Predicting site quality
Topics: Document Classification, E-E-A-T, Navneet Panda, Phrase based Indexing, Probably in use, Ranking
The patent describes methods for predicting site quality scores for new websites using phrase models. It involves generating a phrase model from previously scored sites, where the model maps phrase frequency measures to average site quality scores.
For new sites, relative frequencies of phrases are determined and used with the model to calculate an aggregate site quality score. This predicted score can then be used by search engines to help rank resources from that site in search results.