SlideShare a Scribd company logo
1 of 4
Download to read offline
Sentra fact sheet



Introduction
Sentra is Zorallab’s advanced, highly granular sentiment & entity relation extraction and transaction
system. It is based on the emerging Sentic computing conceptual framework. Sentra is fully automated
comprising a large array of integrated, highly scalable techniques including; Artificial intelligence (AI),
Machine Learning (ML), Natural Language Processing (NLP) and Logic Programming techniques.
Sentra is able to generate highly structured, time-series transactions, in real-time, containing sentiment
analysis as applied to any set of entities and their relationships. It can do this using an unlimited num-
ber of unstructured data sources, (e.g. web sites, documents, blogs, on-line news, emails etc.)




What are sentiment transactions?
There are many systems that will analyse sentiment within text. However, whilst this can be useful, it
has limited value when using data for commercial or analytical applications. Just to know that an article
or blog entry is negative about its subject is not always sufficient to be really useful. This is best illus-
trated by an example.

Let’s take the statement:

      “Microsoft’s share performance has been disappointing this quarter, but the company’s
      flagship operating system, Windows 7.0, has been generally well received and is a big
      improvement”



               © Zorallabs 2012 all rights reserved
Sentra fact sheet


Is this positive or negative? Well, understandably, it is both. In order to analyse this properly we need
to understand the entities being discussed, their relationship and then the sentiment between them. In
other words, we need transactions that clearly structure WHO is saying WHAT about WHOM. This is
what Sentra does. This is what makes it different and uniquely powerful. So, to continue our example, in
analysing the above statement Sentra will generate the following transactions:


                                                           Article   TargetCom-
Date/Time   Author         Source           Source URL                            Event   Product       Sentiment
                                                           Ref       pany


 02/12/11   John Taylor    ABC News         www.abc.com/   11290     Microsoft    Share                 Negative
  09:35                                     a11223.htm                            price



 02/12/11   John Taylor    ABC News         www.abc.com/   11290     Microsoft            Windiws 7.0   Positive
  09:35                                     a11223.htm



Notice that Sentra understood that the word “company’s” refers to Microsoft and was able to understand
that Windows 7.0 is a product of a company called Microsoft.

Now let’s take the example:

      “Samsung states that its new B5029 model is far more flexible than Nokia’s S23”

This is more complex. Sentra would generate the following,


                                                           Article   TargetCom-
Date/Time   Author         Source           Source URL                            Event   Product       Sentiment
                                                           Ref       pany


 04/12/11   Mark Smith     FT               www.ft.com/    20993     Samsung      “> ”    B5029         Positive
  10:23                                     a5886.htm



 04/12/11   Mark Smith     FT               www.ft.com/    20993     Nokia        “<”     S23           Negative
  10:23                                     a5886.htm



Further, the relationship between products B5029 and S23 is understood and extracted as that of com-
petitive products.


Sentra even generates transactions when there is no news
In conjunction with aiHit technology, Sentra monitors millions of company websites and can see when
events/items change, e.g. product releases, changes of executives, customer announcements, partner
changes etc. As Sentra’s AI/ML engines understand the nature of each item, wherever they are located
on the web site, its is able automatically to generate “change event” transactions. For example,




               © Zorallabs 2012 all rights reserved
Sentra fact sheet



                                                                                 Previous
Date/Time   Entity Type    Company          Source URL   Event         Desc                    New Value
                                                                                 Value


 07/12/11   Person         New Wave         Newavw.com   Executive     CEO       Andrew        John Norton
  11:15                    Technology                    change                  Mavey



 07/12/11   Product        Genera           Genera.com   Product An-   V 4.0                   …
  11:16                                                  nouncement




How many sources can Sentra monitor?
Unlimited – Sentra already monitors and maintains a map of the entire WWW. So the number of
sources depends entirely on your monitoring requirements.


How frequently can Sentra update its data?
As often as required. Sentra can monitor sources in near real-time.


Does Sentra monitor only company data?
No. Sentra can monitor and extract transactions from any type of unstructured data. Sentra “under-
stands” many topics and industries including: Economics, Finance, Banking, Engineering, Computer
Science, Health Care, Pharmaceutical Industry, Telecommunication Industry, Politics, etc. Please con-
tact us for more details.


How is Sentra data supplied?
You can acquire Sentra time-series transactions and reference data via an API, (XML, JSON or other
format as required), via FTP or alternatively your Sentra system can be entirely hosted (SaaS) and acces-
sible via a number of query and analytical tools.


Sentiment Analysis has a reputation for not being very accurate, how does
Sentra perform?
To date, typical sentiment analysis engines are based primarily on statistical techniques. Most are not
granular, (i.e. they are article, not sentence level based), and do not understand “context” or “relation-
ships”. Typically they achieve accuracy rates below 70%. However, Sentra’s scalable Sentic Computing
based system is routinely delivering accuracy rates in excess of 85%-90%. This is equivalent to, (even
slightly in excess of), human performance.




               © Zorallabs 2012 all rights reserved
Sentra fact sheet



How much does Sentra cost?
There are no capital outlays. You pay only for initial setup and the number of sites and items/compa-
nies you monitor. Costs depend on the number of sites and frequency of update required. Please do not
hesitate to contact our sales office for a free quotation.


How quickly can I start?
Often, in as little as one week, depending on the sources and entities or fields you require. Typically you
would give us details of the sources you require and the fields/event/relationship types to be monitored.
We then provide a small, sample output for you to evaluate and then switch on your Sentra system. If
you require analysis of entities/relationships/events that we do not currently cover, then just provide us
with samples and we can evaluate and incorporate them into Sentra.


What next?
Simply contact our sales team and we would be deligheted to talk about your requirements.
sales@zorallabs.com




               © Zorallabs 2012 all rights reserved

More Related Content

Similar to Zoral Labs SENTRA presentation

2007 06 Xx Futuro Do Software Sbqs
2007 06 Xx Futuro Do Software Sbqs2007 06 Xx Futuro Do Software Sbqs
2007 06 Xx Futuro Do Software Sbqssrlm
 
Norfolk Intranet 2.0
Norfolk Intranet 2.0Norfolk Intranet 2.0
Norfolk Intranet 2.0djoneseaccess
 
Splunk live london_grs
Splunk live london_grsSplunk live london_grs
Splunk live london_grsjenny_splunk
 
harmon.ie Debuts Collage Press Release
harmon.ie Debuts Collage Press Releaseharmon.ie Debuts Collage Press Release
harmon.ie Debuts Collage Press ReleaseShawn Wiora
 
Big Data for Big Gains in Construction
Big Data for Big Gains in ConstructionBig Data for Big Gains in Construction
Big Data for Big Gains in ConstructionAPE Mobile
 
AWS re:Invent 2016: Delighting Customers Through Device Data with Salesforce ...
AWS re:Invent 2016: Delighting Customers Through Device Data with Salesforce ...AWS re:Invent 2016: Delighting Customers Through Device Data with Salesforce ...
AWS re:Invent 2016: Delighting Customers Through Device Data with Salesforce ...Amazon Web Services
 
MIN Sample - Dreamforce 2014
MIN Sample - Dreamforce 2014MIN Sample - Dreamforce 2014
MIN Sample - Dreamforce 2014Michael Levy
 
Being data driven - our data journey
Being data driven - our data journeyBeing data driven - our data journey
Being data driven - our data journeyIstván Rechner
 
You're Not Ready for Internal Cloud
You're Not Ready for Internal CloudYou're Not Ready for Internal Cloud
You're Not Ready for Internal CloudBMC Software
 
Emerging Prevalence of Data Streaming in Analytics and it's Business Signific...
Emerging Prevalence of Data Streaming in Analytics and it's Business Signific...Emerging Prevalence of Data Streaming in Analytics and it's Business Signific...
Emerging Prevalence of Data Streaming in Analytics and it's Business Signific...Amazon Web Services
 
The big shift 2011 07
The big shift 2011 07The big shift 2011 07
The big shift 2011 07Frank Bennett
 
CA CLOUD ACCELERATOR_Axway_Executive_Profile
CA CLOUD ACCELERATOR_Axway_Executive_ProfileCA CLOUD ACCELERATOR_Axway_Executive_Profile
CA CLOUD ACCELERATOR_Axway_Executive_ProfileAlan Taylor
 
Analytics as a Service in SL
Analytics as a Service in SLAnalytics as a Service in SL
Analytics as a Service in SLSkylabReddy Vanga
 
Splunk for IT Operations Breakout Session
Splunk for IT Operations Breakout SessionSplunk for IT Operations Breakout Session
Splunk for IT Operations Breakout SessionSplunk
 
Chatter &amp; Metrics March 2011
Chatter &amp;  Metrics    March 2011Chatter &amp;  Metrics    March 2011
Chatter &amp; Metrics March 2011Mark Moreno
 
SpectorSoft Spector 360 資料移失防護及網路活動監控軟體產品介紹及應用分析
SpectorSoft Spector 360 資料移失防護及網路活動監控軟體產品介紹及應用分析SpectorSoft Spector 360 資料移失防護及網路活動監控軟體產品介紹及應用分析
SpectorSoft Spector 360 資料移失防護及網路活動監控軟體產品介紹及應用分析Cheer Chain Enterprise Co., Ltd.
 

Similar to Zoral Labs SENTRA presentation (20)

2007 06 Xx Futuro Do Software Sbqs
2007 06 Xx Futuro Do Software Sbqs2007 06 Xx Futuro Do Software Sbqs
2007 06 Xx Futuro Do Software Sbqs
 
Norfolk Intranet 2.0
Norfolk Intranet 2.0Norfolk Intranet 2.0
Norfolk Intranet 2.0
 
Splunk live london_grs
Splunk live london_grsSplunk live london_grs
Splunk live london_grs
 
harmon.ie Debuts Collage Press Release
harmon.ie Debuts Collage Press Releaseharmon.ie Debuts Collage Press Release
harmon.ie Debuts Collage Press Release
 
NSW-IOT-Summit-July2018.pdf
NSW-IOT-Summit-July2018.pdfNSW-IOT-Summit-July2018.pdf
NSW-IOT-Summit-July2018.pdf
 
Big Data for Big Gains in Construction
Big Data for Big Gains in ConstructionBig Data for Big Gains in Construction
Big Data for Big Gains in Construction
 
AWS re:Invent 2016: Delighting Customers Through Device Data with Salesforce ...
AWS re:Invent 2016: Delighting Customers Through Device Data with Salesforce ...AWS re:Invent 2016: Delighting Customers Through Device Data with Salesforce ...
AWS re:Invent 2016: Delighting Customers Through Device Data with Salesforce ...
 
MIN Sample - Dreamforce 2014
MIN Sample - Dreamforce 2014MIN Sample - Dreamforce 2014
MIN Sample - Dreamforce 2014
 
Being data driven - our data journey
Being data driven - our data journeyBeing data driven - our data journey
Being data driven - our data journey
 
You're Not Ready for Internal Cloud
You're Not Ready for Internal CloudYou're Not Ready for Internal Cloud
You're Not Ready for Internal Cloud
 
Emerging Prevalence of Data Streaming in Analytics and it's Business Signific...
Emerging Prevalence of Data Streaming in Analytics and it's Business Signific...Emerging Prevalence of Data Streaming in Analytics and it's Business Signific...
Emerging Prevalence of Data Streaming in Analytics and it's Business Signific...
 
The big shift 2011 07
The big shift 2011 07The big shift 2011 07
The big shift 2011 07
 
Dreamforce 2015
Dreamforce 2015Dreamforce 2015
Dreamforce 2015
 
CA CLOUD ACCELERATOR_Axway_Executive_Profile
CA CLOUD ACCELERATOR_Axway_Executive_ProfileCA CLOUD ACCELERATOR_Axway_Executive_Profile
CA CLOUD ACCELERATOR_Axway_Executive_Profile
 
Bigdata notes
Bigdata notesBigdata notes
Bigdata notes
 
Analytics as a Service in SL
Analytics as a Service in SLAnalytics as a Service in SL
Analytics as a Service in SL
 
Splunk for IT Operations Breakout Session
Splunk for IT Operations Breakout SessionSplunk for IT Operations Breakout Session
Splunk for IT Operations Breakout Session
 
Chatter &amp; Metrics March 2011
Chatter &amp;  Metrics    March 2011Chatter &amp;  Metrics    March 2011
Chatter &amp; Metrics March 2011
 
SpectorSoft Spector 360 資料移失防護及網路活動監控軟體產品介紹及應用分析
SpectorSoft Spector 360 資料移失防護及網路活動監控軟體產品介紹及應用分析SpectorSoft Spector 360 資料移失防護及網路活動監控軟體產品介紹及應用分析
SpectorSoft Spector 360 資料移失防護及網路活動監控軟體產品介紹及應用分析
 
Dreamforce 2015
Dreamforce 2015Dreamforce 2015
Dreamforce 2015
 

Zoral Labs SENTRA presentation

  • 1. Sentra fact sheet Introduction Sentra is Zorallab’s advanced, highly granular sentiment & entity relation extraction and transaction system. It is based on the emerging Sentic computing conceptual framework. Sentra is fully automated comprising a large array of integrated, highly scalable techniques including; Artificial intelligence (AI), Machine Learning (ML), Natural Language Processing (NLP) and Logic Programming techniques. Sentra is able to generate highly structured, time-series transactions, in real-time, containing sentiment analysis as applied to any set of entities and their relationships. It can do this using an unlimited num- ber of unstructured data sources, (e.g. web sites, documents, blogs, on-line news, emails etc.) What are sentiment transactions? There are many systems that will analyse sentiment within text. However, whilst this can be useful, it has limited value when using data for commercial or analytical applications. Just to know that an article or blog entry is negative about its subject is not always sufficient to be really useful. This is best illus- trated by an example. Let’s take the statement: “Microsoft’s share performance has been disappointing this quarter, but the company’s flagship operating system, Windows 7.0, has been generally well received and is a big improvement” © Zorallabs 2012 all rights reserved
  • 2. Sentra fact sheet Is this positive or negative? Well, understandably, it is both. In order to analyse this properly we need to understand the entities being discussed, their relationship and then the sentiment between them. In other words, we need transactions that clearly structure WHO is saying WHAT about WHOM. This is what Sentra does. This is what makes it different and uniquely powerful. So, to continue our example, in analysing the above statement Sentra will generate the following transactions: Article TargetCom- Date/Time Author Source Source URL Event Product Sentiment Ref pany 02/12/11 John Taylor ABC News www.abc.com/ 11290 Microsoft Share Negative 09:35 a11223.htm price 02/12/11 John Taylor ABC News www.abc.com/ 11290 Microsoft Windiws 7.0 Positive 09:35 a11223.htm Notice that Sentra understood that the word “company’s” refers to Microsoft and was able to understand that Windows 7.0 is a product of a company called Microsoft. Now let’s take the example: “Samsung states that its new B5029 model is far more flexible than Nokia’s S23” This is more complex. Sentra would generate the following, Article TargetCom- Date/Time Author Source Source URL Event Product Sentiment Ref pany 04/12/11 Mark Smith FT www.ft.com/ 20993 Samsung “> ” B5029 Positive 10:23 a5886.htm 04/12/11 Mark Smith FT www.ft.com/ 20993 Nokia “<” S23 Negative 10:23 a5886.htm Further, the relationship between products B5029 and S23 is understood and extracted as that of com- petitive products. Sentra even generates transactions when there is no news In conjunction with aiHit technology, Sentra monitors millions of company websites and can see when events/items change, e.g. product releases, changes of executives, customer announcements, partner changes etc. As Sentra’s AI/ML engines understand the nature of each item, wherever they are located on the web site, its is able automatically to generate “change event” transactions. For example, © Zorallabs 2012 all rights reserved
  • 3. Sentra fact sheet Previous Date/Time Entity Type Company Source URL Event Desc New Value Value 07/12/11 Person New Wave Newavw.com Executive CEO Andrew John Norton 11:15 Technology change Mavey 07/12/11 Product Genera Genera.com Product An- V 4.0 … 11:16 nouncement How many sources can Sentra monitor? Unlimited – Sentra already monitors and maintains a map of the entire WWW. So the number of sources depends entirely on your monitoring requirements. How frequently can Sentra update its data? As often as required. Sentra can monitor sources in near real-time. Does Sentra monitor only company data? No. Sentra can monitor and extract transactions from any type of unstructured data. Sentra “under- stands” many topics and industries including: Economics, Finance, Banking, Engineering, Computer Science, Health Care, Pharmaceutical Industry, Telecommunication Industry, Politics, etc. Please con- tact us for more details. How is Sentra data supplied? You can acquire Sentra time-series transactions and reference data via an API, (XML, JSON or other format as required), via FTP or alternatively your Sentra system can be entirely hosted (SaaS) and acces- sible via a number of query and analytical tools. Sentiment Analysis has a reputation for not being very accurate, how does Sentra perform? To date, typical sentiment analysis engines are based primarily on statistical techniques. Most are not granular, (i.e. they are article, not sentence level based), and do not understand “context” or “relation- ships”. Typically they achieve accuracy rates below 70%. However, Sentra’s scalable Sentic Computing based system is routinely delivering accuracy rates in excess of 85%-90%. This is equivalent to, (even slightly in excess of), human performance. © Zorallabs 2012 all rights reserved
  • 4. Sentra fact sheet How much does Sentra cost? There are no capital outlays. You pay only for initial setup and the number of sites and items/compa- nies you monitor. Costs depend on the number of sites and frequency of update required. Please do not hesitate to contact our sales office for a free quotation. How quickly can I start? Often, in as little as one week, depending on the sources and entities or fields you require. Typically you would give us details of the sources you require and the fields/event/relationship types to be monitored. We then provide a small, sample output for you to evaluate and then switch on your Sentra system. If you require analysis of entities/relationships/events that we do not currently cover, then just provide us with samples and we can evaluate and incorporate them into Sentra. What next? Simply contact our sales team and we would be deligheted to talk about your requirements. sales@zorallabs.com © Zorallabs 2012 all rights reserved