HIGHLIGHTS
SUMMARY
The main idea is to create a user relationship graph with users as nodes and determine the edge weights between nodes based on suspicious relationships between users. Currently, some studies have tried to extract collusive relationships between users from the metadata of user reviews, such as rating, review time, or product consistency. Among them, Wang et_al considered the user review time difference and rating difference when building the user relationship graph and, based on this, defined "co-review collusiveness," which is used to describe the degree of user collusion. To effectively utilize these identified . . .
If you want to have access to all the content you need to log in!
Thanks :)
If you don't have an account, you can create one here.