Web Mining

Overview, Social
Media Analytics,
Sentiment Analysis
Web Mining
&
Web Analytics
Web Mining Overview:

 Web mining is a part of data mining

 Web mining is used to discover and extract information

from Web-related data sources such as Web documents,
Web content, hyperlinks and server logs.

 The main goal of Web mining is to look for useful

patterns in Web data by collecting and analysing
information in order to gain insight into trends, the
industry and users.

 Web mining is an iterative process of discovering

knowledge and is proving to be a valuable strategy for
understanding consumer and business activity on the
Web.
 Basically there are three sub categories for mining
web information
These sub categories are:

 Web Content Mining

 Web Usage Mining

 Web Structure Mining

 Web Content Mining

Web Content Mining is the process of mining useful
information from the contents of Web pages and Web
documents, which are mostly text, images and
audio/video files
 Web Usage Mining (Web Behavior Mining)

Web usage mining is the process of extracting useful

information from server logs e.g. use Web usage
mining is the process of finding out what users are
looking for on the internet.
 Web Structure Mining

 Web structure mining is the collection of methods which are used

for mining or analysing the structure of a website or hierarchy or
the links of a website. In web structure mining the structure of a
web is mined on the basis of hyperlinks and intra-links.

 There are two types of web structure mining:

in the first type the patterns are discovered
from the hyperlinks of the web pages, and in
the second type the patterns are discovered
from the document structure. Web structure
mining gives the structure of a website and
the relation between multiple web sites or web
pages
WEB ANALYTICS
In simple terms
 Web analytics is the study of the
behavior of website visitors

In commercial terms
 It refers to the USE of DATA collected
from a WEB SITE to determine which
aspect of the website achieve the
business objectives
WEB ANALYTICS
or
In commercial terms
 It is the measurement, collection,
analysis, and reporting of Internet
data for the purposes of
understanding and optimizing Web
usage.

(Source: Web Analytics Association)

IMPORTANCE
1. Provides insights into the
performance of a website

2. Companies use web analytics to find

out information about:

 visitors and
 how they interact with the webpage
IMPORTANCE
3. Today, Web interactions between
commercial businesses and their
customers take place via e-commerce
stores, customer service sites,
interactive real-time chat, e-mail, and
social media streams; SO IT IS
IMPORTANT TO KNOW VISITORS
BEHAVIOR TO OPTIMIZE THE USAGE
WITH THE SITE
IMPORTANCE
4. Web data integrated with other channels
provides a better picture of the customer–
business relationship and helps in
identifying customer trends
5. It is also useful in assessing the
effectiveness of marketing campaigns and
optimizing marketing spend
6. It improves the customer experience
through faster service, thereby driving
business growth and enhancing reputation
CUSTOMER EXPECTATIONS FROM THE
WEBSITES

 Remember who I am between visits

 Make it easy to find what I need

 Give me relevant content, let me look and

compare

 Share the “wisdom of the crowd” with

me
CUSTOMER EXPECTATIONS FROM THE
WEBSITES

 Recommend products I might be interested in

 Display what people “like me” have looked at

 Guide my shopping decision with relevant

advice

 Give me the right price

 Provide sales support (e.g. click-to-chat)

CUSTOMER EXPECTATIONS FROM THE
WEBSITES

 Send me promotions and coupons

 Allow me to connect with other

customers and enthusiasts

 Tell me when my order will arrive

 Allow me to modify or cancel my order

 Make sure my order arrives on time

CUSTOMER EXPECTATIONS FROM THE
WEBSITES

 Allow me to use my preferred

payment method

 Let me go straight to checkout

WEB ANALYTICS – WHAT IS BEING
ANALYZED
 In its most elemental form, website
administrators use a social analytics
service, such as Google Analytics - the most
widely used social analytics tool globally -
to capture and analyze data including:

 Site visits and unique site visits (i.e.

unique, independent visitors as opposed to
one visitor visiting a site multiple times)

 The pages that are the most and the least

viewed
WEB ANALYTICS – WHAT IS BEING
ANALYZED

 How long the web page is visited

 Physical location of site visitors

(city/country)

 Time of the day that most visitors

access the site

 The last page site visitors access before

leaving
WEB ANALYTICS – WHAT IS BEING
ANALYZED
 The web browsers and operating
systems that visitors use

 Search terms used to find the site

 In most cases, people visit websites not

by typing the Web address into their
browser but by following a link. Such
links can be on other websites or on
search engine results pages. By seeing
where site users are coming from,
company staff can gain a sense of how
best to focus marketing efforts.
INFORMATION ARE TRACKED AND
ANALYZED
 Thisinformation can be used to identify
which parts of a website are effectively
serving the site owner’s objectives

 “Which links are directing lots of traffic to

my site? Should I deepen my relationship
with that organization?” and which are
detracting from those objectives

 “Whydo people leave my site from that

page more than from any others?”
IN OTHER WORDS
How people find your site :
 What search engine do they use?
 What search terms do they use?
 What sites refer visitors to my site?

How people navigate your site

 What content are they most interested in?
 Where do people drop out of the site?

How people become customers

 What part of my web site is most effective at
generating sales?
 What are the conversion rates (number of sales)
based on traffic from different sites?
 Where are the customers located?
WEB ANALYTICS
 Performance Management

 Visitor Data

 Marketing Optimization

 Content Optimization
WEB ANALYTICS - CHALLENGES
 Data volume growth is accelerating, making
it cumbersome to capture and analyze Web
data

 Unstructured social media data growth

compounds the challenge, particularly as it
must be integrated with enterprise structured
data

 Multiple Web interaction platforms (PC,

smartphone, tablet) further add to data
capture and integration challenges
WEB ANALYTICS – HOW IS DATA
COLLECTED
 Server logs

 Script based tracking

WEB ANALYTICS – HOW IS DATA
COLLECTED
 Server logs

 Data saved generally includes:

 IP address of the client
 User name if logging on is necessary.

 Date and Time

 Page of file requested

 Number of bytes returned,

 Browser the client used

 URL of page which contains the link

 Any cookies.

 Any errors
WEB ANALYTICS – HOW IS DATA
COLLECTED
 Script Based Tracking
• Some code (normally Java script) is added to each page.
• This code can collect additional information and send it back
to the server.
– for example: Information about the screen size, partial form
completion.
• The page tagging service manages the process of assigning
cookies to visitors.
• Page tagging can report on events which do not involve a
request to the web server
– Eg. such as interactions within Flash movies or partial form
completion
• The technology is usually provided as part of a hosted solution
and website owners can access real time reports online
without needing any additional hardware or software in-house.
WEB ANALYTICS – HOW IS DATA
COLLECTED
 Web Cookies
• Cookies are small files which are stored on a user's
computer. They are designed to hold a modest amount
of data specific to a particular client and website, and
can be accessed either by the web server or the client
computer. This allows the server to deliver a page
tailored to a particular user, or the page itself can
contain some script which is aware of the data in the
cookie and so is able to carry information from one visit
to the website (or related site) to the next.
BEHAVIORAL METRICS – WEB
BEHAVIOR MINING
 Click-stream data tracks the exact pattern of a
consumer’s navigation through a Web site

 Click-stream data can reveal:

 Number of pageviews
 Pattern of Web sites visited
 Length of stay on a Web site
 Date and time visited
 Number of customers with shopping carts
 Number of neglected shopping carts
BEHAVIORAL METRICS
 Visitor Web site metrics
BEHAVIORAL METRICS
 Exposure, visit, and hit Web site metrics
Social Media
Analytics
 Social media analytics

Social media analytics is the practice of gathering

data from social media websites and analyzing that
data using social media analytics tools to make
business decisions. The most common use of social
media analytics is to mine customer sentiment to
support marketing and customer service activities.
Typical Social Media Analytics objectives include:

 Amplify the business presence

 Running campaign through Social Media

 Reducing customer service costs with proper Social

Media monitoring process
 Getting feedback on products and services

 Track public opinion for a particular product or

business division.
 Dopeople tweet favourably about my
company? Do they tweet about it at all?

 What are the major trends in my field that we

can see over social media? How can I
capitalize on them?

 Whycertain Facebook posts get a lot of

engagement????

 Whichproducts are pictured on Instagram

more often than others
 Benefits/ Usage:
 Social media analytics helps organizations
understand their targeted audience. 
 An American gaming and media streaming website
used social media analytics to analyze and define the
segments of its audience that were most interested
in certain types of video games in order to offer
insight and more effectively support its clients’ ad
strategies.
 Social media analytics can increase
engagement and responsiveness:

 A marketing software company increased the leads

generated through social media by 47% over last
year, thanks to a complete picture of what its
customers are saying on the web.
 Brand awareness has a major impact on consumer
choices. A British non-profit that needed to amplify
its message and increase fundraising used social
media analytics to measure and improve
brand awareness through deep insights on what
consumers were saying about its brand

 Social media analytics can highlight problems

and weaknesses to discover new trends and
avoid a brand crisis. A large brewing company
found that one of its products had a 25% negative
sentiment rating. Thanks to a constant social
media analytics and monitoring, the company was
able to control the crisis and quickly recover.
 Social media analytics can help you learn
from the competition. Monitoring and analyzing
unstructured information help companies stay
informed about the latest from competitors, as well
as the reactions customers and the activities to
avoid.

 One of the most important European supermarket

analyzed social conversations around the home
delivery service of its biggest competitor in order
to understand who its key customers were, how the
customers described the service and customers’
“level of trust” in the company.
 Measuring the Social Media Impact
 Use Cases for Social Analytics
The insights found through Social Media Analytics can
power every part of brand operations. Here are some
examples:
 Increase Customer Acquisition

By delivering what they know their audience wants

 Protect Brand Health

By offering the type of meaty stories they know your

readers love
 Lower Customer Care Costs

 Maximize Product Launches

Gift customers who influence others about your product

 Boost Campaign Performance

 Improve Crisis Management

To understand public misperception and gauge when, if, and how to

respond to potential crises – among other things!
Continued…

Analyse followers
Analyse the reach and results of your posts

Identify influencers

Compare platforms

Improve your ROI

Sentiment
Analysis
Sentiment analysis overview

 Sentiment analysis – otherwise known as

opinion mining – is a much bandied about but
often misunderstood term

 In essence, it is the process of determining the

emotional tone behind a series of words, used to gain
an understanding of the the attitudes, opinions and
emotions expressed within an online mention.
 Sentiment analysis is extremely useful in social media
monitoring as it allows us to gain an overview of the
wider public opinion behind certain topics

 The applications of sentiment analysis are broad and

powerful. The ability to extract insights from social
data is a practice that is being widely adopted by
organizations across the world

 The Obama administration used sentiment analysis to

gauge public opinion to policy announcements and
campaign messages ahead of 2012 presidential
election. Being able to quickly see the sentiment
behind everything from forum posts to news articles
means being better able to strategize and plan for the
future
 It can also be an essential part of your market
research and customer service approach. Not only can
you see what people think of your own products or
services, you can see what they think about your
competitors too