Slides from a practical workshop on gathering customer insights from social media using Social Network Analysis (SNA) with NodeXL and Twitter. SNA allows you to gain insight from thousands of tweets and messages on a range of topics for marketing research or academic use. NodeXL reports can be used for measuring and monitoring an organisation’s own performance as well as a competitors´ performance. At the highest level, a SNA approach allows social media managers to recognize what their audience looks like.
2. Hello!
I’m Wasim Ahmed from the
University of Sheffield
PhD student (Information School )
Research Associate (Management School)
You can find me at @was3210
3. About my
PhD
⊙ PhD project (Faculty Scholarship)
examines infectious disease
outbreaks on Twitter.
⊙ Aim is to develop a better
understanding of how people
respond to outbreaks on Twitter.
⊙ Potential to better inform health
authorities (NHS/WHO/UN) when
disseminate.
4. Reasons for
using social
media
⊙ Regular contributor to the LSE
Impact blog on social media
⊙ Regularly talk at conferences,
industry events, and to government
related to social media
⊙ Visibrain Blog Partner, Connected
Action Partner, Echosec Advisor,
SMRF Member, and NSMNSS
member.
7. Reasons for
using social
media
(Research)
⊙ Network with other researchers
⊙ Use social media to share and
exhange resources
⊙ Use social media to conduct
research in a diverse range of
topics
9. How Social
Media has
been used
⊙ Used to increase brand
recognition and authority
⊙Building communities on
platforms
⊙Increasing sales conversions
10. How Social
Media has
been used
by
organisations
⊙ Building brand loyalty and
ambassadors, influencers
⊙ Improving customer insights
(Visibrain, Pulsar, NodeXL,
DiscoverText)
11. How Social
Media has
been used
by
consumers
⊙ Real time customer service
⊙ Being ‘in the know’ , special
offers etc
⊙ Channel for customer feedback
14. How Social
Media has
been used in
research
⊙ Social media data has been
utilized by research projects
seeking to better undertstand:
⊙ Health
⊙ Natural disasters
⊙ Riots
⊙ Crisis events
⊙ Politics
15. Popularity of
Twitter for
research
from my
article on the
LSE Impact
blog
⊙Twitter is a popular platform in terms
of the media attention it receives and
it therefore attracts more research due
to its cultural status
⊙Twitter makes it easier to find and
follow conversations (i.e., by both its
search feature and by tweets appearing
in Google search results)
16. Popularity of
Twitter for
research
⊙Twitter has hashtag norms which
make it easier gathering, sorting, and
expanding searches when collecting
data
⊙Twitter data is easy to retrieve as
major incidents, news stories and
events on Twitter tend to be centred
around a hashtag
17. Popularity of
Twitter for
research
⊙The Twitter API is more open and
accessible compared to other social
media platforms, which makes
Twitter more favourable to developers
creating tools to access data.
⊙Many researchers themselves are
using Twitter and because of their
favourable personal experiences, they
feel more comfortable with researching
a familiar platform.
18. This talk
looks at
Twitter
o When Twitter began to take
off a number of marketing
professionals tried to exploit it
for commercial purposes
19. 500 million tweets a day
That’s a lot of data!
316 million monthly active users
and
Twitter reports as having:
20. What is
Twitter?
o Twitter allows brief <140 character
text updates, know as ‘tweets’, to be
shared with other users as well as
images, videos, and links.
o Tweets can contain thoughts, feelings,
activities, and opinions (Chew and
Eysenbach, 2010).
21. Toyota ⊙Toyota had to recall a number
of its cars in 2009 ad 2010 due
to a serious safety fault which
resulted in the deaths of over 50
people
22. Toyota o As soon as the recall crisis start
getting media attention
Toyota quickly put together an
‘Online Newsroom’ and a
‘Social Media Strategy Team’
to coordinate all the media
releases
23. Sony
Playstation
Network
o In mid-April 2011 the
PlayStation Network was shut
down without explanation
o Frustrations quickly spread
through social media sites
such as Twitter as gamers
around the world voiced their
annoyance
24. Sony
Playstation
Network
o The lack of regular updates
and information from Sony
served to incense users
o Users struggled to determine
what was fact and what was
rumour on Twitter
25. Sony
Playstation
Network
o “I think It is pretty disgusting
that Sony have waiting 7 days
to tell users that their Credit
Card details may have been
compromised”.
o “I bet the hacker will get emails
out quicker than Sony!”
27. How can you
measure
social
media?
o Many social listening tools such
as Visibrain, Pulsar, and
DiscoverText
o Location based tools such as
Echosec
o Presentation looks specifically at
NodeXL in gaining insights from
social media data and leveraging
this as intelligence
32. Different
Types of API
Application Programming Interface (API)
Twitter’s Search API – focused on relevance and
not completeness, some tweets and users may be
missing from results (7 days back in time up to 3200
queries)
Twitter Streaming API – The Streaming APIs give
developers low latency access to Twitter’s global
stream of tweet data (live stream)
Firehose API – in theory, 100% of Twitter data (most
software allows up to 30 days worth of historical
tweets). Pay for service & one of Twitters revenue
streams.
33. NODEXL
o Network Overview, Discovery, and
Exploration for Excel (NodeXL) is a
graph visualization tool.
o Allows the extraction of data from a
number of popular social media platforms
including Twitter, YouTube, and
Facebook.
o Instagram capabilities in beta
34. Gaining
insights
Social media managers or digital teams
may be faced with a number of questions
such as:
• How do we increase the visibility of our
messages?
• How can we increase the number of followers,
likes and retweets?
• How do we become top influencers around
certain discussions?
• How can we make some of our messages viral?
• How do we gain actionable insight?
35. NODEXL
o From a network point-of-view this translates to:
o How do we build a network reach?
o What divisions or groups are present when users
mention our brand?
o Who are the most influential people in the
discussion?
o What exactly are they talking about?
37. Social
Network
Analysis
Social Network Analysis (SNA) is “the process of
investigating social structures through the use of
network and graph theories” (Otte, Evelien,
Rousseau, and Ronald, 2002)
Key terminology:
Node = ‘actor’ on which relationships
act
Edge = relationship which connects
nodes
38. NODEXL
Early social network diagram of relationships among workers in a factory. The
diagram illustrates the positions different workers occupy within the workgroup.
Originally published in Roethlisberger, F., and Dickson, W. (1939). Management
and the worker. Cambridge, UK: Cambridge University Press.
39. NODEXL
•The World Wide Web is a big
network where pages are nodes and
links are edges
•The Internet is a network where
nodes are computers and edges are
physical connections between
devices
40. Basic
network
graph of
#Durkheim
The circles represent the “vertices” (or Twitter users) and
the lines represent the “edges” (connections between
Twitter users) and the arrows on the lines show the
direction of the edge (who is tweeting at who).
41. Basic
network
graph of
#Durkheim
• The larger the vertex the higher
factor of “betweenness centrality”
• So largest vertices are ones with
many connections to others and
act as a ‘bridge’ between other
vertices i.e., Twitter users
• Important to note there are other
centrality measures
43. NODEXL
Alongside the graph metrics such as
the following are produced overall
and by group level:
• Top Influencers
• Top URLs
• Top Hashtags
• Top Words
• Top Mentioned
• Top Tweeters
44. NODEXL
• Produces metrics 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
48. #WorldMent
alHealthDay
The tweets in the network
were tweeted over the 19-
minute period from
Saturday, 10 October
2015 at 13:03 UTC to
Saturday, 10 October
2015 at 13:23 UTC.
49. @shell OR (shell
(oil OR OR gas
OR climate OR
environment OR
ecology OR
health OR spill
OR fossil
The tweets in the network
were tweeted over the 10-
day, 18-hour, 41-minute
period from Monday, 31
October 2016 at 06:16
UTC to Friday, 11
November 2016 at 00:57
UTC.
50. @hotelfootballuk
via NodeXL
The network was obtained
from Twitter on Monday,
21 November 2016 at
21:46 UTC. The tweets in
the network were tweeted
over the 9-day, 13-hour,
32-minute period from
Saturday, 12 November
2016 at 07:59 UTC to
Monday, 21 November
2016 at 21:32 UTC.
51. @hotelfootballuk
via NodeXL
Interactive
version
The network was obtained
from Twitter on Monday,
21 November 2016 at
21:46 UTC. The tweets in
the network were tweeted
over the 9-day, 13-hour,
32-minute period from
Saturday, 12 November
2016 at 07:59 UTC to
Monday, 21 November
2016 at 21:32 UTC.
52. @hotelfootballuk
via NodeXL
Interactive
version
The network was obtained
from Twitter on Monday,
21 November 2016 at
21:46 UTC. The tweets in
the network were tweeted
over the 9-day, 13-hour,
32-minute period from
Saturday, 12 November
2016 at 07:59 UTC to
Monday, 21 November
2016 at 21:32 UTC.
57. Social Media
could help
you to:
o Build brand awareness
o Generate direct sales
o Provide better customer service
o Build relations with customers
o Boost loyalty
o Increase brand recognition and authority
o Build communities
o Increase sales conversions
58. How could
you use
NodeXL?
o NodeXL can show the divisions or groups
present when users mention a brand
o It can highlight the most influential people in a
discussion, and provide features to target them
o It can help us to understand what people talk
about (graphs will vary week by week)
o By examining the Top URLs, Top Hashtags, Top
Words, Top Mentioned, and Top tweeters,
NodeXL can guide the dissemination of relevant
content
59. How could
you use
NodeXL?
o NodeXL can show the divisions or groups
present when users mention a brand
o It can highlight the most influential people in a
discussion, and provide features to target them
o It can help us to understand what people talk
about (graphs will vary week by week)
o By examining the Top URLs, Top Hashtags, Top
Words, Top Mentioned, and Top tweeters,
NodeXL can guide the dissemination of relevant
content
61. NodeXL
graph gallery
o Navigate to the NodeXL graph gallery
using the following URL:
http://www.nodexlgraphgallery.org/
o Browse the gallery, and find a network
graph of interest
o Examine the different groups, and try
out the interactive explorer
63. Credits Special thanks to all the people who
made and released these awesome
resources for free:
⊙ Presentation template by
SlidesCarnival
⊙ Photographs by Unsplash