Edith Cowan University is using an IBM-developed predictive model to identify students at risk of leaving a course before they complete it, says National ICT Australia (NICTA) researcher Lawrence Cavedon.
"We at NICTA are investigating similar things in health--can we predict the likely risk of contracting a disease, the likely length of stay, or likely future hospital admissions, from patient information?" he notes.
Cavedon says that one of the particular challenges of using information from social media is that the information is in text format rather than structured databases. "At NICTA, we are investigating how to perform text analytics [rather than data analytics] across different types of text documents, from tweets to research papers," he says.
Meanwhile, futurist Ross Dawson speculates that Apple's Siri speech recognition application could be upgraded to perform tasks based on vocal command. "We're on the verge of a significant transition to better human-machine interaction so [machines] understand what we mean," he says. "And voice is a big part of that."
From Sydney Morning Herald (Australia)
View Full Article
Abstracts Copyright © 2011 Information Inc. , Bethesda, Maryland, USA
No entries found