SlideShare a Scribd company logo
Copyright © 2015 KNIME.com AG
Customer Intelligence on Social
Media
Rosaria Silipo
KNIME.com AG
Copyright © 2014 KNIME.com AG 2
Copyright © 2014 KNIME.com AG 3
The KNIME Platform: Open for Innovation
Powerful: Legacy  Future Tools
Collaborative: Scientists  Analysts
Integrative: Legacy  Future Data
Transparent: Existing  Future Expertise
Agile: Internal  External Wisdom
3
Copyright © 2014 KNIME.com AG 4
KNIME Analytics Platform
4
Copyright © 2014 KNIME.com AG 5
NODES perform tasks on data
Nodes are combined to create
WORKFLOWS
Status
Visual KNIME Workflows
Inputs Outputs
Not Configured
Idle
Executed
Error
Copyright © 2014 KNIME.com AG 6
Statistics
Data Mining
Machine Learning
Web Analytics
Text Mining
Network Analysis
Social Media Analysis
WEKA
R
Community / 3rd
MySQL, Oracle, etc.
SAS, SPSS, etc.
Excel, Flat, etc.
Hive etc.
XML, PMML
Text, Doc, Image
Web Crawlers
Industry Specific
Community / 3rd
ETL
Row,
Column
Matrix
Text, Image
Time Series
Java
Python
Community / 3rd
Includes over 1000 native and embedded nodes
via BIRT
PMML
XML
Databases
Excel, Flat, etc.
Hive etc.
Text, Doc, Image
Industry Specific
Community / 3rd
6
Copyright © 2014 KNIME.com AG 7
Who’s Using KNIME?
> 2,000,000 Downloads annually (in 2015)
> 70,000 Individuals using KNIME
> 5,000 Organizations using KNIME
> 700 Customers paying for KNIME
7
Copyright © 2014 KNIME.com AG 8
Top in User Satisfaction
2012 & 2013 Rexer Analytics Survey
Users who know KNIME love it!
8
Open Source
Overall
Copyright © 2014 KNIME.com AG 9
KNIME Analytics Platform: Try it Now!
1. Download from
www.knime.com
2. Browse the KNIME
Learning Hub at
www.knime.com/learning-hub
3. Check out KNIME Press
“KNIME Beginner’s Guide”
4. Become active on our Forum!
Copyright © 2014 KNIME.com AG 10
Copyright © 2014 KNIME.com AG 11
The Problem
A major European Telco
11
• Can you tell us what people say about our new
product?
• Can you tell us who is supporting the product and
who trashing it?
• Of those, can you tell us who is an influencer?
Its Forum Site
Copyright © 2014 KNIME.com AG 12
The Data
12
• The Data Set unfortunately cannot be shared
• Slashdot Forum Data are!
• Slashdot was a public forum built in 1997 and
hosting a number of discussions: from software to
philosophy, from science fiction to politics.
• Politics was the biggest discussion group
• So, politics is what we analyzed to find out:
– What users were thinking about a political issue
– Who was pro and who was con
– Who was an influencer
Copyright © 2014 KNIME.com AG 13
Copyright © 2014 KNIME.com AG 14
The Politics Group in the Slashdot DataSet
14
• 24 000 non anonymous users
• 496 posts
• 140 000 comments
• Most posts have around 200 comments
Copyright © 2014 KNIME.com AG 15
Copyright © 2014 KNIME.com AG 16
Text Analytics: Options
• Tag (Word) Clouds
• Topic Detection
• Topic Shift
• Sentiment Analysis
I find PRODUCT X to be very good and useful,
but it is a bit too expensive.
Copyright © 2014 KNIME.com AG 17
Text Analytics: Workflow
Document type
is required
Loading MPQA
Stanford dictionary for
sentiment attribute
Sumoffrequencies
ofpositiveand
negativewordsper
post/comment
SumofSumof
frequenciesofpositive
andnegativewordsper
user
ScatterPlots
andTagClouds
ReadData
Copyright © 2014 KNIME.com AG 18
Text Analytics: Results
Most negative
user pNutz
Most positive
and most
talkative user
dada21
Copyright © 2014 KNIME.com AG 19
Text Analytics: Open Questions
19
• Is dada21 an influencer?
• Is pNutz an influencer?
• Shall we take marketing actions about any of
them?
Copyright © 2014 KNIME.com AG 20
Copyright © 2014 KNIME.com AG 21
Network Mining: Options
• User Interaction Graph
• Influencers vs. Followers
• User Network Investigation
Copyright © 2014 KNIME.com AG 22
Network Mining: Workflow
Read Data
Create Empty
Network
Create
Network
Content
Extract
largest
sub-graph
Centrality Index for
authority score
Scatter Plots
Copyright © 2014 KNIME.com AG 23
Network Mining: Results
Dada21
Carl Bialik from the WSJ
Doc Ruby
Copyright © 2014 KNIME.com AG 24
Network Mining: Open Questions
24
• Is Carl Bialik from WSJ positive or negative about the
topic?
• Is dada21 positive or negative about the topic?
• What shall we do marketing-wise with non-
influencers such as doc Ruby?
Copyright © 2014 KNIME.com AG 25
Copyright © 2014 KNIME.com AG 26
Text Analytics and Network Mining: Workflow
Read Data
Network Mining
Sentiment Analysis
Joiner
Scatter Plots
Copyright © 2014 KNIME.com AG 27
Text Analytics and Network Mining: Results
pNutz
Carl Bialik
dada21
Doc Ruby
99BottlesOfBeerInMyF
WebHosting Guy
Tube Steak
Catbeller
from the WSJ
Copyright © 2014 KNIME.com AG 28
Text Analytics and Network Mining: Results
Copyright © 2014 KNIME.com AG 29
Copyright © 2014 KNIME.com AG 30
Conclusions
30
• Is Carl Bialik from WSJ is an influencer and …
neutral.
• Most influencers are actually neutral.
• Worth it keep informed
• dada21 is talking positively about each topic. Worth
it to pamper him/her.
• Of the negative talking users, pNutz though
obnoxious, is not the main worry. Catbeller is.
Copyright © 2014 KNIME.com AG 31
Where can I find all this?
White paper, Workflows, and Data is available on the
KNIME web site:
http://www.knime.com/white-papers (section Social
Media)
https://www.knime.org/files/knime_social_media_whit
e_paper.pdf
Copyright © 2014 KNIME.com AG 32
Resources
• KNIME (www.knime.org)
• BLOG for news, tips and tricks(www.knime.org/blog)
• FORUM for questions and answers (tech.knime.org/forum)
• EXAMPLE SERVER for example workflows
• LEARNING HUB (www.knime.org/learning-hub)
• KNIME TV channel on
• KNIME on @KNIME
• KNIME on
https://www.facebook.com/KNIMEanalytics
32
Copyright © 2014 KNIME.com AG 33
Thank You
Free Copy of KNIME Beginner’s Luck Book
at KNIME Press
https://www.knime.org/knimepress
Promotion Code:
ODSCLondonMeetup

More Related Content

PDF
Neo4j & fby presentation
PDF
Schneller Nutzen mit Neo4j: das Beispiel Panama Papers
PDF
Knime customer intelligence on social media: Text Analytics vs. Network Mining
PPTX
Univ. of AZ Global Racing Symposium 2015 - Digital Strategies
PDF
Just add Imagination
PDF
Social media analytics_itu_20120416
PPTX
Social Media Anlytics
PDF
Social CRM
Neo4j & fby presentation
Schneller Nutzen mit Neo4j: das Beispiel Panama Papers
Knime customer intelligence on social media: Text Analytics vs. Network Mining
Univ. of AZ Global Racing Symposium 2015 - Digital Strategies
Just add Imagination
Social media analytics_itu_20120416
Social Media Anlytics
Social CRM

Similar to Knime customer intelligence on social edia (20)

PPTX
Webinar Social Media Analytics - Using KNIME
PDF
DATACTIF SoNetA. BIG DATA ANALYTIS
PPTX
Social media & big data
PDF
El impacto del big data en la estrategia de los medios de comunicacion by Osc...
PDF
Extracting Truths From Social Media - KNIME Fall Summit 2016
PDF
Confessions of an Adapative Marketer Final PDF
PDF
SMA-Unit-I: The Foundation for Analytics
PDF
Knime social media_white_paper
PDF
Himc toolbox slides-petterw
PDF
Social media analytics - 5 key trends
PDF
Soneta. Social Network Analyzer
PPT
Óscar Méndez - Big data: de la investigación científica a la gestión empresarial
PDF
The Rise of Big Data and the Chief Data Officer (CDO)
PPTX
Taming the Data Lake with Scalable Metrics Model Framework
PPTX
Lecture 8 data continued, Content marketing, SEO and SMO overview
PPTX
Spark Social Media
PDF
What Big Data Means for PR and Why It Matters to Us
 
PPT
Gauging Consumer Behaviour via Social Analytics
PDF
Big Data Analytics PowerPoint Presentation Slides
PDF
Notes from the Observation Deck // A Data Revolution
Webinar Social Media Analytics - Using KNIME
DATACTIF SoNetA. BIG DATA ANALYTIS
Social media & big data
El impacto del big data en la estrategia de los medios de comunicacion by Osc...
Extracting Truths From Social Media - KNIME Fall Summit 2016
Confessions of an Adapative Marketer Final PDF
SMA-Unit-I: The Foundation for Analytics
Knime social media_white_paper
Himc toolbox slides-petterw
Social media analytics - 5 key trends
Soneta. Social Network Analyzer
Óscar Méndez - Big data: de la investigación científica a la gestión empresarial
The Rise of Big Data and the Chief Data Officer (CDO)
Taming the Data Lake with Scalable Metrics Model Framework
Lecture 8 data continued, Content marketing, SEO and SMO overview
Spark Social Media
What Big Data Means for PR and Why It Matters to Us
 
Gauging Consumer Behaviour via Social Analytics
Big Data Analytics PowerPoint Presentation Slides
Notes from the Observation Deck // A Data Revolution
Ad

More from Sheamus McGovern (8)

PDF
Schierz ODSC Meetup pdf
PDF
Jon Sedar Topic Modelling
PDF
Forensic linguistics with Apache Spark
PDF
Boris IoT slides
PDF
Deep Learning Frameworks slides
PDF
Transfer Wise Data Talk 2
PDF
Ajit jaokar slides
PDF
Ian Huston - "Deploying your data driven web app on Cloud Foundry"
Schierz ODSC Meetup pdf
Jon Sedar Topic Modelling
Forensic linguistics with Apache Spark
Boris IoT slides
Deep Learning Frameworks slides
Transfer Wise Data Talk 2
Ajit jaokar slides
Ian Huston - "Deploying your data driven web app on Cloud Foundry"
Ad

Recently uploaded (20)

PDF
Lecture1 pattern recognition............
PPTX
1_Introduction to advance data techniques.pptx
PPTX
oil_refinery_comprehensive_20250804084928 (1).pptx
PPT
Miokarditis (Inflamasi pada Otot Jantung)
PDF
“Getting Started with Data Analytics Using R – Concepts, Tools & Case Studies”
PDF
Fluorescence-microscope_Botany_detailed content
PPTX
Database Infoormation System (DBIS).pptx
PPTX
Business Acumen Training GuidePresentation.pptx
PDF
Mega Projects Data Mega Projects Data
PDF
Launch Your Data Science Career in Kochi – 2025
PPTX
CEE 2 REPORT G7.pptxbdbshjdgsgjgsjfiuhsd
PDF
Recruitment and Placement PPT.pdfbjfibjdfbjfobj
PPTX
Global journeys: estimating international migration
PPTX
DISORDERS OF THE LIVER, GALLBLADDER AND PANCREASE (1).pptx
PPTX
advance b rammar.pptxfdgdfgdfsgdfgsdgfdfgdfgsdfgdfgdfg
PPTX
iec ppt-1 pptx icmr ppt on rehabilitation.pptx
PPTX
IBA_Chapter_11_Slides_Final_Accessible.pptx
PDF
22.Patil - Early prediction of Alzheimer’s disease using convolutional neural...
PDF
TRAFFIC-MANAGEMENT-AND-ACCIDENT-INVESTIGATION-WITH-DRIVING-PDF-FILE.pdf
PPTX
Introduction to Knowledge Engineering Part 1
Lecture1 pattern recognition............
1_Introduction to advance data techniques.pptx
oil_refinery_comprehensive_20250804084928 (1).pptx
Miokarditis (Inflamasi pada Otot Jantung)
“Getting Started with Data Analytics Using R – Concepts, Tools & Case Studies”
Fluorescence-microscope_Botany_detailed content
Database Infoormation System (DBIS).pptx
Business Acumen Training GuidePresentation.pptx
Mega Projects Data Mega Projects Data
Launch Your Data Science Career in Kochi – 2025
CEE 2 REPORT G7.pptxbdbshjdgsgjgsjfiuhsd
Recruitment and Placement PPT.pdfbjfibjdfbjfobj
Global journeys: estimating international migration
DISORDERS OF THE LIVER, GALLBLADDER AND PANCREASE (1).pptx
advance b rammar.pptxfdgdfgdfsgdfgsdgfdfgdfgsdfgdfgdfg
iec ppt-1 pptx icmr ppt on rehabilitation.pptx
IBA_Chapter_11_Slides_Final_Accessible.pptx
22.Patil - Early prediction of Alzheimer’s disease using convolutional neural...
TRAFFIC-MANAGEMENT-AND-ACCIDENT-INVESTIGATION-WITH-DRIVING-PDF-FILE.pdf
Introduction to Knowledge Engineering Part 1

Knime customer intelligence on social edia

  • 1. Copyright © 2015 KNIME.com AG Customer Intelligence on Social Media Rosaria Silipo KNIME.com AG
  • 2. Copyright © 2014 KNIME.com AG 2
  • 3. Copyright © 2014 KNIME.com AG 3 The KNIME Platform: Open for Innovation Powerful: Legacy  Future Tools Collaborative: Scientists  Analysts Integrative: Legacy  Future Data Transparent: Existing  Future Expertise Agile: Internal  External Wisdom 3
  • 4. Copyright © 2014 KNIME.com AG 4 KNIME Analytics Platform 4
  • 5. Copyright © 2014 KNIME.com AG 5 NODES perform tasks on data Nodes are combined to create WORKFLOWS Status Visual KNIME Workflows Inputs Outputs Not Configured Idle Executed Error
  • 6. Copyright © 2014 KNIME.com AG 6 Statistics Data Mining Machine Learning Web Analytics Text Mining Network Analysis Social Media Analysis WEKA R Community / 3rd MySQL, Oracle, etc. SAS, SPSS, etc. Excel, Flat, etc. Hive etc. XML, PMML Text, Doc, Image Web Crawlers Industry Specific Community / 3rd ETL Row, Column Matrix Text, Image Time Series Java Python Community / 3rd Includes over 1000 native and embedded nodes via BIRT PMML XML Databases Excel, Flat, etc. Hive etc. Text, Doc, Image Industry Specific Community / 3rd 6
  • 7. Copyright © 2014 KNIME.com AG 7 Who’s Using KNIME? > 2,000,000 Downloads annually (in 2015) > 70,000 Individuals using KNIME > 5,000 Organizations using KNIME > 700 Customers paying for KNIME 7
  • 8. Copyright © 2014 KNIME.com AG 8 Top in User Satisfaction 2012 & 2013 Rexer Analytics Survey Users who know KNIME love it! 8 Open Source Overall
  • 9. Copyright © 2014 KNIME.com AG 9 KNIME Analytics Platform: Try it Now! 1. Download from www.knime.com 2. Browse the KNIME Learning Hub at www.knime.com/learning-hub 3. Check out KNIME Press “KNIME Beginner’s Guide” 4. Become active on our Forum!
  • 10. Copyright © 2014 KNIME.com AG 10
  • 11. Copyright © 2014 KNIME.com AG 11 The Problem A major European Telco 11 • Can you tell us what people say about our new product? • Can you tell us who is supporting the product and who trashing it? • Of those, can you tell us who is an influencer? Its Forum Site
  • 12. Copyright © 2014 KNIME.com AG 12 The Data 12 • The Data Set unfortunately cannot be shared • Slashdot Forum Data are! • Slashdot was a public forum built in 1997 and hosting a number of discussions: from software to philosophy, from science fiction to politics. • Politics was the biggest discussion group • So, politics is what we analyzed to find out: – What users were thinking about a political issue – Who was pro and who was con – Who was an influencer
  • 13. Copyright © 2014 KNIME.com AG 13
  • 14. Copyright © 2014 KNIME.com AG 14 The Politics Group in the Slashdot DataSet 14 • 24 000 non anonymous users • 496 posts • 140 000 comments • Most posts have around 200 comments
  • 15. Copyright © 2014 KNIME.com AG 15
  • 16. Copyright © 2014 KNIME.com AG 16 Text Analytics: Options • Tag (Word) Clouds • Topic Detection • Topic Shift • Sentiment Analysis I find PRODUCT X to be very good and useful, but it is a bit too expensive.
  • 17. Copyright © 2014 KNIME.com AG 17 Text Analytics: Workflow Document type is required Loading MPQA Stanford dictionary for sentiment attribute Sumoffrequencies ofpositiveand negativewordsper post/comment SumofSumof frequenciesofpositive andnegativewordsper user ScatterPlots andTagClouds ReadData
  • 18. Copyright © 2014 KNIME.com AG 18 Text Analytics: Results Most negative user pNutz Most positive and most talkative user dada21
  • 19. Copyright © 2014 KNIME.com AG 19 Text Analytics: Open Questions 19 • Is dada21 an influencer? • Is pNutz an influencer? • Shall we take marketing actions about any of them?
  • 20. Copyright © 2014 KNIME.com AG 20
  • 21. Copyright © 2014 KNIME.com AG 21 Network Mining: Options • User Interaction Graph • Influencers vs. Followers • User Network Investigation
  • 22. Copyright © 2014 KNIME.com AG 22 Network Mining: Workflow Read Data Create Empty Network Create Network Content Extract largest sub-graph Centrality Index for authority score Scatter Plots
  • 23. Copyright © 2014 KNIME.com AG 23 Network Mining: Results Dada21 Carl Bialik from the WSJ Doc Ruby
  • 24. Copyright © 2014 KNIME.com AG 24 Network Mining: Open Questions 24 • Is Carl Bialik from WSJ positive or negative about the topic? • Is dada21 positive or negative about the topic? • What shall we do marketing-wise with non- influencers such as doc Ruby?
  • 25. Copyright © 2014 KNIME.com AG 25
  • 26. Copyright © 2014 KNIME.com AG 26 Text Analytics and Network Mining: Workflow Read Data Network Mining Sentiment Analysis Joiner Scatter Plots
  • 27. Copyright © 2014 KNIME.com AG 27 Text Analytics and Network Mining: Results pNutz Carl Bialik dada21 Doc Ruby 99BottlesOfBeerInMyF WebHosting Guy Tube Steak Catbeller from the WSJ
  • 28. Copyright © 2014 KNIME.com AG 28 Text Analytics and Network Mining: Results
  • 29. Copyright © 2014 KNIME.com AG 29
  • 30. Copyright © 2014 KNIME.com AG 30 Conclusions 30 • Is Carl Bialik from WSJ is an influencer and … neutral. • Most influencers are actually neutral. • Worth it keep informed • dada21 is talking positively about each topic. Worth it to pamper him/her. • Of the negative talking users, pNutz though obnoxious, is not the main worry. Catbeller is.
  • 31. Copyright © 2014 KNIME.com AG 31 Where can I find all this? White paper, Workflows, and Data is available on the KNIME web site: http://www.knime.com/white-papers (section Social Media) https://www.knime.org/files/knime_social_media_whit e_paper.pdf
  • 32. Copyright © 2014 KNIME.com AG 32 Resources • KNIME (www.knime.org) • BLOG for news, tips and tricks(www.knime.org/blog) • FORUM for questions and answers (tech.knime.org/forum) • EXAMPLE SERVER for example workflows • LEARNING HUB (www.knime.org/learning-hub) • KNIME TV channel on • KNIME on @KNIME • KNIME on https://www.facebook.com/KNIMEanalytics 32
  • 33. Copyright © 2014 KNIME.com AG 33 Thank You Free Copy of KNIME Beginner’s Luck Book at KNIME Press https://www.knime.org/knimepress Promotion Code: ODSCLondonMeetup