SlideShare a Scribd company logo
Copyright © 2015 KNIME.com AG
Customer Intelligence on Social
Media
Kilian Thiel
Tobias Koetter
Phil Winters
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
The KNIME Analytics Platform
4
Copyright © 2014 KNIME.com AG 5
Statistics
Data Mining
Machine Learning
Web Analytics
Text Mining
Network Analysis
Social Media Analysis
WEKA
R
JFreeChart
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
via BIRT
PMML
XML
Databases
Excel, Flat, etc.
Hive etc.
Spark
Text, Doc, Image
Industry Specific
Community / 3rd
Over 1000 native and embedded nodes included:
5
Copyright © 2014 KNIME.com AG 9
Top in User Satisfaction
2012 & 2013 Rexer Analytics Survey
Users who know KNIME love it!
9
Open Source
Overall
Copyright © 2014 KNIME.com AG 11
Copyright © 2014 KNIME.com AG 12
The Problem
A major European Telco
12
• 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 13
The Data
13
• 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 14
Copyright © 2014 KNIME.com AG 15
The Politics Group in the Slashdot DataSet
15
• 24 000 non anonymous users
• 496 posts
• 140 000 comments
• Most posts have around 200 comments
Copyright © 2014 KNIME.com AG 16
Copyright © 2014 KNIME.com AG 17
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 18
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 19
Text Analytics: Results
Most negative
user pNutz
Most positive
and most
talkative user
dada21
Copyright © 2014 KNIME.com AG 20
Text Analytics: Open Questions
20
• Is dada21 an influencer?
• Is pNutz an influencer?
• Shall we take marketing actions about any of
them?
Copyright © 2014 KNIME.com AG 21
Copyright © 2014 KNIME.com AG 22
Network Mining: Options
• User Interaction Graph
• Influencers vs. Followers
• User Network Investigation
Copyright © 2014 KNIME.com AG 23
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 24
Network Mining: Results
Dada21
Carl Bialik from the WSJ
Doc Ruby
Copyright © 2014 KNIME.com AG 25
Network Mining: Open Questions
25
• 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 26
Copyright © 2014 KNIME.com AG 27
Text Analytics and Network Mining: Workflow
Read Data
Network Mining
Sentiment Analysis
Joiner
Scatter Plots
Copyright © 2014 KNIME.com AG 28
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 29
Text Analytics and Network Mining: Results
Copyright © 2014 KNIME.com AG 30
Copyright © 2014 KNIME.com AG 31
Conclusions
31
• 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 32
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 33
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
33

More Related Content

PDF
Sentiment Analysis with KNIME Analytics Platform
PPTX
Transforming KNIME Consumer Data into Actionable Insights
PDF
KNIME Data Science Learnathon: From Raw Data To Deployment
PDF
KNIME Software Overview
PDF
Sentiment Analysis with Deep Learning, Machine Learning or Lexicon based
PDF
Knime & bioinformatics
PPT
PDF
Chemistry Data Basics with KNIME Analytics Platform
Sentiment Analysis with KNIME Analytics Platform
Transforming KNIME Consumer Data into Actionable Insights
KNIME Data Science Learnathon: From Raw Data To Deployment
KNIME Software Overview
Sentiment Analysis with Deep Learning, Machine Learning or Lexicon based
Knime & bioinformatics
Chemistry Data Basics with KNIME Analytics Platform

What's hot (20)

PDF
Big Data as easy as 1, 2, 3, ... 4 ... with KNIME
PDF
What's New in KNIME Analytics Platform 4.0 and KNIME Server 4.9
PPTX
From Raw Data to Deployment
PDF
Sharing and Deploying Data Science with KNIME Server
PDF
Heterogeneous Data Mining with Spark
PDF
Knime customer intelligence on social media odsc london
PDF
What's New in KNIME Analytics Platform 4.1
PPTX
Introduction to knime
PDF
Text Processing with KNIME
PDF
Creating a customer segmentation workflow with knime
PDF
R, Spark, Tensorflow, H20.ai Applied to Streaming Analytics
PDF
Flink London meetup 3 March 2016 - Flink basics
PDF
Twitter analytics in Bluemix
PDF
Is it harder to find a taxi when it is raining?
PDF
KNIME - Create Workflow with KNIME
PPTX
Building A Self Service Streaming Platform at Pinterest - Steven Bairos-Novak...
PDF
II-SDV 2017: Search Technologies
PDF
Codeless Deep Learning for Language Modeling and Image Classification
PPTX
Janus graph lookingbackwardreachingforward
PDF
Gain Deep Visibility into APIs and Integrations with Anypoint Monitoring
Big Data as easy as 1, 2, 3, ... 4 ... with KNIME
What's New in KNIME Analytics Platform 4.0 and KNIME Server 4.9
From Raw Data to Deployment
Sharing and Deploying Data Science with KNIME Server
Heterogeneous Data Mining with Spark
Knime customer intelligence on social media odsc london
What's New in KNIME Analytics Platform 4.1
Introduction to knime
Text Processing with KNIME
Creating a customer segmentation workflow with knime
R, Spark, Tensorflow, H20.ai Applied to Streaming Analytics
Flink London meetup 3 March 2016 - Flink basics
Twitter analytics in Bluemix
Is it harder to find a taxi when it is raining?
KNIME - Create Workflow with KNIME
Building A Self Service Streaming Platform at Pinterest - Steven Bairos-Novak...
II-SDV 2017: Search Technologies
Codeless Deep Learning for Language Modeling and Image Classification
Janus graph lookingbackwardreachingforward
Gain Deep Visibility into APIs and Integrations with Anypoint Monitoring
Ad

Viewers also liked (20)

PDF
Advanced analytics for the Internet of Things. Restocking Rental Bike Stations
PPTX
The Actionable Guide to Doing Better Semantic Keyword Research #BrightonSEO (...
PDF
Big Data with KNIME is as easy as 1, 2, 3, ...4!
PPTX
Webinar Social Media Analytics - Using KNIME
PDF
Just add Imagination
PPTX
Sentiment analysis using naive bayes classifier
PPT
How Sentiment Analysis works
PDF
Introduction to Sentiment Analysis
PPTX
Tutorial of Sentiment Analysis
PPT
Opinion Mining Tutorial (Sentiment Analysis)
PDF
Sentiment Analysis of Twitter Data
PPTX
Veri madenciliği teknikleri ile öğrenci segmentasyonu
PDF
Comparing Machine Learning Algorithms in Text Mining
PPTX
Tiffany Iwantoro_Exchange Rate Directional Forecasting using Sentiment Analys...
PDF
Science Festival 2011 Programme
PDF
Multimodal opinion mining from social media
PDF
Social Data Sentiment Analysis
PPTX
A review of sentiment analysis approaches in big
PPTX
Sentiment Analysis Using Machine Learning
PDF
KNIME tutorial
Advanced analytics for the Internet of Things. Restocking Rental Bike Stations
The Actionable Guide to Doing Better Semantic Keyword Research #BrightonSEO (...
Big Data with KNIME is as easy as 1, 2, 3, ...4!
Webinar Social Media Analytics - Using KNIME
Just add Imagination
Sentiment analysis using naive bayes classifier
How Sentiment Analysis works
Introduction to Sentiment Analysis
Tutorial of Sentiment Analysis
Opinion Mining Tutorial (Sentiment Analysis)
Sentiment Analysis of Twitter Data
Veri madenciliği teknikleri ile öğrenci segmentasyonu
Comparing Machine Learning Algorithms in Text Mining
Tiffany Iwantoro_Exchange Rate Directional Forecasting using Sentiment Analys...
Science Festival 2011 Programme
Multimodal opinion mining from social media
Social Data Sentiment Analysis
A review of sentiment analysis approaches in big
Sentiment Analysis Using Machine Learning
KNIME tutorial
Ad

Similar to Knime customer intelligence on social media: Text Analytics vs. Network Mining (20)

PDF
Knime customer intelligence on social edia
PDF
Social media analytics_itu_20120416
PPTX
Univ. of AZ Global Racing Symposium 2015 - Digital Strategies
PPTX
Social media & big data
PDF
Knime social media_white_paper
PPTX
Social Media Anlytics
PDF
Social CRM
PDF
The Rise of Big Data and the Chief Data Officer (CDO)
PDF
Confessions of an Adapative Marketer Final PDF
PDF
El impacto del big data en la estrategia de los medios de comunicacion by Osc...
PPTX
Tech Trends - Social
PDF
Let’s talk about reproducible data analysis
PDF
What Big Data Means for PR and Why It Matters to Us
 
PPTX
Taming the Data Lake with Scalable Metrics Model Framework
PDF
Big Data, Big Deal: For Future Big Data Scientists
PPTX
McKinsey: Understanding shifts in consumer behavior
PDF
Big Data Analytics PowerPoint Presentation Slides
PPTX
2013 10 cu leeds school big data conference - bill jacobs - revolution analytics
PPT
Óscar Méndez - Big data: de la investigación científica a la gestión empresarial
PPTX
Spark Social Media
Knime customer intelligence on social edia
Social media analytics_itu_20120416
Univ. of AZ Global Racing Symposium 2015 - Digital Strategies
Social media & big data
Knime social media_white_paper
Social Media Anlytics
Social CRM
The Rise of Big Data and the Chief Data Officer (CDO)
Confessions of an Adapative Marketer Final PDF
El impacto del big data en la estrategia de los medios de comunicacion by Osc...
Tech Trends - Social
Let’s talk about reproducible data analysis
What Big Data Means for PR and Why It Matters to Us
 
Taming the Data Lake with Scalable Metrics Model Framework
Big Data, Big Deal: For Future Big Data Scientists
McKinsey: Understanding shifts in consumer behavior
Big Data Analytics PowerPoint Presentation Slides
2013 10 cu leeds school big data conference - bill jacobs - revolution analytics
Óscar Méndez - Big data: de la investigación científica a la gestión empresarial
Spark Social Media

More from KNIMESlides (12)

PDF
Automating Inferences out of Financial Data
PDF
Credit Card Fraud Detection Tutorial - KNIME Meetup Berlin 2020
PDF
Credit Card Fraud Detection Tutorial
PDF
Practicing Data Science: A Collection of Case Studies
PDF
Webinar: Behind the Scenes on Guided Analytics
PDF
KNIME Data Science Learnathon: From Raw Data To Deployment - Dublin - June 2019
PDF
Scoring Metrics for Classification Models
PDF
Open Source Story and what’s new in KNIME Software
PDF
Anomaly Detection - Discover unknown Frauds and Anomalies using Machine Learning
PDF
Guided Automation- A Blueprint for Interactive Automated Machine Learning
PDF
KNIME Data Science Learnathon: From Raw Data To Deployment - Paris - November...
PDF
From raw data to deployment
Automating Inferences out of Financial Data
Credit Card Fraud Detection Tutorial - KNIME Meetup Berlin 2020
Credit Card Fraud Detection Tutorial
Practicing Data Science: A Collection of Case Studies
Webinar: Behind the Scenes on Guided Analytics
KNIME Data Science Learnathon: From Raw Data To Deployment - Dublin - June 2019
Scoring Metrics for Classification Models
Open Source Story and what’s new in KNIME Software
Anomaly Detection - Discover unknown Frauds and Anomalies using Machine Learning
Guided Automation- A Blueprint for Interactive Automated Machine Learning
KNIME Data Science Learnathon: From Raw Data To Deployment - Paris - November...
From raw data to deployment

Recently uploaded (20)

PPT
Chapter 3 METAL JOINING.pptnnnnnnnnnnnnn
PPTX
DISORDERS OF THE LIVER, GALLBLADDER AND PANCREASE (1).pptx
PPTX
IBA_Chapter_11_Slides_Final_Accessible.pptx
PPTX
Major-Components-ofNKJNNKNKNKNKronment.pptx
PPTX
Moving the Public Sector (Government) to a Digital Adoption
PPTX
climate analysis of Dhaka ,Banglades.pptx
PPTX
Database Infoormation System (DBIS).pptx
PDF
BF and FI - Blockchain, fintech and Financial Innovation Lesson 2.pdf
PPT
Reliability_Chapter_ presentation 1221.5784
PDF
TRAFFIC-MANAGEMENT-AND-ACCIDENT-INVESTIGATION-WITH-DRIVING-PDF-FILE.pdf
PDF
168300704-gasification-ppt.pdfhghhhsjsjhsuxush
PPTX
Computer network topology notes for revision
PPT
Miokarditis (Inflamasi pada Otot Jantung)
PDF
Mega Projects Data Mega Projects Data
PPTX
Business Ppt On Nestle.pptx huunnnhhgfvu
PDF
“Getting Started with Data Analytics Using R – Concepts, Tools & Case Studies”
PPTX
Supervised vs unsupervised machine learning algorithms
PDF
Introduction to Business Data Analytics.
PPTX
STUDY DESIGN details- Lt Col Maksud (21).pptx
Chapter 3 METAL JOINING.pptnnnnnnnnnnnnn
DISORDERS OF THE LIVER, GALLBLADDER AND PANCREASE (1).pptx
IBA_Chapter_11_Slides_Final_Accessible.pptx
Major-Components-ofNKJNNKNKNKNKronment.pptx
Moving the Public Sector (Government) to a Digital Adoption
climate analysis of Dhaka ,Banglades.pptx
Database Infoormation System (DBIS).pptx
BF and FI - Blockchain, fintech and Financial Innovation Lesson 2.pdf
Reliability_Chapter_ presentation 1221.5784
TRAFFIC-MANAGEMENT-AND-ACCIDENT-INVESTIGATION-WITH-DRIVING-PDF-FILE.pdf
168300704-gasification-ppt.pdfhghhhsjsjhsuxush
Computer network topology notes for revision
Miokarditis (Inflamasi pada Otot Jantung)
Mega Projects Data Mega Projects Data
Business Ppt On Nestle.pptx huunnnhhgfvu
“Getting Started with Data Analytics Using R – Concepts, Tools & Case Studies”
Supervised vs unsupervised machine learning algorithms
Introduction to Business Data Analytics.
STUDY DESIGN details- Lt Col Maksud (21).pptx

Knime customer intelligence on social media: Text Analytics vs. Network Mining

  • 1. Copyright © 2015 KNIME.com AG Customer Intelligence on Social Media Kilian Thiel Tobias Koetter Phil Winters 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 The KNIME Analytics Platform 4
  • 5. Copyright © 2014 KNIME.com AG 5 Statistics Data Mining Machine Learning Web Analytics Text Mining Network Analysis Social Media Analysis WEKA R JFreeChart 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 via BIRT PMML XML Databases Excel, Flat, etc. Hive etc. Spark Text, Doc, Image Industry Specific Community / 3rd Over 1000 native and embedded nodes included: 5
  • 6. Copyright © 2014 KNIME.com AG 9 Top in User Satisfaction 2012 & 2013 Rexer Analytics Survey Users who know KNIME love it! 9 Open Source Overall
  • 7. Copyright © 2014 KNIME.com AG 11
  • 8. Copyright © 2014 KNIME.com AG 12 The Problem A major European Telco 12 • 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
  • 9. Copyright © 2014 KNIME.com AG 13 The Data 13 • 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
  • 10. Copyright © 2014 KNIME.com AG 14
  • 11. Copyright © 2014 KNIME.com AG 15 The Politics Group in the Slashdot DataSet 15 • 24 000 non anonymous users • 496 posts • 140 000 comments • Most posts have around 200 comments
  • 12. Copyright © 2014 KNIME.com AG 16
  • 13. Copyright © 2014 KNIME.com AG 17 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.
  • 14. Copyright © 2014 KNIME.com AG 18 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
  • 15. Copyright © 2014 KNIME.com AG 19 Text Analytics: Results Most negative user pNutz Most positive and most talkative user dada21
  • 16. Copyright © 2014 KNIME.com AG 20 Text Analytics: Open Questions 20 • Is dada21 an influencer? • Is pNutz an influencer? • Shall we take marketing actions about any of them?
  • 17. Copyright © 2014 KNIME.com AG 21
  • 18. Copyright © 2014 KNIME.com AG 22 Network Mining: Options • User Interaction Graph • Influencers vs. Followers • User Network Investigation
  • 19. Copyright © 2014 KNIME.com AG 23 Network Mining: Workflow Read Data Create Empty Network Create Network Content Extract largest sub-graph Centrality Index for authority score Scatter Plots
  • 20. Copyright © 2014 KNIME.com AG 24 Network Mining: Results Dada21 Carl Bialik from the WSJ Doc Ruby
  • 21. Copyright © 2014 KNIME.com AG 25 Network Mining: Open Questions 25 • 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?
  • 22. Copyright © 2014 KNIME.com AG 26
  • 23. Copyright © 2014 KNIME.com AG 27 Text Analytics and Network Mining: Workflow Read Data Network Mining Sentiment Analysis Joiner Scatter Plots
  • 24. Copyright © 2014 KNIME.com AG 28 Text Analytics and Network Mining: Results pNutz Carl Bialik dada21 Doc Ruby 99BottlesOfBeerInMyF WebHosting Guy Tube Steak Catbeller from the WSJ
  • 25. Copyright © 2014 KNIME.com AG 29 Text Analytics and Network Mining: Results
  • 26. Copyright © 2014 KNIME.com AG 30
  • 27. Copyright © 2014 KNIME.com AG 31 Conclusions 31 • 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.
  • 28. Copyright © 2014 KNIME.com AG 32 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
  • 29. Copyright © 2014 KNIME.com AG 33 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 33