Google Used Machine Learning to Remove Millions of Fake Reviews and Ratings from Play Store

BY

Published 18 Dec 2018

NSFW AI Why trust Greenbot

We maintain a strict editorial policy dedicated to factual accuracy, relevance, and impartiality. Our content is written and edited by top industry professionals with first-hand experience. The content undergoes thorough review by experienced editors to guarantee and adherence to the highest standards of reporting and publishing.

Disclosure

Google Play reviews

Using human intelligence and machine learning, Google was able to heavily combat spam content and fake reviews on Google Play this year. The company says the effort led to removing millions of reviews and ratings being removed from the Play Store and thousands of malicious apps identified for suspicious reviews in just a week.

Fake ratings and reviews help a poorly made or malicious app in ranking higher in Play Store lists and thereby reach a wider audience. This is obviously harmful to the entire ecosystem and also ends up negatively affecting genuine developers who put in a considerable amount of work in their apps.

To improve its machine learning algorithm, a team of engineers at Google and analysts monitored and studied fake comments and suspicious activity on the Play Store. This was then followed by skilled reviewers checking the decisions made by the algorithm to ensure it was not weeding our genuine reviews and ratings.

The move is obviously a positive one from Google as this will ensure fake reviews and ratings don’t help a malicious or poorly made app from ranking high in the Play Store list and reaching a wide set of audience. It will also actively encourage developers to create better apps and pay more attention to the reviews they receive since they know it is coming from a genuine user.

[Via Android Developers]