Language Log

« previous post | next post »

This period of prudent isolation is a good time to remember that linguistic analysis applies not only to sound, structure, and sense, but also to social interaction. As the first in a series of posts on this topic, we feature Eve Armstrong's brilliant application of simulated annealing to a problem currently on hold, but sure to re-emerge in full force when our lives de-virtualize: "An Artificially-intelligent Means to Escape Discreetly from the Departmental Holiday Party; guide for the socially awkward" (4/1/2020)G:

We shall employ simulated annealing to identify the global solution of a dynamical model, to make a favorable impression upon colleagues at the departmental holiday party and then exit undetected as soon as possible. The procedure, “Gradual Freeze-out of an Optimal Estimation via Optimization of Parameter Quantification” – GFOOEOPQ, is designed for the socially awkward. The socially awkward among us possess little instinct for pulling off such a maneuver, and may benefit from a machine that can learn to do it for us.

Eve offers the string [g∧fui: c:p∧kw] as a representation for the acronym's pronunciation — translated into the IPA characters thus approximated, I think this means [gʌˌfui ˈɔːpʌk^w] or maybe [gʌˌfui ɔːˈpʌk^w].

No doubt someone will soon apply similar methods to help with navigating the etiquette of on-line gatherings via Zoom or Bluejeans or Houseparty or whatever. And perhaps we can also look forward to development of similar ideas into a convenient smartphone app, with discreet suggestions dynamically updated as the system's evaluation of the ambient situation evolves — a sort of autonomous vehicle guidance algorithm for those whose vehicle is their own feet.

In a final note, Eve warns that

GFOOEOPQ is generalizable to industry and corporate events, graduations, baby’s-first-birthdays, bridal showers, and wedding receptions. I ask that GFOOEOPQ not be used at funerals, religious ceremonies, or any event catered by Zabar’s [33]. In such cases, please respectfully muster sincerity.

Although she is a physicist, Eve has authored several earlier algorithmic explorations of social interaction, notably "A Neural Networks Approach to Predicting How Things Might Have Turned Out Had I Mustered the Nerve to Ask Barry Cottonfield to the Junior Prom Back in 1997", 3/30/2017.

April 1, 2020 @ 8:06 am · Filed by Mark Liberman under Artificial intelligence, Communication

Permalink