Computer scans language warning signs
Programme can predict when online conversations turn sour
New York, July 25: Scientists have developed a computer model that can predict when civil conversations on the internet might take a turn and degenerate into personal attacks.
The researchers from Cornell University in the US hope this model can be used to rescue at- risk conversations and improve online dialogue, rather than for banning specific users or censoring certain topics.
After analysing hundreds of exchanges between Wikipedia editors, they developed the computer programme that scans for warning signs in the language used by participants at the start of a conversation.
The programme looks for signs such as repeated, direct questioning or use of the word ‘ you’ to predict which initially civil conversations would go awry.
Early exchanges that included greetings, expressions of gratitude, hedges such as "it seems," and the words ‘ I’ and ‘ we’ were more likely to remain civil, the study found.
“There are millions of such discussions taking place every day, and you can't possibly monitor all of them live. A system based on this finding might help human moderators better direct their attention,” said Cristian Danescu- Niculescu- Mizil, an assistant professor at Cornell University.
“We, as humans, have an intuition of whether a conversation is about to go awry, but it's often just a suspicion. We can't do it 100 per cent of the time. We wonder if we can build systems to replicate or go beyond this intuition,” Danescu- Niculescu- Mizil said.