Computer scientists from the University of Edinburgh, in collaboration with Lancaster University, Queen Mary University of London and Kings College London, have developed a new software tool capable of fishing out the so-called catfishes, or social media users posting falsified information about themselves.

The new tool, to be presented at the International Conference on Advances in Social Networks Analysis and Mining in Australia, was designed to detect fake profiles in an adult content website. Interestingly, the computer model was able to identify users who faked their age and gender.

"Adult websites are populated by users who claim to be other than who they are, so these are a perfect testing ground for techniques that identify catfishes," said Dr Walid Magdy, of the University of Edinburgh's School of Informatics, in a press release. "We hope that our development will lead to useful tools to flag dishonest users and keep social networks of all kinds safe."

To build the new software tool, the researchers collected information from about 5,000 verified public profiles of an adult content website. The researchers chose adult content website because they believe that this kind of sites is heavily targeted by catfishes that befriend other users and garner more profile views.

By using these profiles, the new tool was trained to identify the gender and estimate the age of a user based on their style of writing in the comments and network activity. The trained model was able to estimate the age and gender of unverified users with high accuracy. Additionally, the software tool also spotted misinformation provided by some users.

Among the users of the adult content website, 40 percent lie about their age and 25 percent hide their real gender. Surprisingly, the researchers observed that women were more likely to provide falsified information than men.

With the positive results of the study, the researchers are confident that their new software tool could be utilized to fish out catfishes and ensure the safety of social media networks.