Two documents relating to the ongoing debate on Nemesysco’s technology and its validity:
The first is a contribution to the discussion of technical aspects behind the technology, “LVA-technology: A short analysis of a lie”. I discuss the shortcomings of the technology on which Nemesysco’s “emotion detection devices” (lie-detectors) are based. This is not a complete analysis but it exposes the essential problems. In a forthcoming development I will assess in more detail the impact of spurious acoustic background activity.
The second document is Nemesysco’s official standpoint regarding the critique that Anders Eriksson and I have directed to their systems. Anders Eriksson and I present the original document along with our comments on Nemesysco’s official response, displayed as sticky notes. (Additional layout of the same document with notes listed on separate pages).
Additional links to news on this issue
The Guardian, UK, 12 March 2009, on the evaluation of “Voice Risk Analysis” (English)http://www.guardian.co.uk/technology/blog/2009/mar/12/voice-risk-analysis-lie-detection-benefits-government-results?commentpage=1
The Guardian, UK, 12 March 2009 (English)
Sveriges Radio, P1, Sweden, 12 March 2009 (Swedish)
BBC, UK, 12 March 2009 (English)
Expresso, Portugal, 10 March 2009 (Portuguese)
Swedish Research Council, 21 February 2009 (Swedish)
Swedish Research Council, 23 February 2009 (English)
I’m one of the bloggers whom Nemesysco quoted in their recent press release. Although they quote me as saying that
“To be fair to Nemesysco, you can see why they took offence. The paper is unusually lively for an academic article. …In fact, in parts the thing reads more like a blog post or an op-ed than a scientific paper”
I’m actually very much in favor of your paper and I think it was brilliantly written. I wish more papers were written like blog posts! Anyway, I wrote a little bit about your paper <a href=”http://neuroskeptic.blogspot.com/2009/02/lies-libel-and-love-detection.html”>here</a>.
And if you don’t know, another blogger has written an awful lot about Nemesysco <a href=”http://www.ministryoftruth.me.uk/”>here is the blog</a>.
Keep up the good work,
It is necessary that somebody keeps an eye on these guys who claim to be able to evaluate whether somebody lies or not. They may hurt innocent people.
It should be easy to test, right? Invite 50 people, let them look at cards with numbers, colors, let them hear statements, whatever – and then see if the detectors can do better than expected from pure chance.
If anything unusual happens, reproduce the experiment.
It is called “science”.
Well, the fact is that this pseudo technology has been tested on a sample of 2785 individuals by the UK’s Department of Work and Pensions, using Nemesysco’s “certified” personal. The published statistical data is absolutely clear in showing that the number of hits and false alarms essentially go hand-in-hand, which is the expected outcome of an irrelevant method. The overall AUC of the ROC curve is a ridiculous 0.65, implying essentially just a few percent more of hits than false-alarms. And this may even be based on the “certified” personal’s “interpretations” of the program’s “complex” outputs and actually listening to the content of the recorded conversations… Someone is making a lot of money exploring some people’s willingness to believe in nice fairy tales associated with an appalling ignorance of statistical processes, speech acoustics and signal processing… Unfortunately, that is a sad and threatening reality.