"The tool is based on two algorithms," says lead author Alvaro Ortigosa. "The first calculates the emotional load of each message and classifies it as positive, negative or neutral. The second deduces emotional state by comparing it with the emotional load of recent messages."
Ortigosa says the algorithms have been trained to mimic human judgment, for they can recognise words carrying emotional load and classify them using an automatic, machine-learning technique.
Ortigosa and his team intend for the app to be used by online educators to provide them a sense of feedback that is normally only accessible to classroom educators who can see their students' faces.
While online students may live on separate continents, a common negativity among the students could alert the professor to difficulties and frustrations that need to be addressed, says Ortigosa who adds that students would have to consent to the app's use.
Other ideas for the app include the remote monitoring of individuals with illness to measure their satisfaction with treatment.
The study was published in the journal Computers in Human Behavior. — Reuters
Did you find this article insightful?