Google Fact Rank: Google Ranking Web Pages On Facts, Not Links

Mar 4, 2015 • 7:40 am | comments (60) by twitter Google+ | Filed Under Google Search Engine Optimization
 

factThe SEO community is buzzing heavily around a paper (PDF) published by Google named Knowledge-Based Trust: Estimating the Trustworthiness of Web Sources.

The paper describes how Google can rank the most factually accurate web pages higher in the search results. Here is the abstract:

The quality of web sources has been traditionally evaluated using exogenous signals such as the hyperlink structure of the graph. We propose a new approach that relies on endogenous signals, namely, the correctness of factual information provided by the source. A source that has few false facts is considered to be trustworthy. The facts are automatically extracted from each source by information extraction methods commonly used to construct knowledge bases. We propose a way to distinguish errors made in the extraction process from factual errors in the web source per se, by using joint inference in a novel multi-layer probabilistic model. We call the trustworthiness score we computed Knowledge-Based Trust (KBT). On synthetic data, we show that our method can reliably compute the true trustworthiness levels of the sources. We then apply it to a database of 2.8B facts extracted from the web, and thereby estimate the trustworthiness of 119M webpages. Manual evaluation of a subset of the results confirms the effectiveness of the method.

So instead of using links to determine the best possible web page to rank for a query, Google may want to rank the page with the fewest false facts the highest. Google calls this Knowledge-Based Trust (KBT).

Of course, no one would currently say that this is how Google's algorithm works. Google's Matt Cutts said in the past, just because Google has a patent, it doesn't mean the algorithm works that way.

But with links getting sucked dry and with Google's emphasis on the knowledge graph and knowledge vault, I wouldn't be surprised if we see Google lean more to factual information.

Which makes me wonder, who determines what the facts are around SEO and what content should rank highest there. :)

EGOL in Cre8asite forums said:

They are assuming that their Knowledge Graph is correct. I don't like that because it is exactly how misconceptions are perpetuated. New discoveries and improvements will have a difficult time entering the knowledge base.

rish3 echoed it in WebmasterWorld:

If Google can't reliably identify trustworthy links, why would we think they can reliably identify trustworthy content in some other way?

Then what if SEOs come up with a way to make up facts and spam Google's fact knowledge engine to trick them into facts that are actually false?

Good times we live in.

Forum discussion at WebmasterWorld & Cre8asite.

Previous story: Daily Search Forum Recap: March 3, 2015
 
blog comments powered by Disqus