Page 1
Copyr i g ht © 2016, SAS Ins t i tu t e Inc . A l l r ights reser ve d .
#SASFPT17
Text Analytics and Cognitive Science
SAS® FORUM
PORTUGAL 2017
Ricardo GalanteSenior Analytics Systems EngineerBusiness Analytics TeamSouthern Europe
[email protected] https://www.linkedin.com/in/ricardogalante/
Page 2
Copyr i g ht © 2016, SAS Ins t i tu t e Inc . A l l r ights reser ve d .
AGENDA
SAS Text
AnalyticsApplicationsText AnalyticsUnstructured Data
Page 3
Copyr i g ht © 2016, SAS Ins t i tu t e Inc . A l l r ights reser ve d .
#SASFPT17
Structured Data
Unstructured Data
Page 4
Copyr i g ht © 2016, SAS Ins t i tu t e Inc . A l l r ights reser ve d .
#SASFPT17
• emails,• electronic notes service,• sequence proteins,• social networking content,• blogs,• call center data,• medical diagnostics• product descriptions
• digital alerts,• financial applications, • videos,• photos,• information generated by sensors,• scientific papers,• judicial reports,• etc.
UNSTRUCTURED DATA
Page 5
Copyr i g ht © 2016, SAS Ins t i tu t e Inc . A l l r ights reser ve d .
#SASFPT17
A LOT OF SOURCES OF UNSTRUCTURED INFORMATION
Page 6
Copyr i g ht © 2016, SAS Ins t i tu t e Inc . A l l r ights reser ve d .
COMMON QUESTIONS ABOUT UNSTRUCTURED DATA
How can I organize my
documents?
Automatic classification.
Are there hidden insights within text data
sources that can help my organization?
Such as call center notes, emails, news, online
forums, social media…
How can I leverage on both
unstructured and structured
data sources?
Customer data + Customer
feedback?
How can I extract as much information as possible from textual data?
Can I also use text data
to analyze and
predict the future?
To reduce churn, improve sales,
reduce costs…
Page 7
Copyr i g ht © 2016, SAS Ins t i tu t e Inc . A l l r ights reser ve d .
Text Analytics
Page 8
Copyr i g ht © 2016, SAS Ins t i tu t e Inc . A l l r ights reser ve d .
Natural Language
Processing
Context
JL
Machine Learning
H
Discovery
Human Input
Topics, Insights,Relationships, Taxonomies,
Scored Documents
Unstructured Text Data
Operations
Further
Analysis
Page 9
Copyr i g ht © 2016, SAS Ins t i tu t e Inc . A l l r ights reser ve d .
Applications
Page 10
Copyr i g ht © 2016, SAS Ins t i tu t e Inc . A l l r ights reser ve d .
Analyzing for Suspicious Activity
Page 11
Copyr i g ht © 2016, SAS Ins t i tu t e Inc . A l l r ights reser ve d .
Analyzing for Suspicious Activity
Page 12
Copyr i g ht © 2016, SAS Ins t i tu t e Inc . A l l r ights reser ve d .
Call Center
Insight(predict report advise code)
NLP Analytics
NLI
Voice/Text
Data
NLG
Page 13
Copyr i g ht © 2016, SAS Ins t i tu t e Inc . A l l r ights reser ve d .
DATA
IMAGE PROCESSING
Discovery Deployment
Page 14
Copyr i g ht © 2016, SAS Ins t i tu t e Inc . A l l r ights reser ve d .
SAS Text Analytics
Page 15
15Copyright © 2012, SAS Institute Inc. All rights reserved.
MINERÍA DE TEXTOS
INTEGRATED
ANALYTICS
Explore textual data to
uncover valuable patterns,
themes, and insights
Integrate structured and
unstructured data for
enhanced:
• Forecasting
• Optimization
• Predictive Modeling
• Network Analysis
SAS® Text
Analytics
SAS TEXT ANALYTICS
• Information Retrieval
• Automatic Topic
Detection
• Content Categorization
• Entity Extraction
• Sentiment Analysis
SAS® Contextual Analysis
SAS® Text Miner
* SAS® Visual Text Analytics
Page 16
Copyr i g ht © 2016, SAS Ins t i tu t e Inc . A l l r ights reser ve d .
Business knowledge
Text mining
and
exploration
Standard
Reports
Predictive
Modeling
SAS
Solutions
UnstructuredData
Categories
Sentiment
Enriched
Dataset
Ad Hoc
Analysis
TEXT ANALYTICS – FLOW ANALYSIS AND TECHNIQUES
Entities
Page 17
Copyr i g ht © 2016, SAS Ins t i tu t e Inc . A l l r ights reser ve d .
SAS TEXT MINER
Page 18
Copyright © SAS Inst i tute Inc. Al l r ights reserv ed.
THANK YOU for your Attention
Ricardo GalanteSenior Analytics Systems EngineerBusiness Analytics TeamSAS Iberia
[email protected] https://www.linkedin.com/in/ricardogalante/