Social Media Analytics Lecture

Social Media Analytics
Wasim Ahmed
Email: wahmed1@Sheffield.ac.uk
Guest Lecture for INF6032 Big Data Analytics
Monday 24th April 2017

About me
• Third Year PhD student in the Health Informatics Research
Group, Information School, University of Sheffield. (Faculty
Scholarship).
• CEO of Sonic Social Media - advise and work with a number
of social media monitoring and analytics organisations as
well as multi-million turnover brands.
• Run an analytics blog with readership in over 196 countries.
Read across media, government, and academia.

24/04/2017 © The University of Sheffield
3
https://wasimahmed.org/about/
http://blogs.lse.ac.uk/impactofsocialsciences/?s=wasim+ahmed
Published a number of
research papers, and
blogged widely.

4
• Delivered a number of talks related to my research such
as to the government , media , and industry.
• Upcoming talk to delegates at the European Centre for
Nuclear Research at CERN in Geneva. June, 2017.
• Co-running a Summer School in Šibenik, Croatia on
social media analytics. June 2017.
Recent and Upcoming talks

Lecture Aims
• Develop knowledge on the types of social media
analytics that are possible.
• Gain an overview of social media analytics tools.
• Understand how social media analytics have
been put to use by organisations.
5

6
• Twitter has over 313 million monthly active users1 –
consumers can use this channel to express their views.
• Businesses spend millions every year tailoring their
brands and protecting them.
• Brands can use Twitter to tap into and target consumers
and may spend a lot of money in doing so.
1 https://about.twitter.com/company
Twitter

7
• Open API so anyone with an Internet connection can
retrieve data
• Open platform where anyone can follow anyone and can
request to follow other users
• A lot of meta-data fields available to developers to
create analytics apps
Why is Twitter so popular?

8
United Airlines
• Recent example of a PR
disaster
• To-date this has received
n=170,346 retweets and
n=151,014 likes

9
Immediate Twitter Aftermath of United Airlines -
NodeXL Network Graph

10
American Airlines

11
American Airlines (Heat Map using
TrendsMap)

• Most frequently shared URLs, Domains, Hashtags,
Words, Word Pairs, Replied-To, Mentioned Users, and
most Frequent Tweeters.
• Produces analytics overall and by group of users (users
are grouped by tweet content).
• By looking at different metrics associated with different
groups (G1, G2, G3 etc) you can see the different topics
that users may be talking about.
NodeXL Produces a Number of Analytics

Centrality
• NodeXL also produces centrality measures
– Centrality measures help address the question:
who is the most important or central person in
this network?
– Centrality measures include:
• Degree centrality
• Closeness centrality
• Betweenness centrality
• Eigenvector centrality
• PageRank centrality

Betweenness Centrality
From Richard Ingram’s blog post visualising
Data: Seeing is Believing
http://www.richardingram.co.uk/2012/12/visu
alising-data-seeing-is-believing/

Degree Centrality
From Richard Ingram’s blog post visualising
Data: Seeing is Believing
http://www.richardingram.co.uk/2012/12/visu
alising-data-seeing-is-believing/

[Divided]
Polarized Crowds
[Unified]
Tight Crowd
[Fragmented]
Brand Clusters
[Clustered]
Community Clusters
[In-Hub & Spoke]
Broadcast Network
[Out-Hub & Spoke]
Support Network
6 kinds of Twitter networks

18
How can you use this?
• You can use social network analysis to
identify influencers and people who are
interested in a particular topic.
• You can identify clusters of users interested in
a particular topic and use automated methods
to target them.

20
In-built Twitter Analytics

21
Software As a Service (SAS)
• A number of online tools have emerged
utilising Twitter data and generated good
revenue by selling analytics as a service.
• Services such as:
• Brand and Media Monitoring
• Consumer Engagement
• Security

22
Visibrain
Audiense
TrendsMap
Echosec
DiscoverText
NodeXL

23
IBM Watson Personality Insights
https://www.ibm.com/watson/developercloud/pe
rsonality-insights.html#how-it-works-block

24
Twitter as a Media Monitoring Tool

25
Monitoring Keywords for Brand Monitoring

26
Monitoring Keywords for Brand Monitoring

27
Social Media For Security – Monitoring Locations

28
Social Media For Security – Monitoring Locations

29
Social Media Analytics For Research (DiscoverText)
Over 150 mentions of DiscoverText in academic research

30
DiscoverText – Powerful Filtering

31
Social Media Analytics for Consumer Engagement (Audiense)

32
Social Media Analytics for Consumer Engagement
(Audiense)
• You can leverage the back end analytics
provided by Twitter to build specific
audiences.
• You can use this information target users and
monitor the performance of the message that
you send.

33
Filter and Target

34
Using R for Text Mining and Social Network
Analysis:
• Text Mining
• Topic Modelling
• Sentiment Analysis
• Social Network Analysis
• Useful guide

Case Studies
35

DHL #AfricaAsOne
• Wanted to increase awareness and target
influencers
• They were able to find over 65 thousand
influencers across 45 African Countries
• Secured a reach of 1,200,750,000, with an
advertising value equivalent of
£12,112,8671
36

DHL #AfricaAsOne
• They used Audiense to create highly
customised groups of Twitter users
• “In-depth filtering and segmentation of
Twitter users by keywords in their bio,
combined with other variables1”
1 https://audiense.com/case-studies/dhl-africaasone/
37

World Economic Forum
• They weren’t engaging journalists and wanted to see
their events gain coverage.
• Used Audiense to launch direct message campaigns to
key segmented users.
• Led to coverage in the BBC, Bloomberg, CNN, and
many more outlets.
38
https://audiense-blog.s3.amazonaws.com/case-
studies/World%20Economic%20Forum%20-
%20Audiense%20Case%20Study%202016.pdf

Further Case Studies
• List of case studies from Audiense
• List of case studies from Visibrain
39

Summary
• We looked at social media analytics and
focused mostly on Twitter due to the open
nature of the platform it is a widely used
platform.
• The Importance of Social Media Analytics
for Businesses (video)
40

Practical on Wednesday
41
• TrendsMap
• Audiense
• NodeXL Graph Gallery

Social Media Analytics Lecture

More Related Content

What's hot (20)

Similar to Social Media Analytics Lecture (20)

Recently uploaded (20)

Social Media Analytics Lecture