h a l f b a k e r yTrying to contain nuts.
add, search, annotate, link, view, overview, recent, by name, best, random
news, help, about, links, report a problem
browse anonymously,
or get an account
and write.
register,
|
|
|
I'm facetious, I'll admit. Sometimes it is so obvious that everyone gets it. Sometimes it's not very obvious at all.
Altered tone, context and content are often the cues we use to identify whether someone is "winding us up", or not.
These things could all be analyzed by a module that fits snugly
into the ear. A very quiet alarm would alert the wearer that their interlocutors were likely being facetious.
There could be a sliding percentage probability scale, for this purpose: "There is an 52% chance that Bob was joking about doing your old lady while you're away on your monthly business trip." Might be best not to wear it if you are going through a relationship breakdown.
Possibly available as an upgrade module for babelfish units.
Affective Computing
http://affect.media.mit.edu/
In the oven! (Don't laugh; I used to work there.) [beland, Oct 04 2004, last modified Oct 05 2004]
Please log in.
If you're not logged in,
you can see what this page
looks like, but you will
not be able to add anything.
Annotation:
|
| |
Sounds like magic so far. How does it know? (I know, you're being facetious now. No excuse.) |
|
| |
Not being facetious. It analyzes input against prior experiences, and strives to give you a percentage probability of facetiousness. |
|
| |
Very similar to the equipment used to assess tapes purportedly by Bin Laden, only a lot smaller. No magic required, just programming. |
|
| |
I already have such a unit. I am training my pet monkey to wear the device and signal by ringing a bell every time I ... <ring!> |
|
| |
Changes in facial muscle configuration, voice timbre and pitch, cadence, skin coloration, infrared emissions, etc., might be useful to have a wearable device watch. (I used to wear one that measured my emotional responses, which included sensors for sweat, muscle tension, breathing, and skin coloration. But this would be a remote sensing problem.) |
|
| |
Much more difficult than acquiring the data would be detecting useful signals. Detecting semantic context linguistically is also an extremely difficult AI problem. |
|
| |
Of course, the typical human brain is already quite well suited for detecting these subtle affective clues. Such a device might be more useful to people with affective disorders, such as autism. |
|
| |
I was thinking that it would be useful for Asperger geeks. All the same I'd be concerned that people in posession of such a device would come to rely on it and become lazy at reading people the usual way. |
|
| |
It'd be a great excuse though... "I'm sorry, my facetiometer seems to be malfunctioning". |
|
| |
Have you noticed how it's always Bob that causes these problems? Something should be done about that guy. |
|
| |
It would need to know everything about you in order to tell if a new piece of "data" is facetious or not. That would mean it would already have to know what your "facetiousness" sounds like. That would mean you would have to get your friend to volunteer to say something facetious (and tell you for a fact that it is) so that you can calibrate the program. This is most impractical. |
|
| |
Me? I just assume they're facetious, until proven otherwise. |
|
| |