Scientists Race to Develop Political Bullshit Detector, All Dials Pegged at 11New Scientist today is summarzing the world of political spin detection software-behavioral scientist Paul Ekman claims he can analyze a speech's text for words that indicate untruths and deception. Others look to analyze the tenor of the voice, and facial recognition to spot lies is becoming more of a reality. But unfortunately, much of the bullshit detector tech here seems like it may be drowning a bit in the selfsame goo. I'm tempted, nay, inclined here to call shennanigans on the simplicity with which the speech-processing algorithm analyzes actual speech:
The algorithm counts usage of first person nouns - "I" tends to indicate less spin than "we", for example. It also searches out phrases that offer qualifications or clarifications of more general statements, since speeches that contain few such amendments tend to be high on spin. Finally, increased rates of action verbs such as "go" and "going", and negatively charged words, such as "hate" and "enemy", also indicate greater levels of spin.
I'm more inclined to subscribe to the newsletter of voice analyst Branka Zei Pollermann of the Vox Institute in Geneva (ah, neutrality). "The voice analysis profile for McCain looks very much like someone who is clinically depressed," says Branka, after running Senator McCain's voice through her software that analyzes "pitch, modulation, volume, and fluency" to generate a unique profile. Obama's varying pitch and tone are on the opposite spectrum, but his furrowed brow tends to project an overly concerned stance. Check out the research summarized and decide for yourself, but don't miss this gem:
Additionally, McCain's voice and facial movements often do not match up, says Pollermann, and he often smiles in a manner that commonly conveys sarcasm when addressing controversial statements. "That might lead to what I would call a lack of credibility."
[New Scientist via /.]