Catfishes Beware!
Marie Donlon | June 08, 2017Image credit: Don Hankins / CC BY 2.0Computer scientists from the University of Edinburgh have created a tool that could make fake online profiles easier to spot.
Dubbed catfishes, these fake online profiles typically provide dishonest information concerning a user’s age and/or gender.
Designed to reveal profiles with misinformation about gender and age specifically, computer scientists taught the computer models to identify fake profiles using an adult content website—an environment teaming with catfishes.
Using the information gathered from roughly 5,000 public profiles on the adult site, researchers were able to use this data to train the computer model to accurately predict the gender and age of a user based on the user’s network activity and writing style in comments.
Researchers found that nearly 40 percent of the adult site users lied about age and one quarter of users lied about gender.
The study will be presented at the International Conference on Advances in Social Networks Analysis and Mining in Australia and was carried out in collaboration with Lancaster University, Queen Mary University of London and King's College London.
Dr. Walid Magdy, of the University of Edinburgh's School of Informatics, said: "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. We hope that our development will lead to useful tools to flag dishonest users and keep social networks of all kinds safe."