Google News Recommendations and the Google Knowledge Base

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”

New Visual Search Photo Features from Google

Google outlining

These details come from an anonymous source who also gave us a bit more details on the project. The report states there will be a new feature integrated, allowing users to outline specific areas of the image in order to directly target their searches.

In Google Goggles, one can only search the whole image, which has proven to bring plenty of discrepancies. Images often display plenty of distractions, background items and other objects that may throw off a search result. According to the sketch provided, the system will also be able to recommend retailers for purchasing products, as well as other details.

Furthermore, it is said this technology has also been tested in “wearable computing devices”. This could suggest this technology may come to products like Google Glass and possibly even VR (or AR) headsets.

Continue reading “New Visual Search Photo Features from Google”

Image Search and Trends in Google Search Using FreeBase Entity Numbers

Google is organizing more and more things in its index based upon entity numbers. I have a couple of examples for you that show how they are being used.

It’s possible that you may have missed a reference to Freebase Entities in a Google Research Blog post from 2013. I missed it myself. The post is
Improving Photo Search: A Step Across the Semantic Gap.

In the post, the author (Chuck Rosenberg) tells us how they improve image searching at Google by labeling images with entities, rather than text strings. The entities they used are entities that you would find at a source such as Freebase. He tells us that they use Freebase Machine ID numbers for those labels:

As in ImageNet, the classes were not text strings, but are entities, in our case we use Freebase entities which form the basis of the Knowledge Graph used in Google search. An entity is a way to uniquely identify something in a language-independent way. In English when we encounter the word “jaguar”, it is hard to determine if it represents the animal or the car manufacturer. Entities assign a unique ID to each, removing that ambiguity, in this case “/m/0449p” for the former and “/m/012×34” for the latter.

Continue reading “Image Search and Trends in Google Search Using FreeBase Entity Numbers”

Google Watch Times Algorithm For Rankings?

Google was granted a patent this week about how Google may rank some search results, by looking at watch times.

The patent appears to be aimed at video content, but it tells us that it might be applied to how long someone might watch a page after they’ve been delivered to the page, even if that page doesn’t contain video. The page may contain images or audio, and watch times for that content might be tracked as well.

watch-time-google

Regarding videos, the patent tells us that a score might be adjusted for resources like videos based on how long people tend to watch that video content. That score might be boosted if people tend to watch the video for longer periods of time, and might be reduced if people historically tend to watch that video for shorter periods of time. This watch times score could be used to boost or demote a video in search rankings for a query.

Continue reading “Google Watch Times Algorithm For Rankings?”

Google Media Consumption History Patent Filed

Google published a foreign patent at WIPO today that has an interesting perspective to it. When someone performs a search that involves a specific entity, their search may be influenced by the search engine’s knowledge of their past interactions with content involving that entity.

For example, someone searches for “Justin Timberlake” and the search system may have collected information about the searcher’s past consumption of content related to that entity, like having attended a concert featuring him, or a movie that he was in:

In some applications, the server-based system additionally receives and stores information describing the user’s consumption of the content. For example, the system can determine that the user viewed the movie “The Social Network” featuring “Justin Timberlake” on a particular date and at a particular location. The system can store the information at the media consumption history that identifies the particular date and the particular location where the user viewed the movie “The Social Network,” and can subsequently receive a request that identifies the user and “Justin Timberlake.” The system can provide a response to the request that includes information about “Justin Timberlake” and can also indicate that the user viewed the movie “The Social Network” that features “Justin Timberlake” on the particular date and at the particular location.

The patent application is:

Continue reading “Google Media Consumption History Patent Filed”

Google on Creating a Relevant Second Screen for TV

Google was granted a patent last week that looks like it might have been among one of the earliest patents filed by the company. It involves showing television programs (News Programs to be more exact), and showing web pages that might be relevant to the transcripts of the shows being presented to viewers.

Transcripts of TV queried to find relevant web pages

The details of this recently granted version of the patent filed are:

Finding web pages relevant to multimedia streams
Invented by Monika H. Henzinger, Bay-Wei Chang, and Sergey Brin
Assigned to Google Inc.
The Board of Trustees of the Leland Stanford Junior University
United States Patent 8,868,543
Granted October 21, 2014
Filed: April 8, 2003

Continue reading “Google on Creating a Relevant Second Screen for TV”