Social media and web analytics

Unit-3
Website metrics
Website metrics are a variety of measurements made on a given website in order to better track
its performance and statistics. Metrics are the numbers behind certain variables related to a website.
Tracking these numbers is vital, and can often give insight that would otherwise be overlooked

Examples of website metrics

Website metrics may sound complicated, but they are actually very straightforward. Here are
a few examples of website metrics that you can track and measure, just to make things a little
more clear:

 Visitor traffic

Visitor traffic is probably the most common website metric. Anyone with a website, no
matter what its context will benefit from knowing how many people are visiting the site.

raffic numbers are a good indication of success. If you notice a large spike in website
traffic after a blog article is uploaded, odds are that you can benefit from more content like
that.

But, you’ll never know unless you track and measure your visitor traffic.

 Traffic sources

Just like you want to track how many visitors you’re getting, you’ll also want to track where
they’re coming from.

Tracking traffic sources will allow you to see exactly how visitors are getting to your website,
whether it be search engine results, a link from another website, or anything else.

 Top viewed pages

If you’re operating a blog or have multiple landing pages, knowing which piece of content
brings in the most pageviews is important.

Everything on a page can affect the traffic either positively or negatively. By knowing what
pages pull in the most traffic, you can essentially optimize all the other, lower-performing
pages.

 Bounce rate

Bounce rate refers to how many people click your website and click away or close their
browser shortly after.

1
NOTES BY- SIDDHARTHA SINGH
CHIEF PROCTOR & ASSISTANT PROFESSOR
KIPM TECHNICAL CAMPUS
 Social media and web analytics
Unit-3
The reason this is a problem is that it means people aren’t finding what they’re looking for.
As the bounce rate goes down, the amount of people that are finding your website helpful
goes up.

 Conversion rate

If your website aims to sell something, knowing how many people click on it and continue
with a sale is important. Conversion rate refers to the people following through with a sale
once they land on your website.

These are just a few of the more important examples of website metrics you can track and
measure. There are many more to consider.

Advantages of website metrics

Tracking and measuring metrics does more for your website than just give you reassurance. If
tracked and acted upon correctly, website metrics will:

 Help determine direction

 Establish a focal point
 Help make decisions, big or small
 Drive performance
 Provide real-time data

Again, these are just a few advantages in tracking website metrics. Depending on your
website’s purpose, and your desired direction, these are subject to change.

As long as the metric is well defined, easy to measure, and aimed towards the improvement
of the website, then it will be of great benefit to you.

Custom campaigns
Custom campaigns are created by adding extra information to the links that users
click on to get to your site. This process is called link tagging and the
“information” you add to the links is called UTM parameters (or campaign tags).

Google Analytics uses the information from these additional parameters (tags) to
identify where exactly the visitor is coming from. The campaign tags overwrite the
default categorization that would normally be assigned to the incoming traffic and
ensures that GA is capturing the correct information.

In that way, the campaign tags help Google Analytics to track more accurately the
incoming traffic and to avoid some common traffic channel misattributions, such
as:

2
NOTES BY- SIDDHARTHA SINGH
CHIEF PROCTOR & ASSISTANT PROFESSOR
KIPM TECHNICAL CAMPUS
 Social media and web analytics
Unit-3
 traffic coming from newsletters is often recorded as “direct”,
 banner ads on third-party websites show up as referral traffic, even though
they’re ads.

You can avoid these and many others tracking mistakes, by using custom
campaigns.

Key Performance Indicators (KPIs)

Key performance indicators (KPIs) refer to a set of quantifiable measurements used to gauge
a company’s overall long-term performance.

KPIs specifically help determine a company's strategic, financial, and operational

achievements, especially compared to those of other businesses within the same sector.

KEY TAKEAWAYS

 Key performance indicators (KPIs) measure a company's success versus a set of

targets, objectives, or industry peers.
 KPIs can be financial, including net profit (or the bottom line, gross profit margin),
revenues minus certain expenses, or the current ratio (liquidity and cash availability).
 Customer-focused KPIs generally center on per-customer efficiency, customer
satisfaction, and customer retention.
 Process-focused KPIs aim to measure and monitor operational performance across
the organization.
 Generally speaking, businesses measure and track KPIs through business analytics
software and reporting tools.

Types of Key Performance Indicators (KPIs)

Financial Metrics
Key performance indicators tied to the financials typically focus on revenue and profit
margins. Net profit, the most tried and true of profit-based measurements, represents the
amount of revenue that remains, as profit for a given period, after accounting for all of the
company's expenses, taxes, and interest payments for the same period.

Calculated as a dollar amount, net profit must be converted into a percentage of revenue
(known as "net profit margin"), to be used in comparative analysis.

For example, if the standard net profit margin for a given industry is 50%, a new business in
that space knows it must work toward meeting or beating that figure if it wishes to remain
competitively viable. The gross profit margin, which measures revenues after accounting for
expenses directly associated with the production of goods for sale, is another common
profit-based KPI.

3
NOTES BY- SIDDHARTHA SINGH
CHIEF PROCTOR & ASSISTANT PROFESSOR
KIPM TECHNICAL CAMPUS
 Social media and web analytics
Unit-3
A financial KPI that's known as the “current ratio” focuses largely on liquidity and can be
calculated by dividing a company's current assets by its current debts.

Customer Metrics
Customer-focused KPIs generally center on per-customer efficiency, customer satisfaction,
and customer retention.

Customer lifetime value (CLV) represents the total amount of money that a customer is
expected to spend on your products over the entire business relationship.

Customer acquisition cost (CAC), by comparison, represents the total sales and marketing
cost required to land a new customer. By comparing CAC to CLV, businesses can measure
the effectiveness of their customer acquisition efforts.

Process Performance Metrics

Process metrics aim to measure and monitor operational performance across the
organization.

By dividing the number of defective products by total products produced, for example,
businesses can measure the percentage of defective products. Naturally, the goal would be to
get this number down as low as possible.

Throughput time represents the total amount of time it takes to run a particular process. For
example, a drive-through restaurant throughput can measure how long it takes to service an
average customer; from the time they make their order to the time they drive away with their
food.

Limitations of Using Key Performance Indicators (KPIs)

Some of the disadvantages to using KPIs include:

 The long time frame required for KPIs to provide meaningful data
 They require constant monitoring and close follow up to be useful
 They open up the possibility for managers to "game" KPIs
 Quality has a tendency to drop when managers are hyperfocused on productivity
KPIs
 Employees can be pushed too hard aiming specifically for KPIs

A/B Testing
A/B Testing or split testing is a comparison between two variants of one aspect, say, two
versions of a webpage. It is like running an experiment between two or more pages
simultaneously to discover which one has the potential to convert more.

4
NOTES BY- SIDDHARTHA SINGH
CHIEF PROCTOR & ASSISTANT PROFESSOR
KIPM TECHNICAL CAMPUS
 Social media and web analytics
Unit-3
For example, e-Commerce websites use A/B testing on products to discover which product
has the potential to earn more revenue. Second example is AdWords campaign manager
running two ads for the same campaign in order to know which of them works well.

A/B testing allows you to extract more out of your existing traffic. You can run A/B Testing on
Headlines, Ads, Call to action, Links, Images, Landing pages, etc…

CRAWLING AND INDEXING

1. Crawling :
Crawling is the discovery process in which search engines send out a team of robots
(known as crawlers or spiders) to find newly updated content.

2. Indexing :
Indexing is the process that stores information they find in an index, a huge database of all
the content they have discovered, and seem good enough to serve up to searchers.

Difference between Indexing and Crawling :

S.No. CRAWLING INDEXING

In the SEO world, Crawling

means “following your Indexing is the process of “adding webpages
1. links”. into Google search”.

Crawling is the process

through which indexing is When search engine crawlers visit any link is
done. Google crawls through crawling and when crawlers save or index that
the web pages and index the links in search engine database is called
2. pages. indexing.

After crawling has been done, the result gets

When google visits your put on to Google’s index (i.e. web search),
website for tracking purpose. which means Crawling and Indexing is a step
3. This process is done by by step process.
Google’s Spiders or

5
NOTES BY- SIDDHARTHA SINGH
CHIEF PROCTOR & ASSISTANT PROFESSOR
KIPM TECHNICAL CAMPUS
 Social media and web analytics
Unit-3
Crawlers.

Indexing means when search engine bots crawl

Crawling is a process which the web pages and saves a copy of all
is done by search engine bots information on index servers and search
to discover publicly available engines show the relevant results on search
4. web pages. engine when a user performs a search query.

It finds web pages and It analyses the web pages content and saves the
5. queues for indexing. pages with quality content in index.

It performs analysis on the page content and

6. It crawls the web pages. stores it in the index.

Crawling is simply when

search engines bots are
actively crawling your
7. website. Indexing is the process of placing a page.

Indexing builds its index with every significant

Crawling discovers the web word on a web page found in the title, heading,
crawler’s URLs recursive meta tags, alt tags, subtitles and other
8. visits of input of web pages. important positions.

Natural Language Processing

Natural language processing is the artificial intelligence-driven process of making
human input language decipherable to software.

6
NOTES BY- SIDDHARTHA SINGH
CHIEF PROCTOR & ASSISTANT PROFESSOR
KIPM TECHNICAL CAMPUS
 Social media and web analytics
Unit-3
Why is Natural Language Processing Important?
Imagine your business software speaks a foreign language that you’re not fluent in –
natural language processing, or NLP, is your translator. It takes your human input,
reorganizes it, and explains what you’ve said in a way that your software can parse.

Natural Language Processing Techniques

The top 7 techniques Natural Language Processing (NLP) uses to extract data from text are:

1. Sentiment Analysis
2. Named Entity Recognition
3. Summarization
4. Topic Modeling
5. Text Classification
6. Keyword Extraction
7. Lemmatization and stemming

Let’s go over each, exploring how they could help your business.

1. Sentiment Analysis

Our specialty here at MonkeyLearn is sentiment analysis. This is the dissection of data (text,
voice, etc) in order to determine whether it’s positive, neutral, or negative.

As you can see in our classic set of examples above, it tags each statement with ‘sentiment’
then aggregates the sum of all the statements in a given dataset.

7
NOTES BY- SIDDHARTHA SINGH
CHIEF PROCTOR & ASSISTANT PROFESSOR
KIPM TECHNICAL CAMPUS
 Social media and web analytics
Unit-3
In this manner, sentiment analysis can transform large archives of customer feedback,
reviews, or social media reactions into actionable, quantified results. These results can then
be analyzed for customer insight and further strategic results.

Try out our sentiment analyzer to see how NLP works on your data.

To complement this process, MonkeyLearn’s AI is programmed to link its API to existing

business software and trawl through and perform sentiment analysis on data in a vast array of
formats.

2. Named Entity Recognition

Named Entity Recognition, or NER (because we in the tech world are huge fans of our
acronyms) is a Natural Language Processing technique that tags ‘named identities’ within
text and extracts them for further analysis.

As you can see in the example below, NER is similar to sentiment analysis. NER, however,
simply tags the identities, whether they are organization names, people, proper nouns,
locations, etc., and keeps a running tally of how many times they occur within a dataset.

How many times an identity (meaning a specific thing) crops up in customer feedback can
indicate the need to fix a certain pain point. Within reviews and searches it can indicate a
preference for specific kinds of products, allowing you to custom tailor each customer
journey to fit the individual user, thus improving their customer experience.

The limits to NER’s application are only bounded by your feedback and content teams’
imaginations.

3. Text Summary

This is a fun one. Text summarization is the breakdown of jargon, whether scientific,
medical, technical or other, into its most basic terms using natural language processing in
order to make it more understandable.

This might seem daunting – our languages are complicated. But by applying basic noun-verb
linking algorithms, text summary software can quickly synthesize complicated language to
generate a concise output.

8
NOTES BY- SIDDHARTHA SINGH
CHIEF PROCTOR & ASSISTANT PROFESSOR
KIPM TECHNICAL CAMPUS
 Social media and web analytics
Unit-3
Try out text summarization by adding your own text to the model below:

Test with your own text

Extract Text

Results
TAGVALUE

SUMMARYThe virus that causes COVID-19 is usually transmitted through droplets

generated when an infected person coughs, sneezes, or exhales.

4. Topic Modeling

Topic Modeling is an unsupervised Natural Language Processing technique that utilizes

artificial intelligence programs to tag and group text clusters that share common topics.

You can think of this a similar exercise to keyword tagging, the extraction and tabulation of
important words from text, except applied to topic keywords and the clusters of information
associated with them

5. Text Classification

Again, text classification is the organizing of large amounts of unstructured text (meaning the
raw text data you are receiving from your customers). Topic modeling, sentiment analysis,
and keyword extraction (which we’ll go through next) are subsets of text classification.

Text classification takes your text dataset then structures it for further analysis. It is often
used to mine helpful data from customer reviews as well as customer service slogs.

6. Keyword Extraction

The final key to the text analysis puzzle, keyword extraction, is a broader form of the
techniques we have already covered. By definition, keyword extraction is the automated
process of extracting the most relevant information from text using AI and machine learning
algorithms.You can mold your software to search for the keywords relevant to your needs –
try it out with our sample keyword extractor.

7. Lemmatization and Stemming

More technical than our other topics, lemmatization and stemming refers to the breakdown,
tagging, and restructuring of text data based on either root stem or definition.

9
NOTES BY- SIDDHARTHA SINGH
CHIEF PROCTOR & ASSISTANT PROFESSOR
KIPM TECHNICAL CAMPUS
 Social media and web analytics
Unit-3
That might seem like saying the same thing twice, but both sorting processes can lend
different valuable data. Discover how to make the best of both techniques in our guide
to Text Cleaning for NLP.

10
NOTES BY- SIDDHARTHA SINGH
CHIEF PROCTOR & ASSISTANT PROFESSOR
KIPM TECHNICAL CAMPUS