New chapter out on text-mining and digital research

A chapter I co-authored on text-mining has (finally!) been published in the Sage publication, Innovations in Digital Research Methods.

51w3SHTuVJLCo-authored with Lawrence Ampofo, Ben O’Loughlin and Andrew Chadwick our chapter covers  researching social media, discussing key techniques for textual analysis and exploring some of the opportunities, limitations and ethical considerations.

The full blurb from the introduction chapter is here:

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.

You can download the introduction over at the Sage website and download a full pre-publication version of the chapter from Royal Holloway’s New Political Communications Unit.

And of course, you can buy a copy of the whole book from Amazon.


Report: PRCA State of Digital PR

I’m really late getting around to posting this, but last month Ketchum’s Danny Whatmough presented the findings of the PRCA’s State of Digital PR report.

The report, which surveyed 136 agency and in-house teams, highlights a number of key themes which for those in and observing the UK’s PR industry should make interesting findings.

It’s a good report but at the moment I just want to pull out a couple of revealing results:

  • Nearly half (46%) of PR practitioners surveys spend only 1-10% of their budget on digital
  • The top activity that measly budget is spent on is web design and build
  • Followed by social media monitoring
  • … and then SEO

I find this interesting partly as while optimists might say that PR is adapting is also highlights the fact that the core digital services undertaken by PR agencies overlap with wider – perhaps more specialised – sectors.

Great that PR is competing on more levels, but does it have the specialist knowledge to compete and win? See my previous post about PR, social media and specialisation.

Conference presentation: Re-Assembling Mediated Power

I was meant to give this presentation last week at the SEDTC conference at Royal Holloway last week but unfortunately wasn’t able to. I thought I’d share it here anyway.

The original abstract is here to give the presentation some context and I’ll hopefully uploading the full paper in due course.

Frames-as-Assemblages – Full conference paper

I’ve eventually found time to finish writing and editing a full version of the conference paper I presented at the Caught in the Frame conference at the University of Leicester last month.

You can see the presentation that accompanies this paper in the post below, but this fuller paper give a more detailed overview of the context in which I’m seeking to develop the notion of frames-as-assemblages. It also draws attention to a number of specific features within assemblages that might offer potentially powerful routes for analysing mediated communications in networked environments.

Arts Council England podcast: social media and UGC

Arts Council England are currently funding a potentially exciting series of digital projects that connect arts organisations, researchers and technology providers to form, in its own words, ” collaborative relationships” that will hopefully create knowledge and practical innovation for people and groups in the creative sectors to improve engagement with audiences and/or explore new business models.

Projects are themed around a number of areas, including:

  • User generated content and social media: harnessing the power of the internet and social media to reach audiences and to give them a platform for discussion, participation and creativity
  • Distribution and exhibition: using digital technologies to deliver artistic experiences and content in new ways in online and place based environments, including exploring international distribution and exhibition
  • Mobile, location and games: developing a new generation of mobile and location-based experiences and services, including games
  • Data and archives: making archives, collections and other data more widely available to other arts organisations and the general public
  • Resources: using digital technologies to improve the way in which arts organisations are run including business efficiency and income generation and the way in which they collaborate with each other
  • Education and learning: developing interactive education and learning resources for children, teachers, young people, adult learners and arts sector professionals

In response to the current projects being delivered – and to showcare some of the interim results – the Arts Council are producing a series of podcasts to discuss the key themes listed above. I took part in the inaugural podcast covering social media and UGC along with Charles Beckett from Arts Council England and Spencer Hyman from Artfinder. You can take a listen via Soundcloud…

The next round of funding for potential projects is now open so if you’re interested head over to the Digital R&D website or take a look at the case studies of current projects.

Assemblages of Resistance – conference paper

Myself and Dan McQuillan have had a joint paper submission accepted for the conference Platform Politics happening in Cambridge in May – 11th to 13th to be exact.

We're working on the paper as I speak but I've shared the abstract below. All feedback welcome…

Assemblages of Resistance – Platform Politics conference paper submission


There's a great line-up and looks like there'll be some interesting discussions. Maybe see you there?

Is this what cutting edge Internet and government research looks like in the UK?

Egov screenshot

Readers of this blog will know that I have a particular interest in edemocracy, politics and the internet. In fact I'd go as far as to say I'm passionate about the ways in which social media and the internet ca be used to empower individuals and government to make our lives and the world around us a better place.

With this in mind you can imagine my excitement to see via Twitter that two towering forces of academia, Oxford University's Internet Institute and London School of Economics Public Policy Group had launched a website, Government on the Web, dedicated to:

"improving knowledge and understanding of e-government and the impact of web-based technologies on government"

"Awesome", I thought. An online repository for research, case studies, practical guides, etc.

Imagine my horror to see the site that has been developed. Take a look at the screenshot above. Yes. That's it. No, I've not searched the Way Back Machine.  That site was designed, built and published *last week*.

I won't list all the failings here – there's too many and it's too mean. But, holy crap, is this representative of the cutting-edge research being done by teams of UK experts in the field? Wow.

Back in 2007 I went to a one-day conference exploring the future of media at Goldsmith's University and blogged that the experience left me feeling that a lot of UK academics don't yet get social media.

Two years on and this site doesn't fill me with much hope that things have changed. The Oxford Internet Institute is twinned with Harvard's Berkman Center? Home to Doc Searls' and his ground-breaking work into VRM. But looking at this site you wouldn't get that impression.

I'll say it again for added emphasis: Wow. Really.


Online monitoring and political behaviour: survey of UK political parties


I popped along to give the keynote speech at a symposium on measuring online political behaviour yesterday organised by Royal Holloway University’s New Political Communications Unit.

In keeping with true keynote style I only managed to get along to
the afternoon sessions at the event, but I still managed to catch a
couple of interesting presentations: one from Rob Pearson at the UK’s Foreign & Commonwealth Office examining the evaluation of its G20 London Summit web presence; the second from Simon Bergman from strategic communications outfit, Information Options.

I was presenting findings from some research I’ve been conducting
into the use of online monitoring by the UK’s three main political
parties: The Conservatives, Labour and the Liberal Democrats which is an area without any in-depth study to date.

I’ve embedded my presentation
above, but be warned – it’s text heavy (hey, it’s tricky articulating
research findings using fancy images) – but here are some of my main

  • All political parties report that they track online influencers qualitatively (e.g. Iain Dale, Guido, Political Betting, etc) but they also reported that they engage with these blogs to help set the national media-agenda (which nicely supports my earlier research).
    Equally, all online or influencer monitoring by parties is performed
    informally – that is, not using paid for or third party tracking tools.
  • One respondent told me that monitoring is about “a gut feeling about what’s going on
    and also the UK political blogosphere is small and well organised. In
    my opinion, using influencers this way suggests that parties are
    perhaps only scratching the surface of influencer engagement. In my day
    job I would advise clients to establish a conversational position
    within influencer networks and build trusted relationships.  This is
    key to developing successful long-term engagement programmes – arguably
    the only real way to change behaviour.
    • Parties do engage directly to a limited extent with individuals
      online, particularly at a local level. However, The Labour Party
      appears to be closest to participating in real-time within online
      networks by engaging non-political networks, e.g. marketing/PR and
      media networks to leverage news or content.


  • Interestingly Labour also use quantitative tracking to identify
    popular or trending issues and content on the Labour Party website and
    to identify ‘content gaps’ on the Labour website. This insight is used
    to create new content to meet demand.
  • The Liberal Democrats use qualitative monitoring in a different way
    altogether: as an internal communications or customer service tool. By
    reading and staying on top of what Lib Dem campaigners and activists
    are saying, thinking and doing, the party can help out or resolve any
    issues that are emerging at a grassroots level. Really interesting use
    of monitoring.

My presentation also tried to fit these findings into a critical framework based on the workManuel Castells has completed in mapping and analysing the Network Society.

I started from the position that political parties monitor online
networks to ensure they can engage effectively with the aim being to
exert influence influence in the network.

One of the most important measures of influence – or more accurately
– power in networks is defined by Castells as “networking-making power” – that is the ability to establish and control particular networks.

This ability is further categorised into two processes: programmers and switchers.

  1. Programmers have “the ability to constitute network(s), and to program/reprogram the network(s) in terms of goals assigned to the network”
  2. Switchers have “the ability to connect and ensure
    cooperation of different networks by sharing common goals and combining
    resources, while fending off competition from other networks by setting
    up strategic cooperation”

Based on my findings I hypothesise that the Tories are Programmers while Labour are Switchers:

    • Conservatives – early political online networks in
      the UK were (and still are to an extent) right-wing or anti-Government.
      This meant that the Conservatives were able to program the network and
      assign goals that were largely identical to its own. This would
      potentially explain why the Conservatives focus online engagement with
      influential nodes in the network rather and not primarily engaging in
      wider debate around issues.


  • Labour – Labour are Switchers as they are seeking
    to cooperate with strategic partner networks through shared goals. For
    example, identifying media networks interested in specific issues and
    leveraging them by combining resources.

Anyway. Those are my main findings. Feel free to challenge, share,
agree with, etc. As always, they open up more questions for further
examination than they answer. But that’s the beauty of research.

Cross-posted to We Are Social.

Tags: online monitoring, politics, Labour Party, Conservatives, Liberal Democrats, Network Society, Manuel Castells