SOCIAL MEDIA ANALYTICS

PRESENTED BY,
B9
INTRODUCTION
• Social Media Analytics is the practice of gathering data from blogs
and social media websites and analyzing that data to make
business decision.
• The most common use of Social Media Analytics is to mine
customer sentiment in order to to support marketing and
customer service activities.
• Social Media Analytics describes the activities of monitoring and
recording, analysing and interpreting the results of interaction and
association among people, topics and ideas
CONSUMERS OF SOCIAL MEDIA ANALYTICS

• Corporates are major consumers of Social Media Analytics

solution. They are interested to know what people thinks about
their product or services.
• There are instances that academics attempted to use the same
technology to predict election results, impact of social
movements etc.
• Economists are now exploring the same techniques of Social
Media Analytics to predict Stock Market Results.
USER GENERATED CONTENT (USG)

• User Generated Content is defined as the form of content such as blogs, wikis,
discussion forums, posts, charts, tweets, podcasts, digital images, video, audio
files, advertisements and other forms of media that was created by users of
an online system or service, often made available via social media websites.
• UCG in the form of product review, blogs or messages on social media
platforms, makes up an increasing share of overall Internet Content.
• It comes as blogs like travel diaries or reports, messages on social networks
like facebook, instagram, twitter, etc, product reviews on platforms like
TripAdvisor or Booking.com
REASON FOR ADDING A UCG ELEMENT

• Better Understanding of Target Audience

• More Site Engagement
• Stronger Community
• Increased Time on Sites
• SEO Benefits
• Increased Social SEO Indicators
• Trustworthy Content
SENTIMENT ANALYSIS

• Sentiment analysis is the process of computationally identifying and

categorising opinions expressed in a piece of text, especially in order to
determine whether the writer’s attitude towards a particular topic, product,
etc. is positive, negative, or neutral.

• Sentiment analysis refers to the use of natural language processing, text

analysis, computational linguistics, and biometrics to systematically identify,
extract, quantify, and study affective states and subjective information.
CHARACTERISTICS OF SENTIMENT ANALYSIS
1. Sentiment Categorisation ( Objective versus Subjective Sentences )
2. Levels of Analysis
• Message Level
• Sentence Level
• Entity and Aspect Level
3. Regular versus Comparative Opinion
• Regular Opinion
 Direct Opinion
 Indirect Opinion

• Comparative Opinion
4. Explicit versus Implicit Opinion
• Explicit Opinion
• Implicit Opinion
5. Role of Semantics
6. Dealing with Figures of Speech
7. Relationships in Social Networks
IMPORTANCE OF SENTIMENT ANALYSIS IN SOCIAL
MEDIA ANALYTICS
Social media sentiments analysis can be an excellent source of information and can provide insight that
can:
 Determine marketing strategy
 Improve campaign success
 Improve product messaging
 Improve customer service
 Test business KPI’s
 Generate leads
TYPES OF SENTIMENT ANALYSIS
1. NLP
 Natural language processing is a field of computer science, artificial
intelligence, and linguistics concerned with the interactions between
computers and human(natural) languages.
 SentiWordNet provides a sentiment polarity values for every term occurring
in the document.
 Each term t occurring a SentiWordNet is associated to 3 numerical scores
obj(t),pos(t), and neg (t).
2. MANUAL PROCESSING:
Human interpretation of sentiment is definitely the most mature
and accurate judge of sentiment. However, it still is not 100%
accurate.

3.KEYWORD PROCESSING:
Keyword processing algorithms assign a degree of positivity or
negativity to an individual word, then it gives and overall
percentage score to the post.
METHODS OF SENTIMENT ANALYSIS

• DOCUMENT-LEVEL SENTIMENT ANALYSIS: This technique assumed that every

document contains an opinion or opinion related words.

• SENTENCE-LEVEL SENTIMENT ANALYSIS: This technique is based on

specialization of documents which contains various sentences and every
sentence contains an opinion behind it.

• COMPARITIVE SENTIMENT ANALYSIS: In this technique identification of

sentences which contain comparative opinions are filter out and opinions are
extracted by considering sequential patterns as features.
• DOCUMENT-LEVEL SENTIMENT ANALYSIS: This technique assumed that every document
contains an opinion or opinion related words.

• SENTENCE-LEVEL SENTIMENT ANALYSIS: This technique is based on specialization of

documents which contains various sentences and every sentence contains an opinion behind
it.

• COMPARITIVE SENTIMENT ANALYSIS: In this technique identification of sentences which

contain comparative opinions are filter out and opinions are extracted by considering
sequential patterns as features.
 WEB ANALYTICS S0CIAL MEDIA
ANALYTICS
•Based or corporate-generated
media, mainly investigating
paid-for and owned media.
•Analysis will reveal patterns
and trends without
hypothesis.
PURPOSE
•Output is limited to visitors
and audiences to channels of
the organisation.
•Audience is made up of
POPULATION website visitors. Does not
include competitors.
•Segmentation relatively easy.
•Based on user-generated
media mainly investigating
earned media.
•Hypothesis are valuable,
search terms to be monitored
must be carefully created.
•Output is large, the size of
the internet user population,
channels can be chosen.
•Audience is made up of
opinion leaders, influencers
and detractors, includes
competitors.
•Segmentation less easy.
 WEB
ANALYTICS
•Can only take place if the
company has a website.
•The use of web counters,
log file analysis and
JavaScript tags, packet-
sniffing solutions have been
used.
•Data capture and analysis
PROCEDURE is automated. Results
generally delivered directly
to clients.
•Analysis by statistics
(numbers).
•Limited number of
vendors.
SOCIAL MEDIA
ANALYTICS
•Can take place without a
corporate website.
•Listening platforms
operate in a similar way to
search engines and search
directories.
•Data capture often
automated but needs
human intervene on the
analysis. Results reach
clients via third parties.
•Analysis by text analytics
(words).
•Numerous vendors.
 WEB
ANALYTICS
•Organisation has full
control over
communications visible to
the public.
•Web users are blind to
PUBLICATION web analytic results.
•The organisation is less
likely to interact with the
website visitor.
SOCIAL MEDIA
ANALYTICS
•Internet users have most
control over
communications viable to
the public.
•If the web users view
conversations, opinions
may change.
•The organisation goes
beyond research and will
interact individually or
collectively.
THE END