and eBooks, new tools for statistical analysis that promote inter-operability between analysis packages and sharing through better documentation of analysis routines.
Chapter 8: Text Mining and Social Media: When Quantitative Meets Qualitative and Software Meets People
Text mining has developed dramatically in recent years in its power to analyse and extract information from very large bodies of unstructured text. Its applications are motivated by a growing awareness that researchers need more powerful tools in order to benefit from rapidly increasing amounts of textual data being generated through the proliferation and unprecedented levels of take up of Web 2.0 technologies. Chief among these are blogs and social media (‘micro-blogs’), the latter exemplified by the rise of platforms such as Facebook and Twitter.
In this chapter, Ampofo, Collister, O’Loughlin and Chadwick explore how text mining using natural language processing (NLP) techniques can provide qualitative social researchers with powerful analytical tools for extracting information from this unstructured data, including harvesting data and analysing it in real time. They survey the range of research tools for text mining, broadly defined, available both in the academic and commercial spheres. People’s use of social media is seen by many researchers as providing an ideal source of data through which to monitor rapidly changing situations, hence, it has come to particular prominence during civil unrest (e.g., the so-called ‘Arab Spring’) and natural disasters (e.g., Hurricane Sandy). Beyond these inherently unpredictable phenomena, one of the most popular emerging applications of social media analysis lies in the tracking of public opinion through the application of NLP-based techniques such as sentiment analysis. These techniques have the capacity to generate results in real time, which offers intriguing possibilities for both commercial and academic research.
To illustrate the potential and challenges of using text mining techniques in social research, Ampofo, Collister, O’Loughlin and Chadwick present overviews of two projects. The first is a study of social media during the televised debates between political party leaders in the 2010 UK general election campaign. The second is also drawn from this election campaign and focuses on the reporting of accusations of bullying against then-Prime Minister Gordon Brown in the British media. The application of NLP-based text analysis tools to social data is still, in many respects, in its infancy. With this thought in mind, the authors conclude by outlining the ontological challenges (echoing the reservations that Elliot and Purdam set out in Chapter 3) and the technical challenges of mining text in social research settings. They note, in the case of social media, increasingly restrictive access policies, and they also consider the ethical implications of text mining used as a social research tool.
Chapter 9: Digital Records and the Digital Replay System
As many of the contributors to this book recognize, the capacity to capture behaviour through the ‘digital footprint’ that people generate as a by-product of their everyday activities has the potential to transform the practice of empirical social science. In this chapter, Crabtree, Tennent, Brundell and Knight examine how new tools for data collection and analysis make it possible to exploit this data. Their discussion focuses in particular on the development of ‘digital records’ that enable social science researchers to combine novel and heterogeneous forms of digital data, such as video, text message logs and GPS data, with more traditional and established forms, such as audio recordings and transcriptions of talk.
The authors describe the Digital Replay System (DRS), an open source, extensible suite of interoperable tools for assembling, synchronizing, visualizing, curating and analysing digital records.3 In Chapter 5, Lambert presents solutions to the data management problems attendant in the use of conventional kinds of social data such as surveys. From this perspective, DRS can be viewed as a prototype for meeting the data management and linking challenges presented by novel sources of social data. Crabtree and his co-authors provide a step-by-step exposition of several different examples; these include capturing rich accounts of people’s physiological reactions while on a fairground ride, a corpus linguistics perspective on visitors’ interactions in an art gallery, and disaster mapping and management. Collectively, these examples illustrate how the use of a system like DRS can enable the assembly of digital records capturing a wide range of interactions between people that are a by-product of their use of various digital devices, and make them available for subsequent visualization, curation and analysis. Finally, the authors consider future developments, particularly the prospects for making use of mass participation in social science research through the use of mobile devices for the crowd-sourcing of data.
Chapter 10: Social Network Analysis
The distinctive contribution of social network analysis (SNA) to social research is its stress on the importance of studying the structure of relationships between people rather than considering them as unconnected individuals. Like many of the other advances in research methods covered in this book, SNA is a mature methodological tool. Arguably, it owes its rise to greater prominence in recent years to two factors. One is that, as with many other established social research methodologies, e-Infrastructure has extended the scale and complexity of what is achievable, in this case by providing SNA with new and more powerful means to capture social network datasets, analyse them and visualize the results. The second factor is that many of the new types and sources of digital social data – such as hyperlink networks (the structures of links between websites) and social networking sites such as Facebook and Twitter – are inherently relational.
In this chapter, Ackland and Zhu review the history and methodological principles of SNA, and survey several of the research tools now available for SNA data collection, analysis and visualization. They draw on examples of studies of Facebook, Twitter, Flickr, online newsgroups and websites to illustrate contemporary and arguably the most prominent uses of SNA – to study people’s behaviour in social networking sites. Ackland and Zhu go on to discuss two key ontological questions associated with SNA as a research methodology. The first is its ‘construct validity’, an issue that has potentially major implications. Simply put, the question is: do the social structures observed in, for example, Facebook, have real-world analogies or are they properties only of the online world, entirely unrelated to its real world counterpart? If the answer is no, then arguably, for all the talk about the opportunities for social research offered by new sources of social data, the impact in terms of increased understanding of social phenomena will be very limited.
Ackland and Zhu’s second question relates to debates about the capacity of social research methodologies to distinguish between causality and correlation. Here, they offer a somewhat more optimistic prognosis, observing that data generated through people’s activity on, for example, social networking sites, is rich and time-stamped, allowing for more fine-grained analysis, while the sites themselves can be thought of as natural research instruments, ideal for carrying out large scale experiments.4 Like other contributors to this volume, they conclude with a warning about the pitfalls for researchers of relying on data sources, such as Facebook, that are proprietary and whose access is subject to terms and conditions that may change at any time.
Chapter 11: Visualizing Spatial Data and Social Media
As earlier chapters have emphasized, the social data landscape is changing at an ever-increasing pace. The ways in which data is visualized has always played an important role in its analysis and in the presentation of results, and the ever-increasing volumes of data raise new challenges for visualization methods and tools. In this chapter, following a brief history of geographic information systems (GIS), Batty and his colleagues describe new ways of visualizing social
