B. Data Analysis Methods
This section introduces and discusses methods for digital data analysis. While there are many ways to define and characterize digital analysis methods, this section is structured according to the following broad families of methods:
Digital analysis often overlap to a great extent with more "traditional" methods. However there are also some special questions to consider. Digital methods, as distinguished from "traditional" methods, often deal with data gathered from different digital sources, which in most cases comprise data gathered from the internet and social media (but not always, see Salganik 2019 ch. 2.2). Importantly, digital research materials in the social sciences and humanities are highly various, and often might contain text, pictures, and increasingly also audio and video material.
While digital data can be analysed using traditional methods in social sciences, such as textual or visual analyses, they also lend for digitally enhanced and computational approaches. Digital data themselves can be processed automatically, for example, through text mining techniques. As in the case of more traditional data sources, digital data often are associated with metadata – or, information that does not in itself constitute data contents, but instead is related to it and describes the contents. For instance, in the case of Twitter data, digital methods can be used to explore timestamps, senders' names or even data that shows which browser or app was used by the tweeter. Data can also be enriched through mining them, or new data sets and new variables. To continue with the example of Twitter, tweet data can be enriched by adding information about the hashtags used in them. These features of the data (see Huhtamäki & Laaksonen 2017) can then be explored with a variety of methods, e.g., examining their frequency, carrying out network analysis, or identifying clusters in the data. Some approaches need specialized software or programming skills – however, many tools are well documented and already partially built, so in many cases it is not necessary to build everything from scratch.
The subsections give more examples of tools and discuss the different families of methods in more detail. Below is a list of resoruces that introduce different analysis methods and discuss methodological aspects related to their use.
Research Methods Web Resources
Menetelmäopetuksen Tietovaranto (FIN)
Methods Map by the University of Jyväskylä
The internet is full of tutorials! If you are puzzled by how to do, for instance, social network analysis, see if there are some good YouTube tutorials about it!
Books and Articles
Fielding, Nigel; Lee, Raymond & Blank, Grant (eds.) (2008). The SAGE Handbook of Online Research Methods. London: SAGE Publications Ltd. (Helka)
Huhtamäki, Jukka & Laaksonen, Salla-Maaria (2017). Näin laadullinen tieto jalostuu laskennalliseksi: piirteet sosiaalisen median analytiikassa. Rajapinta-blogi 16.10.2017.
Ignatow, Gabe; Mihalcea, Rada (2017) An Introduction to text mining. Research design, data collection and analysis. SAGE.
- General introduction with special sections on analysing narratives, themes, and metaphors
Marres, Noortje (2012). The Redistribution of Methods: On Intervention in Digital Social Research, Broadly Conceived. The Sociological Review 60:1, 139–165.
Salganik, Matthew (2019). Bit by bit: Social research in the digital age. Princeton University Press. [free online version]
- Bit by Bit offers a general introduction for social scientists to working with big data and other digital methods such as surveys and experiments.
Salmons, Janet (2016). Doing Qualitative Research Online. London: SAGE Publications Ltd.
- This book is about designing online qualitative studies; The ethics of online study; Collecting qualitative data; Analysing data and reporting findings