Big Data Expo 2015 - Big 4 Data BonaparteBigDataExpo
油
Sinds 2010 gebruikt het Nederlands Forensisch Instituut (NFI) Bonaparte voor slachtofferidentificatie. Deze software is speciaal voor het NFI ontwikkeld door Big4Data. Big4Data is specialist op het gebied van Machine Learning en Kunstmatige Intelligentie technieken en ontwikkelt modellen waarmee Big Data vraagstukken beantwoord kunnen worden.
In deze keynote zal Willem Burgers, ontwikkelaar van Bonaparte, belichten hoe de software tot stand is gekomen en hoe de technieken die zijn ontwikkeld voor artificieel redeneren, worden gebruikt om het biologische verwantschapsmodel (op basis van DNA) te modelleren. Tot slot zal hij ingaan op enkele van de zaken waarvoor Bonaparte is gebruikt door het NFI; onder meer MH17 (2014), Tripoli (2010), de Vaatstra zaak (2012) zullen worden besproken.
This document summarizes a presentation on machine learning and its applications. It begins with defining machine learning as a field that allows computers to learn without being explicitly programmed. It then provides an example of a "Hello World" machine learning program that trains a classifier to distinguish apples from oranges. The document also outlines the machine learning workflow and discusses popular machine learning libraries. Finally, it lists several applications of machine learning, such as spam filtering in Gmail and photo organization in Google Photos.
Is a mobile phone more dangerous than an AK47?voginip
油
The document discusses how digital technologies like social media, mobile devices, and cloud computing empowered self-organizing networks during the Arab Spring in 2010-2011. These same forces are now disrupting traditional business hierarchies and government structures globally. Statistics show rapid growth of internet and social media usage among younger demographics worldwide. Some governments initially responded by trying to restrict access to these technologies, but a transition toward more open systems may better enable civic participation and innovation.
Machine Learning with Applications in Categorization, Popularity and Sequence...Nicolas Nicolov
油
This document provides an overview of machine learning techniques including categorization, popularity, and sequence labeling applications. It outlines the goals of introducing important machine learning concepts and illustrating techniques through examples. The tutorial aims to be self-contained and explain notation. The outline includes examples of machine learning applications, encoding objects with features, the machine learning framework, linear models, tree models, boosting, ranking evaluation, and sequence labeling with hidden Markov models.
This document discusses using machine learning with R for data analysis. It covers topics like preparing data, running models, and interpreting results. It explains techniques like regression, classification, dimensionality reduction, and clustering. Regression is used to predict numbers given other numbers, while classification identifies categories. Dimensionality reduction finds combinations of variables with maximum variance. Clustering groups similar data points. R is recommended for its statistical analysis, functions, and because it is free and open source. Examples are provided for techniques like linear regression, support vector machines, principal component analysis, and k-means clustering.
Applications of Machine Learning at USC presentation by Alex Tellez
- Powered by the open source machine learning software H2O.ai. Contributors welcome at: https://github.com/h2oai
- To view videos on H2O open source machine learning software, go to: https://www.youtube.com/user/0xdata
Machine Learning and Real-World ApplicationsMachinePulse
油
This presentation was created by Ajay, Machine Learning Scientist at MachinePulse, to present at a Meetup on Jan. 30, 2015. These slides provide an overview of widely used machine learning algorithms. The slides conclude with examples of real world applications.
Ajay Ramaseshan, is a Machine Learning Scientist at MachinePulse. He holds a Bachelors degree in Computer Science from NITK, Suratkhal and a Master in Machine Learning and Data Mining from Aalto University School of Science, Finland. He has extensive experience in the machine learning domain and has dealt with various real world problems.
This talk given at the Hadoop Summit in San Jose on June 28, 2016, analyzes a few major trends in Big Data analytics.
These are a few takeaways from this talk:
- Adopt Apache Beam for easier development and portability between Big Data Execution Engines.
- Adopt stream analytics for faster time to insight, competitive advantages and operational efficiency.
- Accelerate your Big Data applications with In-Memory open source tools.
- Adopt Rapid Application Development of Big Data applications: APIs, Notebooks, GUIs, Microservices
- Have Machine Learning part of your strategy or passively watch your industry completely transformed!
- How to advance your strategy for hybrid integration between cloud and on-premise deployments?
This document summarizes a graph analysis of the Dutch movie world using data from IMDB. It discusses using a graph to represent relationships between actors and actresses who have appeared in the same movies. Nodes in the graph represent individuals and edges link those who have co-starred. The analysis identifies central individuals based on degree and betweenness centrality and detects communities of individuals who frequently appear together. It presents an example community of 54 individuals visualized through a word cloud.
A Unifying theory for blockchain and AILonghow Lam
油
This document proposes a unifying theory connecting blockchain and artificial intelligence technologies. It introduces the Lam-Visser theory and how it fits within the Damhof Quadrants framework. The document provides definitions related to the main result, which states that there exists a minimal, ultra-connected, almost everywhere linear and generic solvable, semi-countable polytope if a certain condition is met. It then discusses applications of this theory to questions of associativity and the computation of analytically independent subalgebras.
Data Science inspiratie sessie, ludieke voorbeelden die enkele machine learning technieken illustreren. Voorspellen van huizenprijzen, soap analytics, auto's, Ikea, de nederlandse film wereld
Jaap Huisprijzen, GTST, The Bold, IKEA en IensLonghow Lam
油
Jaap Huisprijzen, GTST, The Bold, IKEA en Iens, zomaar wat toepassingen van machine learning met Dataiku.
際際滷s of my presentation at BigDataExpo Utrect 20-Sep-2018
際際滷s from my lightning talk at satRDay Amsterdam, 1 sep 2018. Two hobby projects with R package text2vec. 1. Predicting house prices from house descriptions. 2. Word embeddings from the soap series The Bold and The Beautiful
際際滷s of my presentation at the Dataiku meetup on 12th July in Amsterdam (NL)
https://www.meetup.com/Analytics-Data-Science-by-Dataiku-Amsterdam/events/251910036/
RTL collects various data sources like click data, account data, and campaign data. Their data science team uses this data for tasks like churn modeling, response modeling, and customer segmentation. They employ techniques like text mining, computer vision, and association rule mining. For text mining of movie plots, they create a term document matrix and calculate cosine similarity to find similar movies. They also use pre-trained models like VGG16 and ResNet with Keras to perform tasks like content tagging, feature extraction, and measuring image similarities. Survival curves are also used to analyze at what points in episodes or series people stop watching.
Keras with Tensorflow backend can be used for neural networks and deep learning in both R and Python. The document discusses using Keras to build neural networks from scratch on MNIST data, using pre-trained models like VGG16 for computer vision tasks, and fine-tuning pre-trained models on limited data. Examples are provided for image classification, feature extraction, and calculating image similarities.
This summary provides the key points from the document in 3 sentences:
The document discusses extending results on maximal isometries to characterizing properties of Beltrami vectors and applications to questions of countability. It presents definitions for tangential arrows and canonically composite factors. The main result is a theorem stating that under certain conditions, every Euclidean group is linear, semi-reducible and maximal.
Parameter estimation in a non stationary markov modelLonghow Lam
油
This document is the thesis of Longhow Lam on parameter estimation in a nonstationary Markov model for copolymer propagation. It discusses developing a mathematical model to describe the formation of tri-block copolymer chains from monomers during a three-phase chemical process, including the phenomenon of tapering where both monomer types can react during the third phase. The thesis will estimate the model parameters from experimental data, examine identifiability, and analyze the degree of tapering.
The analysis of doubly censored survival dataLonghow Lam
油
This document describes methods for analyzing doubly censored survival data, where the time of infection is interval censored and the time of disease onset or death may be right censored. It applies these methods to data from Amsterdam Cohort Studies on HIV infection. Specifically, it 1) introduces nonparametric models for the infection and incubation time distributions that use maximum likelihood estimation on interval-censored data, 2) applies these methods to data from three cohort studies, estimating the seroconversion and incubation time distributions, and 3) explores extensions including incorporating covariates and using marker data to estimate distributions for prevalently infected individuals.
Machine learning overview (with SAS software)Longhow Lam
油
The document provides an agenda and materials for a workshop on machine learning with SAS. It includes an introduction to machine learning concepts and algorithms. Specific methods that are discussed include regression, decision trees, dimension reduction techniques, and other supervised and unsupervised learning methods. The document emphasizes how SAS software can be used across the entire analytics lifecycle for machine learning, from data preparation to model deployment.
Machine Learning with Applications in Categorization, Popularity and Sequence...Nicolas Nicolov
油
This document provides an overview of machine learning techniques including categorization, popularity, and sequence labeling applications. It outlines the goals of introducing important machine learning concepts and illustrating techniques through examples. The tutorial aims to be self-contained and explain notation. The outline includes examples of machine learning applications, encoding objects with features, the machine learning framework, linear models, tree models, boosting, ranking evaluation, and sequence labeling with hidden Markov models.
This document discusses using machine learning with R for data analysis. It covers topics like preparing data, running models, and interpreting results. It explains techniques like regression, classification, dimensionality reduction, and clustering. Regression is used to predict numbers given other numbers, while classification identifies categories. Dimensionality reduction finds combinations of variables with maximum variance. Clustering groups similar data points. R is recommended for its statistical analysis, functions, and because it is free and open source. Examples are provided for techniques like linear regression, support vector machines, principal component analysis, and k-means clustering.
Applications of Machine Learning at USC presentation by Alex Tellez
- Powered by the open source machine learning software H2O.ai. Contributors welcome at: https://github.com/h2oai
- To view videos on H2O open source machine learning software, go to: https://www.youtube.com/user/0xdata
Machine Learning and Real-World ApplicationsMachinePulse
油
This presentation was created by Ajay, Machine Learning Scientist at MachinePulse, to present at a Meetup on Jan. 30, 2015. These slides provide an overview of widely used machine learning algorithms. The slides conclude with examples of real world applications.
Ajay Ramaseshan, is a Machine Learning Scientist at MachinePulse. He holds a Bachelors degree in Computer Science from NITK, Suratkhal and a Master in Machine Learning and Data Mining from Aalto University School of Science, Finland. He has extensive experience in the machine learning domain and has dealt with various real world problems.
This talk given at the Hadoop Summit in San Jose on June 28, 2016, analyzes a few major trends in Big Data analytics.
These are a few takeaways from this talk:
- Adopt Apache Beam for easier development and portability between Big Data Execution Engines.
- Adopt stream analytics for faster time to insight, competitive advantages and operational efficiency.
- Accelerate your Big Data applications with In-Memory open source tools.
- Adopt Rapid Application Development of Big Data applications: APIs, Notebooks, GUIs, Microservices
- Have Machine Learning part of your strategy or passively watch your industry completely transformed!
- How to advance your strategy for hybrid integration between cloud and on-premise deployments?
This document summarizes a graph analysis of the Dutch movie world using data from IMDB. It discusses using a graph to represent relationships between actors and actresses who have appeared in the same movies. Nodes in the graph represent individuals and edges link those who have co-starred. The analysis identifies central individuals based on degree and betweenness centrality and detects communities of individuals who frequently appear together. It presents an example community of 54 individuals visualized through a word cloud.
A Unifying theory for blockchain and AILonghow Lam
油
This document proposes a unifying theory connecting blockchain and artificial intelligence technologies. It introduces the Lam-Visser theory and how it fits within the Damhof Quadrants framework. The document provides definitions related to the main result, which states that there exists a minimal, ultra-connected, almost everywhere linear and generic solvable, semi-countable polytope if a certain condition is met. It then discusses applications of this theory to questions of associativity and the computation of analytically independent subalgebras.
Data Science inspiratie sessie, ludieke voorbeelden die enkele machine learning technieken illustreren. Voorspellen van huizenprijzen, soap analytics, auto's, Ikea, de nederlandse film wereld
Jaap Huisprijzen, GTST, The Bold, IKEA en IensLonghow Lam
油
Jaap Huisprijzen, GTST, The Bold, IKEA en Iens, zomaar wat toepassingen van machine learning met Dataiku.
際際滷s of my presentation at BigDataExpo Utrect 20-Sep-2018
際際滷s from my lightning talk at satRDay Amsterdam, 1 sep 2018. Two hobby projects with R package text2vec. 1. Predicting house prices from house descriptions. 2. Word embeddings from the soap series The Bold and The Beautiful
際際滷s of my presentation at the Dataiku meetup on 12th July in Amsterdam (NL)
https://www.meetup.com/Analytics-Data-Science-by-Dataiku-Amsterdam/events/251910036/
RTL collects various data sources like click data, account data, and campaign data. Their data science team uses this data for tasks like churn modeling, response modeling, and customer segmentation. They employ techniques like text mining, computer vision, and association rule mining. For text mining of movie plots, they create a term document matrix and calculate cosine similarity to find similar movies. They also use pre-trained models like VGG16 and ResNet with Keras to perform tasks like content tagging, feature extraction, and measuring image similarities. Survival curves are also used to analyze at what points in episodes or series people stop watching.
Keras with Tensorflow backend can be used for neural networks and deep learning in both R and Python. The document discusses using Keras to build neural networks from scratch on MNIST data, using pre-trained models like VGG16 for computer vision tasks, and fine-tuning pre-trained models on limited data. Examples are provided for image classification, feature extraction, and calculating image similarities.
This summary provides the key points from the document in 3 sentences:
The document discusses extending results on maximal isometries to characterizing properties of Beltrami vectors and applications to questions of countability. It presents definitions for tangential arrows and canonically composite factors. The main result is a theorem stating that under certain conditions, every Euclidean group is linear, semi-reducible and maximal.
Parameter estimation in a non stationary markov modelLonghow Lam
油
This document is the thesis of Longhow Lam on parameter estimation in a nonstationary Markov model for copolymer propagation. It discusses developing a mathematical model to describe the formation of tri-block copolymer chains from monomers during a three-phase chemical process, including the phenomenon of tapering where both monomer types can react during the third phase. The thesis will estimate the model parameters from experimental data, examine identifiability, and analyze the degree of tapering.
The analysis of doubly censored survival dataLonghow Lam
油
This document describes methods for analyzing doubly censored survival data, where the time of infection is interval censored and the time of disease onset or death may be right censored. It applies these methods to data from Amsterdam Cohort Studies on HIV infection. Specifically, it 1) introduces nonparametric models for the infection and incubation time distributions that use maximum likelihood estimation on interval-censored data, 2) applies these methods to data from three cohort studies, estimating the seroconversion and incubation time distributions, and 3) explores extensions including incorporating covariates and using marker data to estimate distributions for prevalently infected individuals.
Machine learning overview (with SAS software)Longhow Lam
油
The document provides an agenda and materials for a workshop on machine learning with SAS. It includes an introduction to machine learning concepts and algorithms. Specific methods that are discussed include regression, decision trees, dimension reduction techniques, and other supervised and unsupervised learning methods. The document emphasizes how SAS software can be used across the entire analytics lifecycle for machine learning, from data preparation to model deployment.
Machine learning overview (with SAS software)Longhow Lam
油
Heliview 29sep2015 slideshare
1. Copyright 息 2012, SAS Institute Inc. All rights reserv ed.
GOEDE TIJDEN SLECHTE TIJDEN, IENS AJAX?
TEXT ANALYTICS EN MACHINE LEARNING IN ACTION
Longhow Lam -- Data Scientist
Heliview Business Analytics
https://www.linkedin.com/today/author/7434679
https://longhowlam.wordpress.com/
@longhowlam
http://www.slideshare.net/LonghowLam
2. Copyright 息 2012, SAS Institute Inc. All rights reserv ed.
AGENDA
Inleiding Text mining & Machine learning
Ludieke voorbeelden
Goede tijden Slechte tijden
IENS Reviews
Ajax wedstrijden
3. Copyright 息 2012, SAS Institute Inc. All rights reserv ed.
INLEIDING TEXT MINING EN
MACHINE LEARNING
4. Copyright 息 2012, SAS Institute Inc. All rights reserv ed.
TEXT MINING BASIS
Document 1: Ik loop over straat in Amsterdam, 1057DK, met mijn fiets
Document 2: Zij liep niet maar fietste met haar blauwe fieets, //bitly.com/sdrtw
Document 3: Mijn tweewieler is kapot, wat een slecht stuk ijzer, @#$%$@!
Terms Doc 1 Doc 2 Doc 3
+Fiets (znmw) 1 1 1
Fietsen (ww) 0 1 0
Blauwe (bvg) 0 1 0
Amsterdam (locatie) 1 0 0
+Lopen (ww) 1 1 0
Straat (znmw) 1 0 0
Kapot (bijw) 0 0 1
Slecht 0 0 1
Stuk Ijzer 0 0 1
1057DK (postcode) 1 0 0
//bitly.com/sdrtw (Internet) 0 1 0
TERM DOCUMENT MATRIX: A
Elk document is een (zeer) lange vector van
tellingen (vaak veel nullen!)
Teksten / ongestructureerde data is zijn nu
gewone data geworden.
Comprimeer / reduceer deze matrix A
Pas machine learning toe op gereduceerde
5. Copyright 息 2012, SAS Institute Inc. All rights reserv ed.
TEXT MINING BASIS
Geavanceerd woordjes tellen
Parse & Filter
Part of speech
Entity detection
Mixed / numeric / abbrev.
Stemming
Spell checks, Stop lijst, Synoniem lijst
Multi-term woorden
Pas Traditionele data mining toe
Clustering
Prediction / machine learning
6. Copyright 息 2012, SAS Institute Inc. All rights reserv ed.
TEXT MINING VOORSPELLEN OF CLUSTEREN
Combineer teksten en gewone data om gedrag te voorspellen (churn / fraude)
Pas machine learning toe om
gedrag Y te voorspellen met een
model f
Maak automatisch topics / clusters in hoge stapels documenten
Pas cluster technieken toe om documenten
in clusters (topics) in te delen
Topic 1 Topic 2 Topic 3
7. Copyright 息 2012, SAS Institute Inc. All rights reserv ed.
MACHINE LEARNING ENKELE TECHNIEKEN
Voorspellen
Trees
Random Forests
Clusteren
K-means
Hi谷rarchisch clusteren
DBSCAN
Lineaire regressie
f
y = f(x) = a0 + a1x1 + a2x2+anxn
Neurale netwerken y = f(g(h(x)))
8. Copyright 息 2012, SAS Institute Inc. All rights reserv ed.
TEXT MINING VOORBEELDEN
ECHTE DATA MAAR LUDIEKE VOORBEELDEN
Ludieke voorbeelden met directe toepassingen
Goede tijden slechte tijden Soap analytics
Iens Restaurant analytics
Ajax Wedstrijd verslagen
9. Copyright 息 2012, SAS Institute Inc. All rights reserv ed.
GTST ANALYSIS TEXT ANALYTICS
Business pain
Kijkend naar een paar GTST afleveringen: waar gaat dit over, zijn
er trends in de serie, is het niet allemaal het zelfde?
Aanpak
Neem alle duizenden samenvattingen en pas SAS text mining toe
10. Copyright 息 2012, SAS Institute Inc. All rights reserv ed.
GTST ANALYSIS TEXT ANALYTICS
Business pain
Kijkend naar een paar GTST afleveringen: waar gaat dit over, zijn
er trends in de serie, is het niet allemaal het zelfde?
Aanpak
Neem alle duizenden samenvattingen en pas SAS text mining toe
11. Copyright 息 2012, SAS Institute Inc. All rights reserv ed.
GTST ANALYSIS RESULTATEN
Hoofd topics in 5000 afleveringen
12. Copyright 息 2012, SAS Institute Inc. All rights reserv ed.
GTST ANALYSIS RESULTATEN
Hoofd topics in 5000 afleveringen
13. Copyright 息 2012, SAS Institute Inc. All rights reserv ed.
GTST ANALYSIS RELATIE TUSSEN TOPICS
14. Copyright 息 2012, SAS Institute Inc. All rights reserv ed.
GTST ANALYSIS INZOOMEND OP EEN TOPIC
15. Copyright 息 2012, SAS Institute Inc. All rights reserv ed.
GTST ANALYSIS INZOOMEND OP EEN TOPIC
Sub-topics van een hoofd topic: topic 16 (Ludo, Isabelle, Martine, Janine)
Het eenzaam voelen van Harmsen.
Plan van Jack, gevaarlijk
Afscheidsbrief schrijven
Paniek, angst,
Vragen opdracht kind geven
Geld terug krijgen betalen
Business validatie: De trouwe GTST kijker bij SAS kan zich hierin vinden..
16. Copyright 息 2012, SAS Institute Inc. All rights reserv ed.
GTST ANALYSIS RESULTATEN
Trends over tijd m.b.v. een Bayesian belief netwerk
17. Copyright 息 2012, SAS Institute Inc. All rights reserv ed.
GTST ANALYSIS TRENDS OVER TIJD
18. Copyright 息 2012, SAS Institute Inc. All rights reserv ed.
GTST ANALYSIS GELIJKENIS AFLEVERINGEN OVER DE JAREN
19. Copyright 息 2012, SAS Institute Inc. All rights reserv ed.
IENS RESTAURANT PATH ANALYTICS
Business pain
Ik heb Chinees gegeten. Waar moet ik de volgende keer eten?
Kan ik het sentiment voorspellen?
Aanpak
Kijk naar wat andere doen, IENS restaurant reviewers!
20. Copyright 息 2012, SAS Institute Inc. All rights reserv ed.
IENS RESTAURANT PATH ANALYTICS
Business pain
Ik heb Chinees gegeten. Waar moet ik de volgende keer eten?
Kan ik het sentiment voorspellen?
Aanpak
Kijk naar wat andere doen, IENS restaurant reviewers!
21. Copyright 息 2012, SAS Institute Inc. All rights reserv ed.
EERST EEN PAAR
LUDIEKE FEITJES
IENS DATA (TRADITIONELE BI)
Meest voorkomende naam (39 keer)
Onder Hollandse
restaurant (6 keer)
Duurzame keukens
Biologisch (67%)
Frans (58%)
Vis (44%)
Vegetarisch (39%)
Regionaal (36%)
Chinees (3%)
Zon 700 reviews op een normale zaterdag
Valentijn 2015 1200 reviews (1.7 keer)
23 keer
12 keer
22. Copyright 息 2012, SAS Institute Inc. All rights reserv ed.
IENS RESTAURANT PATH ANALYSIS: GEGENEREERDE REGELS
23. Copyright 息 2012, SAS Institute Inc. All rights reserv ed.
IENS RESTAURANT PATH ANALYSIS: GEGENEREERDE REGELS
24. Copyright 息 2012, SAS Institute Inc. All rights reserv ed.
IENS REVIEWS VOORSPEL SENTIMENT M.B.V. DE REVIEWS ZELF
Text miner om te parsen, filteren en reduceren
Machine learning om eet cijfer te voorspellen
25. Copyright 息 2012, SAS Institute Inc. All rights reserv ed.
IENS REVIEWS HET EET CIJFER VOORSPELLEN
Neuraal network (2 X 20) R2 van 0.65
Random forest (250 trees) R2 van 0.63
Linear regressie model R2 van 0.56
26. Copyright 息 2012, SAS Institute Inc. All rights reserv ed.
Voorspelde score versus de Gegeven score
IENS REVIEWS HET EET CIJFER VOORSPELLEN
27. Copyright 息 2012, SAS Institute Inc. All rights reserv ed.
IENS REVIEWS SENTIMENT ANALYSE / PREDICTIVE MODELING
28. Copyright 息 2012, SAS Institute Inc. All rights reserv ed.
AJAX VOETBAL VERSLAGEN
Business pain
Ik kan niet mee praten op mijn werk over voetbal
Kan ik wat tips meegeven aan ons SAS NL voetbal team?
Aanpak
Text mine alle Ajax voetbal verslagen en leer wat
interessante resultaten uit je hoofd.
Er zijn 476 voetbal verslagen. Ik heb gescraped
van seizoen 2000/01 tot 2014/15.
29. Copyright 息 2012, SAS Institute Inc. All rights reserv ed.
AJAX CONCEPT LINKING VOETBAL TIPS EN STOF OM OVER MEE TE PRATEN
Het verdedigingstrio van der Wiel,
Vertongen, Anita
Wie herinnert zich niet de mooie passes
van Aldewereld naar Boerrigter
Chivu, Machlas en Heitinga worden
vaak geassocieerd met overtredingen
Zorg niet voor veel balverlies, is een
domper zorgt voor onrust en leidt niet tot
een overwinning
De Jong en Chivu worden vaak met
verlies geassocieerd.
Knullig spelen levert ook grote kans op
verlies..
Score binnen 23 minuten! Leidt vaak tot winst
30. Copyright 息 2012, SAS Institute Inc. All rights reserv ed.
AJAX CONCEPT LINKING VOETBAL TIPS EN STOF OM OVER MEE TE PRATEN
31. Copyright 息 2012, SAS Institute Inc. All rights reserv ed.
WERKT HET ? SAS NEDERLAND VOETBAL TEAM
Twee weken geleden 6e geworden i.p.v. altijd laatste !!!!
32. Copyright 息 2012, SAS Institute Inc. All rights reserv ed.
SAMENVATTEND
Analyse op teksten is makkelijk te doen.
Snel inzichten uit teksten te halen
Business validatie nodig en belangrijk!
Dit is ludiek! Maar talrijke serieuze toepassingen