Skip to main content

Twitterbots - Tony Veale and Mike Cook ***

This is an odd one. It's an in-depth look at Twitterbots - applications designed to post on Twitter making human-like pronouncements. We start with a really interesting, if highly verbose introductory section about these programs, introducing me to lots of examples I hadn't come across. I particularly liked the historical examples of condensing a message with humour (and a bit of intellectual oddity) in the Latin punning telegraph messages that seem to have been briefly popular amongst the British establishment in the mid-nineteenth century. For example, in 1856, when the British annexed the Indian province of Oudh (rhymes with loud), the governor-general sent the message 'Vovi.' This means 'I have vowed'... which sounds distinctly like 'I have Oudh.'

Then we plunge into the mechanics of Twitterbot construction. Tony Veale and Mike Cook, two British/Irish academics writing with a distinctly transatlantic style, give us detailed guidance on simplistic bot production using simple templates and collections of words or phrases, and also explore some more sophisticated methods using Java.

The book then turns into an exploration of the way that a program can build language structures - the kind of categorisation needed to provide a tweet builder with a 'Lego set' of appropriate words and phrases and the way it's possible to use some of the classic (if slightly hackneyed) academic breakdowns of stories, plots and characters to generate a pseudo-story format out of components (if you've read one of those 'how to write a novel' books that breaks down a hero's journey or whatever, into standard stages, you'll know the kind of thing).

What we end up with is a mix of an investigation of the world of Twitterbots, a how-to manual to get started writing your own code for them, and an analysis of just how much story can be broken down and built up in this component fashion. I found the presentation over-wordy and rather too academic in approach - but nonetheless interesting.

What the authors don't do - perhaps because they themselves are part of this scene - is some kind of psychological analysis of the nature of adults spending a lot of time on what is, in the end, the generation of rather weak snippets of writing that are only occasionally mildly amusing. The only reason the resultant tweets are of interest is because they're machine produced. It's rather like Samuel Johnson's dog walking on its hind legs: it's not done well, but you are surprised to find it done at all.


Using these links earns us commission at no cost to you

Review by Brian Clegg


Popular posts from this blog

Models of the Mind - Grace Lindsay *****

This is a remarkable book. When Ernest Rutherford made his infamous remark about science being either physics or stamp collecting, it was, of course, an exaggeration. Yet it was based on a point - biology in particular was primarily about collecting information on what happened rather than explaining at a fundamental level why it happened. This book shows how biologists, in collaboration with physicists, mathematicians and computer scientists, have moved on the science of the brain to model some of its underlying mechanisms. Grace Lindsay is careful to emphasise the very real difference between physical and biological problems. Most systems studied by physics are a lot simpler than biological systems, making it easier to make effective mathematical and computational models. But despite this, huge progress has been made drawing on tools and techniques developed for physics and computing to get a better picture of the mechanisms of the brain. In the book we see this from two directions

The Ten Equations that Rule the World - David Sumpter ****

David Sumpter makes it clear in this book that a couple of handfuls of equations have a huge influence on our everyday lives. I needed an equation too to give this book a star rating - I’ve never had one where there was such a divergence of feeling about it. I wanted to give it five stars for the exposition of the power and importance of these equations and just two stars for an aspect of the way that Sumpter did it. The fact that the outcome of applying my star balancing equation was four stars emphasises how good the content is. What we have here is ten key equations from applied mathematics. (Strictly, nine, as the tenth isn’t really an equation, it’s the programmer’s favourite ‘If… then…’ - though as a programmer I was always more an ‘If… then… else…’ fan.) Those equations range from the magnificent one behind Bayesian statistics and the predictive power of logistic regression to the method of determining confidence intervals and the kind of influencer matrix so beloved of social m

How to Read Numbers - Tom Chivers and David Chivers *****

This is one of my favourite kinds of book - it takes on the way statistics are presented to us, points out flaws and pitfalls, and gives clear guidance on how to do it better. The Chivers brothers' book isn't particularly new in doing this - for example, Michael Blastland and Andrew Dilnot did something similar in the excellent 2007 title The Tiger that Isn't - but it's good to have an up-to-date take on the subject, and How to Read Numbers gives us both some excellent new examples and highlights errors that are more common now. The relatively slim title (and that's a good thing) takes the reader through a whole host of things that can go wrong. So, for example, they explore the dangers of anecdotal evidence, tell of study samples that are too small or badly selected, explore the easily misunderstood meaning of 'statistical significance', consider confounders, effect size, absolute versus relative risk, rankings, cherry picking and more. This is all done i