TOTAL: {[ getCartTotalCost() | currencyFilter ]} Update cart for total shopping_basket Checkout

Daily Dashboard | Will Systems Predict Which Users Will Become Online Trolls? Related reading: A view from Brussels: EDPS sends signal on data transfers 

rss_feed

""

""

Embedded in virtually every online forum and comment section lurk trolls: online users, often behind a veil of anonymity, who pollute conversations with uncivil discourse and petty bigotry. To limit such users, online platforms often resort to hiring individuals to sort out and filter trolls, but things could change. The Washington Post reports that researchers are working on a system to predict who will become a troll. Justin Cheng, Cristian Danescu-Niculescu-Mizil and Jure Leskovec trudged through 18 months of user activity from specific, major online sites to identify “future banned users.” They found a number of trends that lead up to online trolling and have since designed a program to predict who those users will be—doing so with relatively little information. The program, by using just five to 10 user posts, successfully predicted a “future banned user” 80 percent of the time.
Full Story

Comments

If you want to comment on this post, you need to login.