1

ABSTRACT

Google is a search engine and people search several things in Google to get accurate information.

As per the huge database maintained by Google the search results crop up. Google uses a very

realistic approach to this searching method and in the process they have developed an algorithm.

This algorithm is known as hummingbird algorithm. It was made to make the search in Google

more logical. In the world of Search-engine-optimization this new algorithm of Google will affect

vastly. Previously SEO was mostly depended on the most searched keywords and their frequencies.

The new hummingbird algorithm will change the SEO concept. More stress has been put on

conversational keywords. This concept will help provide more direct and realistic search results to

the users. Google is trying to put a more rational approach that will be able to process real time

speech patterns of human. Through Hummingbird algorithm Google is trying to understand the

possible intents of every user. The long process of Google to read the mind of people looks more

possible after implementation of the new hummingbird algorithm. This algorithm will give more

importance to keywords that will be a part of conversation and more elaborative in nature.

2

1. INTRODUCTION

Google started using Hummingbird about 30 August 2013, and announced the change on September

26 on the eve of the company's 15th anniversary. The Hummingbird update was the first major

update to Google's search algorithm since the 2010 “Caffeine Update”, but even that was limited

primarily to improving the indexing of information rather than the sorting of information. Google

search chief Amit Singhal stated that Hummingbird is the first major update of its type since 2001.

Conversational search leverages natural language, semantic search, and more to improve the way

search queries are parsed. Unlike previous search algorithms which would focus on each individual

word in the search query, Hummingbird considers each word but also how each word makes up the

entirety of the query the whole sentence or conversation or meaning is taken into account, rather

than particular words. The goal is that pages matching the meaning do better, rather than pages

matching just a few words.

Expanded Knowledge Graph features focused on making it more usable. Hummingbird places

greater emphasis on page content making search results more relevant and pertinent and ensuring

that Google delivers users to the most appropriate page of a website, rather than to a home page or

top level page.

1.1 WHAT IS HUMMINGBIRD?

The Hummingbird is an entirely new algorithm. It approaches search engine queries in a brand new

and intelligent way utilizing new technology combined with older features of the existing

algorithms. It is named for the speed and accuracy of the tiny bird.

1.2 THE RESURGENCE OF LONG TAILED KEYWORDS

The Hummingbird is what Google is calling the latest (greatest?) algorithm that they slipped in

under our radar in August. Hummingbird will take a search engine query using long-tailed

keywords and try to decipher the context of the question rather than chase the specific keywords

within the question. The goal is to provide results that actually answer to the question.

3

1.3 PAGE RANK ALGORITHM

Hummingbird looks at PageRank how important links to a page are deemed to be along with other

factors like whether Google believes a page is of good quality, the words used on it and many other

things. A webpage‟s ranking is determined by analyzing the ranking of all the other webpages that

link to the webpage in question. It is calculated as,

„n‟ = the number of pages in the web.

C (Tn) = the PageRank of each page by the number of outgoing links on that page .

d= damping factor decrease the influence of all of the pages in relation to the page in question.

1.4 GOOGLE GROWTH

Fig 1.4: Google Search timeline growth from 97-13

4

2. ARCHITECTURE OF GOOGLE HUMMINGBIRD ALGORITHM

Fig 2: Architecture of hummingbird algorithm

Hummingbird is a change in search algorithm that utilizes several factors which helps to initiate

conversation with the searcher and provides real answers to the queries instead of returning

keyword matching documents. Hummingbird is all about conversation and long tail queries are

often involved in conversation. Also, during conversation, we involve one or more entities and this

is where Knowledge Graph and semantics enters. The crux is that Google has adapted its search

algorithm to handle complex and conversational queries entered by the user with the introduction of

Hummingbird. It has used semantics and Knowledge Graph to a much greater depth than it has used

in the past.. The signals for ranking documents remains the same and Panda, Penguin, EMD etc. are

all parts of the main algorithm which is now the Hummingbird. Factors like Domain Authority,

Page Rank, Social Popularity, Overall Content Relevancy, Tf-Idf Score, Domain age, Google

Authorship, Use of Meta Data etc. all contribute towards ranking a specific document. But, we can

surely utilize this new model to adapt our existing content based on the manner a query gets parsed

and identified.

5

3. WORKING PROCESS OF GOOGLE HUMMINGBIRD ALGORITHM

Fig 3: Processing the user query and displaying the appropriate pages

SEO now requires a keener understanding of your audience. It doesn‟t start or end with keywords;

rather, it starts with the user and an understanding of what your user wants. Your content may have

four or five different types of users, who are searching for the answer to a query. Understanding

what‟s being served to which user and catering to those important segments with a good user

experience on your site is key.

Currently, personas are talked about more than ever in the search marketing world. Traditional

marketers have long since used this model to better understand their product or service user. This

depth of understanding is important as you think about the topics your users are interested in and

how you can be a solution for them with your content.

Keyword research still guides us to the topics people in our audience are searching for; but, our

responsibility as marketers is to go beyond that data. That means having the most useful, most

engaging, best quality page for a query with the appropriate keywords on the page. And although

keyword optimization often happens best when a topic is thoughtfully written, and has enough

6

depth to include many variations of a concept, optimizing your page for specific queries still

reinforces the topic of the page. If you haven‟t spent much effort gathering qualitative data about

your users, now is a good time to start. Surveys, monitoring conversations on social and talking

face-to-face with your customers will help you build those personas to better understand what

matters to them, so you can execute with content. But more on that in another post.

3.1 THE PAGE: HOW IS IT PERFORMING?

At BrightEdge, we‟ve been arming our customers with ways to measure our content‟s performance

at a page level even before Google‟s secure search was launched in full. This was not only in

anticipation of the change, but also a way to help businesses better understands the metrics that

matter.

Post-Hummingbird and post-secure search is all about measuring the content, not the keyword. Start

measuring what pages are generating the most value for you, and what types of content are

generating the greatest ROI.

If you have content that ranks well, but isn‟t driving traffic or engagement on your site, it‟s not

doing a good job of satisfying your users. You want to think about metrics like overall traffic to a

page, conversion rate and so on. Then, you can begin to look at groups of pages on your site that

best perform on a traffic and revenue level, depending on your goals. In the old paradigm, SEOs

may have used a “more content is better” approach. But now, it‟s relevancy, credibility, timeliness

and quality over quantity.

Once you have a picture of page performance on your site overall, you can then begin to make

decision decisions about where you want to focus time and resources on your website.

Fig 3.1: Keyword Relations: One Word Can Modify Search Results

7

3.2 KNOWLEDGE GRAPH

The Knowledge Graph is a knowledge base used by Google to enhance its search engine's search

results with semantic-search information gathered from a wide variety of sources With this new

algorithm Google is better able to understand the meaning of a sentence and return results to far

more complex search queries. In the past, Google analyzed keywords individually and tried to

match those individual keywords to the content of the site, but as search queries evolved, so has

Google.

In theory, the Knowledge Base has collected data for only a short while; however, most people

believe differently. To this very moment, knowledge is being gathered, categorized, cross-

referenced thousands upon thousands of ways, and stored. This vast well of knowledge is available

to the Hummingbird. With such a Knowledge Graph, was it not inevitable that Google would

eventually find a way to utilize this information with an algorithm that deciphers the context of all

the words in a query rather than homing in on a few key words therein? This is exactly what

Hummingbird is designed to do.

Information from Google‟s Knowledge Graph also appears more often than it did previously, which

helps Google provide answers directly in their search results. Early indicators show that the

medical-related queries appear to show Knowledge Graph info more often than others. Below is an

example of a two-word query in which an answer from the Knowledge Graph is shown at the top of

the search results

Fig 3.2: Search results of Knowledge Graph

8

4. TYPES OF SEARCH TECHNIQUES

4.1 SEMANTIC SEARCH

Google has implemented semantic search into its core algorithm by the recent introduction of

Hummingbird. This is a phenomenal change and one of the biggest to happen after Caffeine

Semantic search involves the study and implementation of semantics in the search technology in

order to find out the real intent of the searcher behind the search query and presenting the answers

or set of results that closely relates to what the user is searching. It takes into account the

importance of context and identifies a proper relationship between the terms used in the search

query before presenting the final search results.

4.1.1 What Is Semantics?

Semantics involves finding the relationship between words, phrases, symbols and the meaning they

denote. It further involves the study of linguistics, syntax, etymology, communication, semiotics

etc.

4.1.2 Where Does It Apply?

Search engines use semantics to return relevant results to the query. Ambiguous queries (those

queries which have more than one meaning) are broken down and processed via set of pre-defined

words helping the engines grasp the real context of the query. The use of semantics applies on

research related queries where the user is looking for answers instead of navigating to a specific

web page. Google applies semantics in its Knowledge Graph.

4.1.3 Page Rank and Relevancy Score: Two Basic Factors For Document Ranking

Google applies two basic factors for judging the importance and relevance of any webpage before

ranking them. These factors are Page Rank (for measuring popularity by analysing the backlinks)

and relevancy (by analysing the use of keywords or search query terms used in the webpage). But,

this form of ranking documents do not help to find those pages which may be relevant to searchers

intent as the popularity factor may reduce the rankings of semantically relevant documents. This is

the reason that Google uses semantics to identify and prioritize the rankings of pages having

semantically relevant content rather than only counting the keywords and backlinks for analysing

any webpage.

9

4.1.4 Query Processing In a Semantic Environment

The figure below describes the steps involved in the processing of the query by Google. The search

query received by Google is parsed (using a parser) to identify one or more members (first and

second search terms). In this process, synonyms or other replacement terms gets identified. These

synonyms are known as candidate synonyms and they further get broken down and processed as

qualified synonyms. Then, a relationship engine is used to identify the relationship between the

members based upon their respective domains. Here a domain simply means a centralized category

of similar words. First search term gets identified by the first domain which is a semantic category

having a collection of predefined entities. Similarly, the second term gets identified by a second

domain also containing a database of similar entities. This helps Google to relate the terms to the

closest matching identities (One essential point to note here is that Google will only find and relate

words in the query with those already present in its database which is the Knowledge Graph, hence

some queries although semantically similar might not show up). A separate search gets conducted

by a query engine using domain matching relationship (do not get confused with the word domain

with domain name, here domain means category) and final results gets displayed after a semantic

query is identified (the query engine may pluralize or rephrase the query if required). Hence, in

simple words, a complex query entered by the user is broken down and simplified involving several

processes into semantic query. Thereafter, relevant web pages are identified and displayed as a final

set of results.

Fig 4.1.4: Query parsed in a Semantic Environment

10

Many search engine optimizers and internet marketers often miss the crucial part of identifying

semantically related queries while doing keyword research because the main query gets broken

down into semantic query before it is processed by Google. Hence, the chance of ranking increases

when the content of the webpage is written keeping the semantic variants in mind mentioning all the

entities matching specific domains.

4.2 CONVERSATIONAL SEARCH

Users of Google Chrome may have noticed a small microphone icon in the right hand corner of

Google‟s search box (now on Google search as well). If the user clicks on that microphone (and has

configured their computer for it) they may ask aloud the question they would have typed into the

search box. The question is then displayed on the search screen, along with the results.

If the answer to the query is in Google‟s Knowledge Graph, an Information Card is displayed with

the pertinent facts listed along with a list of sites you may visit with more information and

hopefully, the answer to your question. What users of “Google Speak” have come to realize is that

the more conversational the query, the more information is provided.

“Conversational search” is one of the biggest examples Google gave. People, when speaking

searches, may find it more useful to have a conversation. “What‟s the closest place to buy the

iPhone 5s to my home?” A traditional search engine might focus on finding matches for words

finding a page that says “buy” and “iPhone 5s,” for example. Hummingbird should better focus on

the meaning behind the words.

It may better understand the actual location of your home, if you‟ve shared that with Google. It

might understand that “place” means you want a brick-and-mortar store. It might get that “iPhone

5s” is a particular type of electronic device carried by certain stores. Knowing all these meanings

may help Google go beyond just finding pages with matching words.

In particular, Google said that Hummingbird is paying more attention to each word in a query,

ensuring that the whole query the whole sentence or conversation or meaning is taken into account,

rather than particular words. The goal is that pages matching the meaning do better, rather than

pages matching just a few words.

11

Hummingbird expands the use of the Knowledge Graph, so that Google answers more complex

search queries and also improves the follow-up search process. For example, if we first search

“picture of Washington Monument” and then do a second search for “how tall is it?” Google will

understand the context of your second query.

How tall is it

Fig 4.2: Follow Up query process

12

4.3 VOICE SEARCH

Voice search naturally tends to mean more conversational and more natural language .Rather than

searching for a one or two word phrase, people will be more inclined to use whole sentences,

questions, and more complex queries when they speak. Hummingbird will determine the most

relevant and highest quality pages that meet the needs of the searcher.

Fig 4.3(a) Query Translation

Fig: 4.3(b) Results for Voice Search Based Query

13

4.4 MOBILE SEARCH

Analysts believe that these changes are heavily influenced by Google's desire to become more

mobile. As well as their mobile search engine pages, Google also owns Android which even has its

own voice search capabilities. Hummingbird will have a direct impact on those who employ mobile

friendly landing pages or sites.

Over time, people are going to increasingly gravitate to voice search in environments where that is

acceptable (e.g. environments where speaking to your device is not seen as intrusive). Voice queries

are far more likely to fall into the pattern of the natural language queries. As in all things search,

Google wants to dominate mobile search too. Google wants to process “real” speech patterns.

Fig 4.4: Mobile Search Technique

14

5. FEATURES

5.1 COMPARISONS

The knowledge graph enables more comparisons between search objects (ex: “compare butter vs

olive oil”, “compare Saturn vs Jupiter” etc.).

Fig 5.1: Comparison between Jupiter and Saturn

5.2 GEO-LOCATION ENHANCEMENT

If someone asks “What‟s the best place to buy an iPhone 5s?” then Google will likely bring a result

near to his current location.

5.3 IMPROVED MOBILE SEARCH DESIGN AND FUNCTIONALITY

Voice search and Android/iPhone synchronization are improved and will likely continue to improve

quickly.

15

6. ADVANTAGES

Search engine parse full query more quickly.

Google will be able to rank and identified content it has indexed with relevant queries.

Search engine can compile voice based queries more accurately.

Return relevant results discarded irrelevant results.

Search results would be determined to best suit the user experience.

More pages that are original offer more opportunities to answer search engine queries.

A wider topic coverage area for your expertise.

The opportunity to introduce more long tail keywords.

Surfing the news websites for your niche and writing creative content from current stories.

Videos are still hot and alluring for those choosing links with answers to their questions.

Infographics draw the curious and are a great way to answer search engine queries in a

creative and attractive manner.

7. DISADVANTAGES

7.1 THINK LONG-TERM

The new algorithm also teaches an important lesson on the speed at which the Web evolves: it takes

much time to search long tailed keywords.

7.2 DEDICATED WEBSITE

If you are having a website and you write article on different topic such that your website is based

on Mobile gadgets and you write all the latest information about them and suddenly you start to

write post on politics then Google will not give preference to your politics related articles. Before

launching the Hummingbird Algorithm Google categories the Post but Now Google is categorizing

the complete website so this is the time to drop you‟re all the post that is not related to your website.

16

7.3 USING A COPYRIGHT IMAGE/PICTURE ON WEBSITE

Google Started Voice Searching and also Picture matching so if you don‟t want to loose your

website rank don‟t use any copyright Picture in your article.

7.4 USING KEYWORDS ARE OLD FASHION

For the Old Search Google Algorithm then we have to use different keywords like this Pitfall of

Google Hummingbird Algorithm ,Drawback of Google Search New engine Technique,

Disadvantage of Hummingbird search Algorithm. So Google is Working For User query and

Genuine Content based and Content Meaning.

8. CONCLUSION

Hummingbird is paying more attention to each word in a query, ensuring that the whole query the

whole sentence or conversation or meaning is taken into account, rather than particular words. The

goal is that pages matching the meaning do better, rather than pages matching just a few words.

Google Hummingbird is designed to apply the meaning technology to billions of pages from across

the web, in addition to Knowledge Graph facts, which may bring back better results.

17

9. REFERENCES

http://thenextweb.com/google/2013/09/26/google-unveils-search-updates-for-

mobile-new-page-rank-algorithm-and-knowledge-graph-comparisons

http://www.cs.duke.edu/courses/spring08/cps049s/Slides/bryan.ppt

http://googleblog.blogspot.com/2010/06/our-new-search-index-caffeine.html

http://www.scf.usc.edu/~csci571/2013Fall/extras/GooglesNewSearchAlgorithm.p

ptx

http://www.entrepreneur.com/article/229926

http://searchengineland.com/google-hummingbird-172816

http://en.wikipedia.org/wiki/Semantic_search

http://www.google.com/insidesearch/howsearchworks/thestory/

http://searchengineland.com/5-ways-to-unlock-the-benefits-of-semantic-search-

hummingbird-175634

http://mashable.com/2012/03/22/google-semantic-search-seo/