New software being developed to filter fake reviews
A new software system is being developed to limit the amount of fake reviews posted on user-generated review websites in an effort to help consumers
According to a team of researchers at Cornell University, fake reviews are a growing problem affecting user generated review sites and this particular team are working to stop it with a new program which has been tested on reviews of Chicago hotels. The software uses keyword analysis and word combination patterns detect fake reviews. For example, fake reviews use more verbs than their more truthful counterparts. The currently unnamed program also has the ability to post deceptive opinions with 90 percent accuracy, but is currently only trained on hospitality in Chicago. Ultimately, the group sees the software as a filter for sites like Amazon but it seems far from finished, so until then we just have to carry on using our intuition to do the hard work for us.