Speaking of cybersex...

As I rehearse and refine my presentation for Thursday, I'm extra-attuned to any new information that pertains to adult community and sexuality in virtual spaces.

A USC study of chat rooms as repositories of knowledge looks like it could have interesting results if applied to adult community.

A USC Information Sciences Institute system pulls answers from online conversations by identifying the alpha chatterers.

The system, to be presented at a conference on human language technology on June 6, was developed to analyze technical conversations in which an objectively correct answer exists. But the method for statistically characterizing response by the group to individuals is generalizable.

Online communities are now firmly established in domains ranging from high school gossip to professional open-source software design discussions, generating huge repositories of records of human knowledge processing, pre-converted to digital form.

"For study of online natural language interaction, it's the mother lode," says Eduard Hovy of the University of Southern California Information Sciences Institute.

Sex chat doesn't necessarily have objectively correct answers. But it does have "an inherent structure, including temporal ordering, references to previous statements, labeled sourcing and other clues" like any other human conversation. This, according to researchers, "opens the door to much deeper machine-generated understanding."

I'm also interested in how the researchers categorize different types of chat contributions. These obviously do not belong solely to the realm of technical conversation.

inform – corrections, descriptions, elaborations, suggestions, and answers to questions, both simple and complex
requests – requests for information or for action (e.g., commands)

social – acknowledgements, thanks, compliments, criticisms, objections, and supportive statements

Interesting implications ... thinking of how this might come in handy for online sex ed.

Press release is here, and the paper will be presented today at the Human Language Technology Conference at NYU in New York.