Democratising Access to Social Media Data – the Collaborative Online Social Media ObServatory (COSMOS)

Luke Sloan is a Senior Lecturer in Quantitative Methods and Deputy Director of the Social Data Science Lab at the School of Social Sciences, Cardiff University, UK. Luke has worked on a range of projects investigating the use of Twitter data for understanding social phenomena covering topics such as election prediction, tracking (mis)information propagation during food scares and ‘crime-sensing’. His research focuses on the development of demographic proxies for Twitter data to further understand who uses the platform and increase the utility of such data for the social sciences. He sits as an expert member on the Social Media Analytics Review and Information Group (SMARIG) which brings together academics and government agencies. @DrLukeSloan

The vast amount of data generated on social media platforms such as Twitter provide a rich seam of information for social scientist on opinions, attitudes, reactions, interactions, networks and behaviour that was hitherto unreachable through traditional methods of data collection. The naturally-occurring user-generated nature of the data offers different insights to the social world than that collected explicitly for the purposes of research, thus social media data augments our existing methodological toolkit and allows us to tackle new and exciting research problems.

However, to make the most of a new opportunity we need to learn how the tool works. What does Twitter data look like? How is it generated? How do we access it? How can it be visualised? The bottom line is that, because social media data is so different to anything we have encountered before, it’s hard to understand how it can be collated and used.

That’s where COSMOS comes in. The Collaborative Social Media ObServatory (COSMOS) is a free piece of software that has been designed and built by an interdisciplinary team of social and computer scientists. It provides a simple and visual interface through which users can set up their own Twitter data collections based on random samples or key words and plot this data in maps, as networks or through other visual representations such as word clouds and frequency graphs. COSMOS allows you to play with the data, selecting subsets (such as male and female users) and seeing how they differ in their use of language, sentiment or network interactions. It directly interrogates the ONSAPI and draws in key areas statistics from the 2011 Census, allowing you to investigate the relationship between, for example, population characteristics (Census) and anti-immigrant sentiment by locale (Twitter). Any social media data collected through COSMOS can then be exported in a variety of formats for further analysis in other packages such as SPSS, STATA, R and Gephi.

COSMOS is free to anybody working in academia, government or the third sector – simply go to www.socialdatalab.net and click on the ‘Software’ tab on the top menu bar to request access and view our tutorial videos.

Give it a go and see what you can discover!