1.
Presented by: Dennis L. Kappen, Ph.D. Candidate,
GAMER Lab, FBIT
Twitter :3d_ideation
Image Source: http://room214.com/social/getting-to-know-twitter-analytics

2.
12/12/2016 Dennis L. Kappen Twitter :3d_ideation 2
Image Source: http://cdn2.business2community.com/wp-content/uploads/2015/02/twitter-analytics.png.png
Moving Product or Service > to Customer
Supply Chain Management > SCM

3.
12/12/2016 Dennis L. Kappen Twitter :3d_ideation 3
 Extracting intelligence
 from 22,399 #supplychain tweets.
 Framework
 descriptive analytics (DA),
 content analytics (CA) integrating text
mining and sentiment analysis,
 network analytics (NA)
 Findings
 Usage of supply chain tweets
Image Source: http://cdn2.business2community.com/wp-content/uploads/2015/02/twitter-analytics.png.png

4.
12/12/2016 Dennis L. Kappen Twitter :3d_ideation 4
 Introduction
 Background
 Framework
 Research method (Results)
 Discussion
 Implications
 Limitations and Future
Work
Image Source: https://media.licdn.com/mpr/mpr/AAEAAQAAAAAAAAQWAAAAJGE4ODJkOWY0LTVmYTctNDA5NC04ZDRkLWMwNWEwZWU5MzY1NQ.jpg

5.
12/12/2016 Dennis L. Kappen Twitter :3d_ideation 5

6.
12/12/2016 Dennis L. Kappen Twitter :3d_ideation 6
 Slow growth in the usage of social media
 Focus on:
 product traceability data
 geo-location and mapping data
 supply chain visibility and intelligence
Image Source:
https://pharmapromotional.files.wordpress.
com/2013/08/pharma_supply_chain_inform
ation_flow.png

7.
12/12/2016 Dennis L. Kappen Twitter :3d_ideation 7
 Access toTwitter data usingTwitter
Application Programming Interface (API)
 UnderstandTwitter within SCM context
 Analyse: tweets, replies, and retweets
Image Source:
http://www.glitztechnology.com/images/twi
tterapi-539x230.jpg

8.
12/12/2016 Dennis L. Kappen Twitter :3d_ideation 8
 Research direction:
 Tweet characteristics
 Topics characteristics
 User characteristics
 Sentiment characteristics.
Image Source:
http://www.glitztechnology.com/images/twi
tterapi-539x230.jpg

9.
12/12/2016 Dennis L. Kappen Twitter :3d_ideation 9
 Twitter Firehoses are
expensive
 Analysis is expensive
 Extract intelligence
from the highly
enriched and
unstructured social
media data

10.
12/12/2016 Dennis L. Kappen Twitter :3d_ideation 10
 Framework:
 Descriptive analytics (DA)
 Content analytics (CA)
 Network analytics (NA)
Image Source:
https://upload.wikimedia.org/wikipedia/com
mons/b/b7/Lorimerlite_framework.JPG

11.
 Descriptive analytics (DA)
 Descriptive Statistics
 Tweet metrics
▪ INTELLIGENCE extraction
▪ METRICS: number of tweets, word counts,
@user per tweet, number of hashtags, etc.
▪ WHO tweets, replies, and retweets?
▪ WHICH URLs?
12/12/2016 Dennis L. Kappen Twitter :3d_ideation 11
Image Source: http://wersm.com/wp-
content/uploads/2013/11/twitter-analytics-
657x360.jpg

12.
 Content analytics (CA)
 Texts are unstructured
 Text cleaning and processing
 Information and opinions
 Advanced text mining:
sentiment analysis
 TwitterAnalytics relies on
automatic text processing
techniques and algorithms
12/12/2016 Dennis L. Kappen Twitter :3d_ideation 12
Image Source:
http://www.contentanalyticsinc.com/about

13.
 Network analytics (NA)
 Users engage using@reply
and retweet
 Network topology
▪ Nodes (users)
▪ Edges (relationships)
 Twitter data
▪ friendship network and @reply (or
mention) network.
12/12/2016 Dennis L. Kappen Twitter :3d_ideation 13
Image Source:
http://www.contentanalyticsinc.com/about

14.
 Network analytics (NA)
 Centrality analysis
 Community analysis
 Modularity analysis
12/12/2016 Dennis L. Kappen Twitter :3d_ideation 14
Image Source:
http://www.contentanalyticsinc.com/about

15.
12/12/2016 Dennis L. Kappen Twitter :3d_ideation 15

16.
12/12/2016 Dennis L. Kappen Twitter :3d_ideation 16

17.
12/12/2016 Dennis L. Kappen Twitter :3d_ideation 17

18.
 500 million tweets/day (2015)
 #supplychain 22,399 tweets
 Script languages
 Tweet Statistics
 Original tweets (58%)
 Retweets (28%)
 @replies (14%)
12/12/2016 Dennis L. Kappen Twitter :3d_ideation 18
Image Source: http://yogfitness.com/wp-
content/uploads/2016/04/historical-
tweets.jpg

19.
 4313 unique users
 Active users = original tweets
+ retweets+@replies
 Visibility = @replies received
+ retweets received
12/12/2016 Dennis L. Kappen Twitter :3d_ideation 19
Image Source: http://yogfitness.com/wp-
content/uploads/2016/04/historical-
tweets.jpg

20.
12/12/2016 Dennis L. Kappen Twitter :3d_ideation 20
 Active users = original tweets + retweets+@replies
 Visibility = @replies received + retweets received

21.
12/12/2016 Dennis L. Kappen Twitter :3d_ideation 21
 One or more URLs = 89%
 Active andVisible users include URLs in their
tweets
 Top URLs include:
 companies' webpages
 SCM online newspaper sites, and
 articles about manufacturing leadership,
 and Big Data.

22.
12/12/2016 Dennis L. Kappen Twitter :3d_ideation 22

23.
12/12/2016 Dennis L. Kappen Twitter :3d_ideation 23
 3839 different hashtags appear 62,575 times

24.
12/12/2016 Dennis L. Kappen Twitter :3d_ideation 24

25.
12/12/2016 Dennis L. Kappen Twitter :3d_ideation 25
Exemplar tweets Sentiment
This development is pretty exciting for me #supplychain #sustainability 3 (Positive)
Samsung assures excellent working conditions in China. 〈http://t.co/9VcBIL1XAj
#workingconditions #supplychain #responsiblesourcing #rtw〉
3 (Positive)
Loving the feedback that I am getting on this report today! #supplychain
〈http://t.co/7DJaJFFl〉
3 (Positive)
As parked 787 s multiply? Boeing cash drain worries grow 〈http://t.co/up6V9sBYbi
#supplychain〉
-3 (Negative)
CHaINA Magazine: Apple Finds Child Labor Abuses in Its Supply Chain – As the
controversy regarding. 〈http://t.co/kt6MMXvng #SupplyChain〉
-3 (Negative)
Walmart US Chief Says Sales are Suffering Because of Restocking Issues
〈http://t.co/xhpK4pYy3v #supplychain〉
-3 (Negative)

26.
12/12/2016 Dennis L. Kappen Twitter :3d_ideation 26
Exemplar tweets Sentiment
CSR Investigation of #Apple #SupplyChain by #SACOM reveals continued
#labor abuse throughout despite Apple's claims.
〈http://t.co/Cm0VYeTT94 #CSR〉
Negative
Loving this Green Supply Chain infographic 〈http://t.co/M0spSUs6WG
#supplychain #CSR #infographic @SCInsightsLLC〉
Positive
IT Supply Chain Disruption a MajorThreat to Business from @forbes
〈http://t.co/raX48u4Zcw #supplychain #IT #analytics〉
Negative
How @Sony strengthened its supply chain and added value
〈http://t.co/B0DTiWPAnm #GrnBz via @GreenBiz #IT #supplychain〉
Positive
Logistics Could I expect to receive my parcel today? I doubt it. Another terrible
experience from @Parcel2Go #expensive #supplychain #logistics
Negative
Great day @ #DalhousieUniversity! Excellent case study presentations
by 16 teams. Join Careers in Motion @JDIcareers #logistics #supplychain
Positive
Risk With new #supplychain controls in place IKEA meatballs back after
horsemeat scare 〈http://t.co/YKvYT1ov1H #risk〉
Negative

27.
12/12/2016 Dennis L. Kappen Twitter :3d_ideation 27
 5447 Nodes = users
 9238 edges = relationships (@reply)
 Network diameter = 19
 Average path length =5.82
Example: 6 nodes, 7 edges : StackOverflow

28.
12/12/2016 Dennis L. Kappen Twitter :3d_ideation 28
Image Source:
http://image.slidesharecdn.com/socialnetw
orkanalysis-100225055227-
phpapp02/95/social-network-analysis-19-
638.jpg?cb=1385568277
 Degree Centrality
 In-degree
 Out-degree

29.
12/12/2016 Dennis L. Kappen Twitter :3d_ideation 29
 CentralityAnalysis (node-level)
 Nodes connectedness
 Community Analysis (network-level)
 Network was sparsely distributed
 Over 400 communities in the #supplychain
network
Image Source:
http://www.compjournalism.com/wp-
content/uploads/2012/11/centrality-
measures.png

30.
12/12/2016 Dennis L. Kappen Twitter :3d_ideation 30Companies Industry Press Individual users

31.
12/12/2016 Dennis L. Kappen Twitter :3d_ideation 31
(Blondel et al., 2008)

32.
12/12/2016 Dennis L. Kappen Twitter :3d_ideation 32

33.
12/12/2016 Dennis L. Kappen Twitter :3d_ideation 33
Image Source:
http://www.supplychain247.com/images/arti
cle/a_portrait_of_the_supply_chain_manag
er_wide_image.jpg
 Topical
 73% of #supplychain tweets contained two or
more hashtags
 Factors for information diffusion

34.
12/12/2016 Dennis L. Kappen Twitter :3d_ideation 34
Image Source: http://blog.mytmc.com/wp-
content/uploads/2015/01/ConnectPorts.jpg
 Topic Areas
 Popular hashtags
 Topics of interest

35.
12/12/2016 Dennis L. Kappen Twitter :3d_ideation 35
Image Source: http://http://erau.edu/-
/media/images/shared/degrees/videos/worldwide/
master-of-science-in-logistics-and-supply-chain-
management-source.png
 Characteristics of users
 Job or career services
 SCM practitioners
 Trade magazines
 Active users vsVisible users
 Users vsTweets

36.
12/12/2016 Dennis L. Kappen Twitter :3d_ideation 36
Image Sourcehttp://beta.www.hull.ac.uk/editor-
assets/images/Logistics/supply.png
 #supplychain had low sentiment
 Major events influencing sentiments
 Promotional tweets
 Negative sentiment

37.
12/12/2016 Dennis L. Kappen Twitter :3d_ideation 37
Image Sourcehttp://beta.www.hull.ac.uk/editor-
assets/images/Logistics/supply.png

38.
12/12/2016 Dennis L. Kappen Twitter :3d_ideation 38
 Short data collection period
 #supplychain vs keywords
 Future work
 Guidelines
 Impact of social media on supply chain
performance

39.
12/12/2016 Dennis L. Kappen Twitter :3d_ideation 39
 Research Methods section
 Reporting Results
 Themes in word analysis and sentiment
analysis
 No explanation of the evolution of these
themes (inductive or deductive ?)

40.
www.gamefulplay.ca
Twitter :3d_ideation
12/12/2016 Dennis L. Kappen Twitter :3d_ideation 40
.com