analysis software due to its novelty in five areas: i) it is supported and informed by rigorous methodological and technical research conducted by an interdisciplinary team (computer and social scientists) that informs users in their analysis; ii) the platform allows for the linking of multiple digital data sources (social media, other digital, curated and administrative); iii) it integrates a number of data analysis tools using a workflow model (e.g. sentiment analysis can be followed by a social network analysis, which can then be geo-located); iv) its analysis algorithms are open, transparent, inspectable and refreshable/adaptable by users; and v) users do not need any knowledge of programming. The platform is free to academic and public sector users conducting not-for-profit research.