Digital data presents a wealth of possibilities for new data collection, thereby expanding the scope of research questions that can be answered within the social sciences. Yet, new efforts are plagued by the twin problems of technological complexity and generalizability. In this half day workshop, we present an overview of survey research for sampling and its application to questions about the Internet. We then turn to new sources for collecting data such as Twitter and Facebook, and then consider them within the lessons learned from traditional survey research.
Topics to be Covered
Surveys as a data collection tool: How and why do we generalize from samples?
Online survey tools: Survey Gizmo, LimeSurvey – are these tools fit for large scale research and how complex are they to deploy?
Non-reactive data: Twitter, Facebook, Social News – what data is available or not through the major social media platforms?
Packages for online data: NodeXL – open tool for collecting network data on social media through a point and click interface.
Coding environments: Introducing Python – when all else fails why should we consider scripting as a means for data collection?
Who Should Take This Course?
The workshop will present a number of examples of online surveys and analyses of Twitter and Facebook, and also enable students to bring and discuss questions and issues from their own research and thesis projects. Students with an interest in quantitative methods for making claims about and through the internet will find this course especially useful.
The workshop will introduce the audience to online survey tools as well as tools for capturing data from Twitter and Facebook. In particular, we cover Limesurvey and NodeXL, two recent free offerings designed to simplify data collection for social scientists. The course requires no prior experience with coding or statistics.
The workshop will include presentations and demonstrations, and enable participants to bring their needs for surveys and survey data. It will discuss issues including data collection, sampling, representativeness, and different online survey tools and approaches.
Hansen, D., Smith, M. A., Shneiderman, B. (2010) Analyzing Social Media with NodeXL. New York: Morgan Kaufman.
Russell, M. (2011) Mining the Social Web. Sebastopol, CA: O’Reilly Media. Fielding, N., Lee, R., Blank, G. (2008) The Sage Handbook of Online Research Methods. Thousand Oaks, CA: Sage Publications.
About the speakers