Boffins come up with rumour filter

A group of Korean researchers has developed technology to filter rumours from postings on social notworking sites.

The researchers, who work at the Graduate School of Culture Technology at the Korea Advanced Institute of Science and Technology (KAIST) – sheesh! –  looked at 100 cases of rumours and true stories spread on Twitter in the US between 2006 and 2009.

By looking at the numbers and using sociology and psychology theories, the scientists worked out what a rumour looked like.

Cha Mee-young, an assistant professor at KAIST who led the team, said it was difficult to classify rumours at the very early stage of their dissemination. After some time has passed what is a rumour and what is truth becomes clearer.

Apparently, you have to look at the characteristics of rumours ― how long they spread for, who disseminates them and which words are frequently used. After a while, the team could correctly identify 90 percent of unfounded claims as rumours.

One of the big ones that kept appearing as a rumour were allegations that US President Barack Obama was a Muslim, the “antichrist” and illegally obtained his American citizenship.

Rumours spread over a long period while truth can be widely spread in a short time, and is rarely mentioned again. Rumours are also circulated randomly by people who do not know each other while the spread of ordinary information can be tracked along the networks of online acquaintances.

Words associated with assumption and doubt are frequently seen in rumours. They include, “not sure,” “no idea if it works,” and “heard”,

The research was jointly conducted by Jung Kyo-min, a professor at Seoul National University, and Microsoft Research Asia in China.