Mapping Online Publics

Continuing my series of posts on methods for doing quantitative research using Twitter data, this will be a fairly tentative post. I’m currently looking into ways to examine the terms and concepts used by tweeters as they discuss specific issues; we’ve done similar work looking at the content of blog-based debates in the past, using the (commercial) concept mapping software Leximancer, but I’ve never been fully satisfied with the information generated by Leximancer, and especially with its data visualisation functionality, so it’s time to look at the alternatives.

Ideally, I’d like to leave the visualisation aspects to the open source software Gephi, which I’ve already used for some useful network visualisations (more on that in another post), so what I’m really after is a software that produces word and concept co-occurrence data for my source texts (in this case, a database of tweets on a specific subject), and pushes this out in a format that Gephi can understand (e.g. UCINet or Pajek, or even Gephi’s own network data format). At the ICA conference in Singapore last month, I came across a (commercial, sadly) quantitative text analysis software called WordStat – part of a larger software package available from Provalis Research that includes various other statistical tools which are less relevant for me here –, so that’s where I’ll start.

Read the rest of this entry →

Following on from our look at Twitter activity during the Australian leaders’ debate and Masterchef broadcasts, here’s an overview of the patterns we can see in the content of the tweets themselves. For this, I’ve grabbed all tweets containing the ‘#debate’ hashtag during 5 p.m. and midnight on Sunday (during which time, as we have seen, ‘#debate’ as more active than the general ‘#ausvotes’ tag for the election’).

In the first place, I’ve now selected all 2553 tweets containing either ‘Julia’ or ‘Gillard’, and created a simple word cloud using Wordle – manually removing ‘Julia’ and ‘Gillard’ (and variations thereof) as terms, as well as ‘debate’, ‘ausvotes’, and ‘RT’. Here’s the result:

Read the rest of this entry →

Sunday night’s leaders’ debate is unlikely to be remembered for the policy positions it revealed – indeed, perhaps the most memorable aspect of the night was how federal politics was nearly upstaged by the finale of Masterchef (some kind of cooking show, I believe .

So, how did the night unfold? Following the methodology I’ve outlined in my previous post on using Twapperkeeper archives to track tweeting patterns, we’ve had a look at Twitter activity across the three key hashtags ‘#ausvotes’, ‘#debate’, and ‘#masterchef’.

Read the rest of this entry →