Featured Snippets and Sentence Compression
A couple of Augusts ago, I went to a Semantic Business and Technology conference where the head of Yahoo’s Knowledge Graph, Nicolas Torzec, discussed how updates took place to the knowledge graph when some earth-shaking event took place. He told us that they were manually editing information in that knowledge graph. Upon hearing that, I thought it seemed like an area that could have used a machine learning element to it, to automate it to keep it up to date.
Another place that would benefit from machine learning would be generating featured snippets that answer questions people might ask at Google, and it appears that they thought it might be useful there, too. A Wired Magazine article from Monday describes how the sentence compression algorithms behind these featured snippets might be used:
Google’s Hand-Fed AI Now Gives Answers, Not Just Search Results
Continue reading “Answering Featured Snippets Timely, Using Sentence Compression on News”
Ranking Events without Links
This summer, Google was granted a patent that describes how the search engine might rank events based upon data that might indicate the popularity of those events, without relying on things such as the number of links pointed to pages about those events. The patent involves ranking events that occur in physical locations.
Examples of the kinds of events talked about in this patent include such things as music concerts, art exhibits, and athletic contests, all happening for specified periods of times at specified physical locations, such as concert halls, galleries, stadiums, or museums.
Since many events in a geographic region can happen at the same time or at overlapping times, interested individuals may at times find it difficult to determine which events to attend. For example, individuals may be unaware that events of interest are scheduled to occur or may have difficulty identifying the most interesting events when multiple events are occurring.
This ranking events patent lays out a general process flow to describe how the method in the patent works. It starts with receiving data about a physical location, and events taking place there during a certain time period and computing signal scores for those events based upon things such as a mention of the event and a popularity score for the event based upon those signal scores.
Continue reading “Ranking Events in Google Search Results”
Google News Recommendations
I’ve seen posts from SEO by the Sea show up in search results with an “In the News” heading above them, even though my site hasn’t officially been accepted in Google News. Some blog posts that have been given that “In the News” treatment have been criticized lately. See: Google does a better job with fake news than Facebook, but there’s a big loophole it hasn’t fixed. It seems that this criticism is going to have an impact, with the “In the News” label taken away from Google Search Results:
Google is removing its ‘In the news’ label due to the fake news nightmare
Are there any other solutions? I do like when something I write is treated as newsworthy and is presented to a larger audience in a way that helps those posts stand out, but sometimes satire blog posts end up being treated that way as well. This article points out some other possible solutions:
Continue reading “Google News Recommendations and the Google Knowledge Base”
I noticed a blog post published yesterday, November 2, 2016, and it looked helpful: Use JSON-LD to add Schema.org to your Website. Schema and structured data seem to be growing in importance on the Web, as we see more knowledge panels and rich snippets and product search results. I’ve been working Knowledge Panel into Site Audits. JSON-LD seems to be favored by Google in adding structured data on your web pages. See: What is JSON-LD? A Talk with Gregg Kellogg.
If you do SEO and aren’t familiar with GS1, you probably should be. They invented the use of bar codes in shopping. They also came up with GTINS (Global Trade Item Numbers) which are used online at places such as eBay and Amazon, and Google Product Search. A recent blog post by GS1 Vice President Rich Richardson is also worth reading: Why bar code numbers matter.
In February, GS1 published an extension to Schema for products. Extensions like this are how Search and SEO are growing. The Schema blog told us about it in:
Continue reading “GS1 Web Vocabulary Schema Workshops in California”
Exploring The Google Knowledge Graph Search API
The Google Knowledge Graph Search API on a query for Google shows the following Entities and results scores for them. I thought they were diverse enough to be interesting and worth sharing. A couple of the ones listed seem odd, such as the Indian Action movie. “Thuppakki” and the Town in Kansas,”Topeka.” (It seems like there is a song titled, “Google Google” in the film Thuppakki, and in 2010 Topeka renamed itself “Google” to try to attract Google Fiber to the area.) We are told by Google that “Results with higher result scores are considered better matches.”
These are the Google Knowledge Graph Search API results on a search for Google:
Google “resultScore”: 292.863342
Google Chrome “resultScore”: 51.392109
X “resultScore”: 51.392109
Googleplex “resultScore”: 44.052853
Google China “resultScore”: 30.75222
Google Lively “resultScore”: 30.75222
DoubleClick “resultScore”: 29.141159
GV “resultScore”: 28.957876
Thuppakki “resultScore”: 28.693569
Google Store “resultScore”: 26.077885
“Google Japan” “resultScore”: 24.272602
DeepMind Technologies “resultScore”: 24.115602
Topeka “resultScore”: 23.718664
Rich Miner “resultScore”: 21.961121
Google Capital “resultScore”: 21.048887
Google Hacks “resultScore”: 21.003328
“Google Korea” “resultScore”: 20.818398
Barney Google and Snuffy Smith “resultScore”: 20.384176
Verily Life Sciences “resultScore”: 19.65727
Patrick Pichette “resultScore”: 19.614473
Continue reading “Entities in the Google Knowledge Graph Search API for Google”