I attended last week (unfortunately only part of) an interesting workshop on the effects of today’s abundance and diversity of digital data on social science practices, aptly called “Science XXL“. A variety of topics were discussed and different research experiences were shared, but I’ll just summarize here a few lessons learned that I find interesting.
- Digital data are archive data. Data retrieved automatically from the digital traces of individual actions, such as those mined from the APIs of platforms such as Twitter, are unlike survey data in that they were not originally recorded for research purposes. The researcher must select relevant records on the basis of some understanding of the conditions under which these data were produced. Perhaps ironically, digital data share these characteristic with data from historical or literary archives.
- Digital data are not necessarily “big”, in the sense that their volume is often small (at least in social science research so far!), even though they may share other characteristics of big data such as velocity (being generated on the fly as people use digital platforms) or variety (being little or not structured).
- Digital data can help fill gaps in survey data, for example when survey sampling is not statistically representative: detail and volume can provide extra information that supports general conclusions.
- Non-clean data, outliers and aberrant observations may be very informative, revealing details that would escape attention if researchers focused only on the average or center of the distribution (the normal law cherished in classical statistical approaches). Special cases are no longer a prerogative of qualitative research.
- Data analysis is a key ingredient of “computational social science” a field that is growing in importance after an initial phase in which it was largely confined to agent-based simulation and complexity theory.
National Statistical Institutes (NSIs) have long been the recognised repositories of all socio-economic information, mandated by governments to collect and analyse data on their behalf. The development of big data is shaking this world. New actors are coming in and commercially-oriented, privately-produced information challenges the monopoly of NSIs. At the same time, NSIs themselves can tap into digital technologies and produce “big” data. More generally, these new sources offer a range of opportunities, challenges and risks to the work of NSIs.
The Statistical Journal of the IAOS, the flagship journal of the International Association for Official Statistics, has published a special section on big data – of particular interest to the extent that it is free of charge!
Fride Eeg-Henriksen and Peter Hackl introduce this special section by defining big data and emphasising its interest for official statistics. But it is crucial, albeit admittedly not easy, to separate the hype around big data from its actual importance.
The other papers are concrete examples of how big data may be integrated into official statistics:
Continue reading “New publications on big data and official statistics”
I gave a presentation on the topic of “Data and social networks: empowerment and new uncertainties” at the Better Decisions Forum on Big Data and Open Data that took place in Rome on 12 November 2014. The event brought together six speakers from different backgrounds on a variety of topics related to data, and participants were businesspeople, public administration managers, journalists, data and computer scientists.
Here is a video of my talk:
Unfortunately as you will have noticed, the slides are not always very clearly visible, so it’s better to download them from their original source:
My interview before my talk:
See? I am trying to stick to my 1st-January commitment of blogging more this year…
Network data are among those that are changing fastest these days. When I say I study social networks, people almost automatically think of Facebook or Twitter –without necessarily realizing that networks have been around for, well, the whole history of humanity, long before the internet. Networks are just systems of social relationships, and as such, they can exist in any social context — the family, school, workplace, village, church, leisure club, and so forth. Social scientists started mapping and analysing networks as early as the 1930s. But people didn’t think of their social relationships as “networks” and didn’t always see themselves as “networkers” even if they did invest a lot in their relationships, were aware of them, and cared about them. The term, and the systemic configuration, were just not familiar. There was something inherently informal and implicit about social ties.
What has changed with Facebook and its homologues, is that the network metaphor has become explicit. People are now accustomed to talking about “networks”, and think in systemic terms, seeing their own relationships as part of a more global structure. Network ties have become formal — you have to make a clear choice and action when you add a “friend” on Facebook, or “follow” someone on Twitter; you will have a list of your friends/followers/followees (whatever the specific terminology is) and monitor changes in this list. You know who the friends of your friends are, and can keep track of how many people viewed your profile /included you in their “lists” / mentioned you in their Tweets. Now, everyone knows what networks are –so if you are a social network researcher and conduct a survey like in the old days, you won’t fear your respondents may misunderstand. In fact, you may not even need to do a survey at all –the formal nature of online ties, digitally recorded and stored, makes it possible to retrieve your network information automatically. You can just mine network tie data from Facebook, Twitter, or whatever service your target populations happen to be using.
Continue reading “Network data, new and old: from informal ties to formal networks”
All the hype today is about Data and Big Data, but this notion may seem a bit elusive. My students sometimes struggle understanding the difference between “data” and “literature”, perhaps because of the unfortunate habit to call library portals “databases”. Even colleagues are sometimes uncomfortable with the notion of data (whether “big” or “small”) and the breadth it is now taking. So, a definition can be helpful.
Data are pieces of unprocessed information – more precisely raw indicators, or basic markers, from which information is to be extracted. Untreated, they hardly reveal anything; subject to proper analysis, they can disclose the inner working of some relevant aspects of reality.
The “typical” example of socioeconomic data is the observations/variables matrix, where each row represents an observation – an individual in a population – and each column represents a variable – a particular indicator about that individual, for example age, gender, or geographical location. (In truth data types are more varied and may also include unstructured text, images, audio and video; But for the sake of simplicity, let’s stick to the Matrix here.)
Continue reading “What is data?”