Patent: On Information Gain Scores and How It May Influence Google Ranking

Bill Slawski breaks down a newly granted Google patent Contextual Estimation of Link Information Gain that sheds some light on how Google may use Information gain scores in ranking.

Information gain scores indicate how much more information one source may bring to a person who has seen other sources on the same topic. Pages with higher information gain scores may be ranked higher than pages with lower information gain scores.

An information gain score for a given document indicates “additional information included by a page beyond the information contained in other pages already presented to the user.”

How Does this Information Gain Score Process Work?

1. The first set of pages displayed to the searcher is identified.
2. The pages of the first set share a common topic and can be identified based on being previously provided to the user
3. The searcher may look for a topic and one or more pages that are responsive to that query may be returned
4. For each new page in the second set of pages, an information gain score is determined indicating whether that page includes information not contained in the pages of the first set of documents
5. Based on the information gain scores, one or more of the new documents may be selected to provide to the user, and/or the new documents may be ranked based on their respective information scores
6. The new pages can be ranked and as the searcher views more pages, the second set of pages may be re-ranked based on new information gain scores
7. While the entire Content of Those pages may be viewed by a machine learning approach, an alternative representation of the document, such as a semantic feature vector or embedding, a “bag-of-words” representation, etc., may be generated from each of the documents and applied as an input across the machine learning model

The patent clearly states that “these search results may be ranked at least in part based on their respective information gain scores.”

This may mean that some pages may be boosted in rankings based upon how much information they would add to a searcher, and maybe demoted if they don’t add much information to a searcher.

Head over to Bill’s break down for more info including things like How are Information Gain Scores Calculated?