Integrate the most
advanced text analytics into
your predictive models.
April 27th, 2017
Webinar
MeaningCloud Extension for RapidMiner
Before we get started…
Presenter
How to participate
• Send questions with the chat feature, or
• Click the “Raise your hand” button to speak
and we’ll enable your mic
• Afterwards, you’ll be able to access a recording of the
webinar and its contents as tutorials on our blog
Antonio Matarranz
CMO
MeaningCloud Extension for RapidMiner
The purpose of this webinar…
To learn how to combine
text and data in advanced
analytical models
MeaningCloud Extension for RapidMiner
Agenda
 Analytics platforms. Introduction to RapidMiner
 Text analytics. Introduction to MeaningCloud
 Combining text and data analytics. MeaningCloud
Extension for RapidMiner
 Practical case demo
 Application scenarios
 How this Extension is different
 Product roadmap
 Conclusions and Q&A
MeaningCloud Extension for RapidMiner
Data Prep
Speed and optimize all data
exploration, blending and
cleansing tasks
Operationalize
Easily deploy and
maintain models and
embed analytic results
Model & Validate
Apply machine learning to rapidly
prototype and confidently
validate predictive models
Embed results in
all types of
business apps and
data visualization
tools
Incorporate all
types of data
ACCELERATES TIME TO VALUE
Integrated analytics platforms
MeaningCloud Extension for RapidMiner
RapidMiner Studio
MeaningCloud Extension for RapidMiner
RapidMiner Studio
Access to Data and
Processes
All kind of Operators,
including 129 for
Modelling
MeaningCloud Extension for RapidMiner
Deploy
• High velocity scoring
• APIs to deploy your predictive
results into the broadest array of
business applications, e.g.,
Salesforce, Marketo, Tableau
• Lightning-fast creation of web-
based reports
• Model monitoring tools to
ensure continued performance
4
Prep Data
• Access all types of data:
structured, unstructured and
Big Data sources
• Interactive data visualizations.
Anomaly & outlier detection
• Normalization & standardization
• Dimension reduction / feature
selection
1
Validate
• Breadth of validation schemes
• Cross-validation
• Visual evaluation
• Honest validation
• Encapsulate data prep,
modeling into validation
• Model performance metrics
• Cluster performance measures
3
Model
• Statistical & machine learning
• Predictive modeling
• Segmentation & clustering
• Association mining
• Similarity computation
• Feature weighting
• Model, parameter & features
optimization
2
Ability to visually execute
your entire Predictive
Analytics workflow in a
single place
Mainly focused on
structured data
RapidMiner Studio
MeaningCloud Extension for RapidMiner
Why should we be using text analytics?
Structured data
Unstructured
content
MeaningCloud Extension for RapidMiner
Opinions
Facts
Concepts
Organizations
People
Semantic
Analysis
Relationships
Themes
Text analytics
Extract meaning and actionable insights from unstructured content
Automation of costly manual activities
MeaningCloud Extension for RapidMiner
MeaningCloud: “Meaning as a Service”
(SaaS and on-premises)
Sign up and use it for FREE at
http://www.meaningcloud.com
MeaningCloud Extension for RapidMiner
MeaningCloud’s APIs
Identifies occurrences of
names of people,
organizations, abstract
concepts, quantities, etc.
Theme classification
according to
predefined taxonomies
Identifies general and
attribute-level polarity
Distinguishes among 60
languages
Performs detailed morphosyntactic
analysis
Evaluates the impact of
opinions on several
reputational axes
Discovers meaningful topics
and similarities among texts
without relying on predefined
taxonomies
MeaningCloud Extension for RapidMiner
Add-in for Excel
 An experience fully integrated into Excel
 Easy to use - No programming!
 The most convenient way to evaluate, prototype, and use MeaningCloud
13
MeaningCloud Extension for RapidMiner
MeaningCloud Customization Tools
MeaningCloud Extension for RapidMiner
MeaningCloud Extension for RapidMiner
Integrating the most advanced text analytics into RapidMiner
Download it here
MeaningCloud Extension for RapidMiner
MeaningCloud Extension for RapidMiner
Combine text analytics and
structured data in powerful
predictive models
Operators for
• Topics Extraction
• Text Classification
• Sentiment Analysis
• Lemmatization
Access to personal
resources created with
Customization Tools
MeaningCloud Extension for RapidMiner
PRACTICAL CASE
MeaningCloud Extension for RapidMiner
Analysis of comments from Amazon
Data: 1,500 food reviews from Amazon (vía Kaggle)
Structured data Unstructured text
MeaningCloud Extension for RapidMiner
Questions we would like to ask
Is there any (co)relation between Score and Sentiment?
1 2 3 4 5
Score
P+ → 5
P → 4
Sentiment NEU → 3
N → 2
N+ → 1
MeaningCloud Extension for RapidMiner
What (co)relation exists between Score and Sentiment?
Correlation Score – Polarity
MeaningCloud Extension for RapidMiner
Questions we would like to ask
Which attributes have the biggest impact on sentiment?
Predictive analytics
Model: factors that
predict sentiment
f(Atr1, Atr2, Atr3,…)
Texto Atr1 Atr2 Atr3 … Sentim
This … 1 0 1 … P
I am … 0 1 1 … N
… … … … … …
Texto Atr1 Atr2 Atr3 … Sentim
Your … 0 1 0 … N
Today… 1 0 0 … P
… … … … … …
Texto Atr1 Atr2 Atr3 … Sentim Pred
Your … 0 1 0 … N N
Today… 1 0 0 … P NEU
… … … … … …
Training set
Test set
MeaningCloud Extension for RapidMiner
Which attributes have the biggest impact on sentiment?
Rule model
if HelpfulnessDenominator ≤ 0.500 and con_food ≤ 0.500 then positive (39 / 339 / 39)
if con_product ≤ 0.500 and HelpfulnessNumerator > 1.500 and ent_tea > 0.500 then positive (1 / 25 / 2)
if con_$ ≤ 0.500 and HelpfulnessNumerator > 0.500 and con_mistake ≤ 0.500 then positive (49 / 340 / 52)
if HelpfulnessNumerator ≤ 0.500 and HelpfulnessDenominator ≤ 5 and con_chip ≤ 0.500 and con_restaurant ≤ 0.500 and
con_beef ≤ 0.500 and ent_Science ≤ 0.500 and con_baby ≤ 0.500 and con_world ≤ 0.500 and con_pill ≤ 0.500 and
ent_Food_and_Drug_Administration ≤ 0.500 and ent_HAM_Base ≤ 0.500 and con_consumer ≤ 0.500 and con_book
≤ 0.500 then positive (8 / 74 / 3)
if con_snack > 0.500 then positive (0 / 3 / 0)
if HelpfulnessDenominator > 11.500 and HelpfulnessNumerator > 13 then neutral (3 / 1 / 0)
if HelpfulnessDenominator > 4.500 and HelpfulnessDenominator ≤ 7.500 then negative (0 / 0 / 3)
if con_can > 0.500 and con_scratch ≤ 0.500 then positive (0 / 3 / 0)
if HelpfulnessNumerator ≤ 2.500 and con_baby ≤ 0.500 then neutral (13 / 6 / 10)
if HelpfulnessNumerator ≤ 9 then positive (2 / 7 / 2)
else negative (0 / 0 / 1)
correct: 811 out of 1025 training examples.
MeaningCloud Extension for RapidMiner
Which attributes have the biggest impact on sentiment?
Performance Vector
MeaningCloud Extension for RapidMiner
OTHER FEATURES AND
APPLICATIONS OF THE EXTENSION
MeaningCloud Extension for RapidMiner
Combining data and unstructured information
Customer data
Consumption /
use activity
Interactions /
incidents
Social
comments
Predictive analytics
More actionable
insights
Increased
predictive capacity
Model: factors
that predict
variables
Enriching models purely based on structured data
MeaningCloud Extension for RapidMiner
Application scenarios
Root cause analysis Fraud & churn prevention
Segmentation, targeting &
scoring People analytics
MeaningCloud Extension for RapidMiner
Opinions
The sentence “The
highest interest rate in
industry!” is…
 Positive, if talking
about savings
 Negative, if talking
about mortgages
Customized linguistic resources improve accuracy
Mentions
 Names of banks and
financial companies,
e.g., JPMorgan, BNP
Paribas, Citibank
 Product names, e.g.,
Your Way Account.
Compass Account…
Themes
Example: analysis of bank’s customer opinions
Products
Accounts
Checking
Savings
Borrowing
Credit
Mortgage
Channel
Office
Phone
Internet
MeaningCloud Extension for RapidMiner
Customization tools
 Create your own dictionaries, classification
models, and sentiment analysis
 Graphical user interface - no programming!
 Improve precision & recall
Learn more about customization in this webinar
MeaningCloud Extension for RapidMiner
A view into the future
 Usability
 URL parameter
 Documents: creation and file
parameter
 Language identification
 Aspect-based sentiment analysis
 PoS (Part of Speech) tagging
 Text clustering
 User profiling
 Vertical packs, e.g., banking, health
 Emotion detection
 Intent detection
Q2 2017 Q3 2017 Q4 2017 Q1 2018 Q2 2018
Roadmap MeaningCloud Extension for RapidMiner
GA
MeaningCloud Extension for RapidMiner
In conclusion
Close integration between
RapidMiner and MeaningCloud
 For RapidMiner users
 For MeaningCloud users
Data + text combination
boost model value
MeaningCloud Extension for RapidMiner
Q & A
MeaningCloud Extension for RapidMiner
Stay tuned to our emails and blog
We’ll be posting a recording of the webinar and
its contents as tutorials soon
MeaningCloud Extension for RapidMiner
Thank you for your attention!
 MeaningCloud LLC
54 W. 40th St.
New York, NY 10018
+1 (646) 403-3104
 MeaningCloud Europe SL
Llano Castellano 13
28034 Madrid (Spain)
+34 91 3324301
sales@meaningcloud.com
support@meaningcloud.com
http://www.meaningcloud.com
@MeaningCloud
https://www.linkedin.com/company/meaningcloud

Integrate the most advanced text analytics into your predictive models - MeaningCloud webinar

  • 1.
    Integrate the most advancedtext analytics into your predictive models. April 27th, 2017 Webinar
  • 2.
    MeaningCloud Extension forRapidMiner Before we get started… Presenter How to participate • Send questions with the chat feature, or • Click the “Raise your hand” button to speak and we’ll enable your mic • Afterwards, you’ll be able to access a recording of the webinar and its contents as tutorials on our blog Antonio Matarranz CMO
  • 3.
    MeaningCloud Extension forRapidMiner The purpose of this webinar… To learn how to combine text and data in advanced analytical models
  • 4.
    MeaningCloud Extension forRapidMiner Agenda  Analytics platforms. Introduction to RapidMiner  Text analytics. Introduction to MeaningCloud  Combining text and data analytics. MeaningCloud Extension for RapidMiner  Practical case demo  Application scenarios  How this Extension is different  Product roadmap  Conclusions and Q&A
  • 5.
    MeaningCloud Extension forRapidMiner Data Prep Speed and optimize all data exploration, blending and cleansing tasks Operationalize Easily deploy and maintain models and embed analytic results Model & Validate Apply machine learning to rapidly prototype and confidently validate predictive models Embed results in all types of business apps and data visualization tools Incorporate all types of data ACCELERATES TIME TO VALUE Integrated analytics platforms
  • 6.
    MeaningCloud Extension forRapidMiner RapidMiner Studio
  • 7.
    MeaningCloud Extension forRapidMiner RapidMiner Studio Access to Data and Processes All kind of Operators, including 129 for Modelling
  • 8.
    MeaningCloud Extension forRapidMiner Deploy • High velocity scoring • APIs to deploy your predictive results into the broadest array of business applications, e.g., Salesforce, Marketo, Tableau • Lightning-fast creation of web- based reports • Model monitoring tools to ensure continued performance 4 Prep Data • Access all types of data: structured, unstructured and Big Data sources • Interactive data visualizations. Anomaly & outlier detection • Normalization & standardization • Dimension reduction / feature selection 1 Validate • Breadth of validation schemes • Cross-validation • Visual evaluation • Honest validation • Encapsulate data prep, modeling into validation • Model performance metrics • Cluster performance measures 3 Model • Statistical & machine learning • Predictive modeling • Segmentation & clustering • Association mining • Similarity computation • Feature weighting • Model, parameter & features optimization 2 Ability to visually execute your entire Predictive Analytics workflow in a single place Mainly focused on structured data RapidMiner Studio
  • 9.
    MeaningCloud Extension forRapidMiner Why should we be using text analytics? Structured data Unstructured content
  • 10.
    MeaningCloud Extension forRapidMiner Opinions Facts Concepts Organizations People Semantic Analysis Relationships Themes Text analytics Extract meaning and actionable insights from unstructured content Automation of costly manual activities
  • 11.
    MeaningCloud Extension forRapidMiner MeaningCloud: “Meaning as a Service” (SaaS and on-premises) Sign up and use it for FREE at http://www.meaningcloud.com
  • 12.
    MeaningCloud Extension forRapidMiner MeaningCloud’s APIs Identifies occurrences of names of people, organizations, abstract concepts, quantities, etc. Theme classification according to predefined taxonomies Identifies general and attribute-level polarity Distinguishes among 60 languages Performs detailed morphosyntactic analysis Evaluates the impact of opinions on several reputational axes Discovers meaningful topics and similarities among texts without relying on predefined taxonomies
  • 13.
    MeaningCloud Extension forRapidMiner Add-in for Excel  An experience fully integrated into Excel  Easy to use - No programming!  The most convenient way to evaluate, prototype, and use MeaningCloud 13
  • 14.
    MeaningCloud Extension forRapidMiner MeaningCloud Customization Tools
  • 15.
    MeaningCloud Extension forRapidMiner MeaningCloud Extension for RapidMiner Integrating the most advanced text analytics into RapidMiner Download it here
  • 16.
    MeaningCloud Extension forRapidMiner MeaningCloud Extension for RapidMiner Combine text analytics and structured data in powerful predictive models Operators for • Topics Extraction • Text Classification • Sentiment Analysis • Lemmatization Access to personal resources created with Customization Tools
  • 17.
    MeaningCloud Extension forRapidMiner PRACTICAL CASE
  • 18.
    MeaningCloud Extension forRapidMiner Analysis of comments from Amazon Data: 1,500 food reviews from Amazon (vía Kaggle) Structured data Unstructured text
  • 19.
    MeaningCloud Extension forRapidMiner Questions we would like to ask Is there any (co)relation between Score and Sentiment? 1 2 3 4 5 Score P+ → 5 P → 4 Sentiment NEU → 3 N → 2 N+ → 1
  • 20.
    MeaningCloud Extension forRapidMiner What (co)relation exists between Score and Sentiment? Correlation Score – Polarity
  • 21.
    MeaningCloud Extension forRapidMiner Questions we would like to ask Which attributes have the biggest impact on sentiment? Predictive analytics Model: factors that predict sentiment f(Atr1, Atr2, Atr3,…) Texto Atr1 Atr2 Atr3 … Sentim This … 1 0 1 … P I am … 0 1 1 … N … … … … … … Texto Atr1 Atr2 Atr3 … Sentim Your … 0 1 0 … N Today… 1 0 0 … P … … … … … … Texto Atr1 Atr2 Atr3 … Sentim Pred Your … 0 1 0 … N N Today… 1 0 0 … P NEU … … … … … … Training set Test set
  • 22.
    MeaningCloud Extension forRapidMiner Which attributes have the biggest impact on sentiment? Rule model if HelpfulnessDenominator ≤ 0.500 and con_food ≤ 0.500 then positive (39 / 339 / 39) if con_product ≤ 0.500 and HelpfulnessNumerator > 1.500 and ent_tea > 0.500 then positive (1 / 25 / 2) if con_$ ≤ 0.500 and HelpfulnessNumerator > 0.500 and con_mistake ≤ 0.500 then positive (49 / 340 / 52) if HelpfulnessNumerator ≤ 0.500 and HelpfulnessDenominator ≤ 5 and con_chip ≤ 0.500 and con_restaurant ≤ 0.500 and con_beef ≤ 0.500 and ent_Science ≤ 0.500 and con_baby ≤ 0.500 and con_world ≤ 0.500 and con_pill ≤ 0.500 and ent_Food_and_Drug_Administration ≤ 0.500 and ent_HAM_Base ≤ 0.500 and con_consumer ≤ 0.500 and con_book ≤ 0.500 then positive (8 / 74 / 3) if con_snack > 0.500 then positive (0 / 3 / 0) if HelpfulnessDenominator > 11.500 and HelpfulnessNumerator > 13 then neutral (3 / 1 / 0) if HelpfulnessDenominator > 4.500 and HelpfulnessDenominator ≤ 7.500 then negative (0 / 0 / 3) if con_can > 0.500 and con_scratch ≤ 0.500 then positive (0 / 3 / 0) if HelpfulnessNumerator ≤ 2.500 and con_baby ≤ 0.500 then neutral (13 / 6 / 10) if HelpfulnessNumerator ≤ 9 then positive (2 / 7 / 2) else negative (0 / 0 / 1) correct: 811 out of 1025 training examples.
  • 23.
    MeaningCloud Extension forRapidMiner Which attributes have the biggest impact on sentiment? Performance Vector
  • 24.
    MeaningCloud Extension forRapidMiner OTHER FEATURES AND APPLICATIONS OF THE EXTENSION
  • 25.
    MeaningCloud Extension forRapidMiner Combining data and unstructured information Customer data Consumption / use activity Interactions / incidents Social comments Predictive analytics More actionable insights Increased predictive capacity Model: factors that predict variables Enriching models purely based on structured data
  • 26.
    MeaningCloud Extension forRapidMiner Application scenarios Root cause analysis Fraud & churn prevention Segmentation, targeting & scoring People analytics
  • 27.
    MeaningCloud Extension forRapidMiner Opinions The sentence “The highest interest rate in industry!” is…  Positive, if talking about savings  Negative, if talking about mortgages Customized linguistic resources improve accuracy Mentions  Names of banks and financial companies, e.g., JPMorgan, BNP Paribas, Citibank  Product names, e.g., Your Way Account. Compass Account… Themes Example: analysis of bank’s customer opinions Products Accounts Checking Savings Borrowing Credit Mortgage Channel Office Phone Internet
  • 28.
    MeaningCloud Extension forRapidMiner Customization tools  Create your own dictionaries, classification models, and sentiment analysis  Graphical user interface - no programming!  Improve precision & recall Learn more about customization in this webinar
  • 29.
    MeaningCloud Extension forRapidMiner A view into the future  Usability  URL parameter  Documents: creation and file parameter  Language identification  Aspect-based sentiment analysis  PoS (Part of Speech) tagging  Text clustering  User profiling  Vertical packs, e.g., banking, health  Emotion detection  Intent detection Q2 2017 Q3 2017 Q4 2017 Q1 2018 Q2 2018 Roadmap MeaningCloud Extension for RapidMiner GA
  • 30.
    MeaningCloud Extension forRapidMiner In conclusion Close integration between RapidMiner and MeaningCloud  For RapidMiner users  For MeaningCloud users Data + text combination boost model value
  • 31.
  • 32.
    MeaningCloud Extension forRapidMiner Stay tuned to our emails and blog We’ll be posting a recording of the webinar and its contents as tutorials soon
  • 33.
    MeaningCloud Extension forRapidMiner Thank you for your attention!  MeaningCloud LLC 54 W. 40th St. New York, NY 10018 +1 (646) 403-3104  MeaningCloud Europe SL Llano Castellano 13 28034 Madrid (Spain) +34 91 3324301 sales@meaningcloud.com support@meaningcloud.com http://www.meaningcloud.com @MeaningCloud https://www.linkedin.com/company/meaningcloud