Discussions of 'big data' are everywhere. To some it heralds the end of the 'paradigm wars' and the dawn of a new golden age of robust computational social science. For others, 'big data' is far from being a panacea, and is merely another tool in the researcher's toolbox, and one that needs subjecting to the same methodological questioning as any other method.
What is 'big data' anyway? Do you plan to use to 'big data' in your research? What do you think it will offer you? Or is 'big data' no big deal?
After the US election, it is hard to say Big Data is not a big deal. The campaigns relied on Big Data (http://goo.gl/hqwwf) and Nate Silver (http://fivethirtyeight.blogs.nytimes.com/) and others did a great job in predicting the results. But one should acknowledge that election data was abundant, of good quality (at least not bad), and that it is not about causal inference and explanation, but forecasting.
You may also be interested in the slides from the event run recently by Sage and the ESRC at the British Academy on Big Data.
Greetings, let me reply, even though my level of english is not enough, sorry.
As a Psychologist and Methodologist, working in a latin american country, we are going to define and to study social phenomena that are strongly linked to real contexts. I can see a despairing searching for methodologies that enable researchers to take into account needs that are in the opposite side to "big data" studies. In fact, that means that all researchers, specially in clinical psychology and educational psychology, are asking for methods related to small n-samples, instead big samples. In fact, I think there is a lack of information and procedures in small data samples, in contrast with big data studies. I recently read "Single Case and Small-n Experimental Design", that's people wants now.
I can perceive a lot of distrust with big data procedures, because the main focus is, first: study big databases, second: make a hypothesis. But specially in psychology, methodologies emphasize the reverse process.
I'm trying to dive into big data procedures, but honestly, professionals here, are searching for a different perspective.
I am excited about the possible 'big data' applications in social science, provided that the measures used when compiling are closely exmined and deemed comparable, which may be a significant issue. With that said, because of the funding issues often faced in areas related to the social sciences (as opposed to the 'hard' sciences), I would like to see data sets available for social constructs similar to what is now available for genetics studies through the Human Genome Project.
if you are interested in learning more about managing 'big data', what about attending a free online-course from coursera?
'...about building `web-intelligence' applications exploiting big data sources arising social media, mobile devices and sensors, using new big-data platforms based on the 'map-reduce' parallel programming paradigm.'
You can register now and will receive notification about the upcoming course (Python 2.7 on your PC is needed)
I do not know if there is anything that can be calssified as big or small data. What one looks for is the meaning of that data in relation to one's research. For me any data that can sufficiently help in understanding my research problem is good enough.
I do not believe in quantity rather i believe in the quality of the data.