Filtering Methods to Remove Inappropriate Reviews Effectively
Online user-generated reviews can influence many people when they decide what to do. Offensive or irrelevant reviews are often posted to review services, and they can ruin services' reputation. Review service providers employ many human workers to manually remove these inappropriate reviews, but such manual operations incur high costs. To reduce these costs, we are developing methods that can remove inappropriate reviews based on various expressions. Our methods can remove such reviews on Tabelog effectively, and we were selected to present at the highly regarded IEEE BigData 2018.