my journey to data science · data science is the extraction of actionable knowledge directly from...

Post on 16-Aug-2020

1 Views

Category:

Documents

0 Downloads

Preview:

Click to see full reader

TRANSCRIPT

A journey into Data

Science in Libraries

Luis Martinez-Uribe

Data Scientist

Library

Fundación Juan March

Photo with CC BY-NC-SA 2.0 licence taken from https://www.flickr.com/photos/bg2axk/

Second EDISON Conference - 16 March 2017

Outline

Data Science My personal journey

Data Science at Fundación Juan March

Training

Looking ahead

What is Data Science?

Data science is the extraction of actionable knowledge directly from datathrough a process of discovery, or hypothesis formulation and hypothesis testing.

National Institute of Standards and Technology (NIST) Big Data Working Group (2015)

Data Science

Statistics

Computer science

Mathematics

Social science

Software engineering

Ethics

Artificial Intelligence

What is Data Science for?

What is Data Science for?

A pathway to Data Science in Libraries

BSc Mathematics

Social Science Data Librarian

Research Data Management

Data Scientist

MSc InformationSystems

PhD

Sociology

Big Data

Klavans, Richard and Kevin W. Boyack. (2006). “Quantitative Evaluation of Large Maps of

Science.” Scientometrics 68 (3): 475-499.

Research Data Management

CURATION

CAPTURE AND STORAGE

ANALYSIS

VIZ AND BI

Tools

KnowledgePortals

01Our users and visitors

02Classifiers

03Search & recommend

04Vizs

05Analysis of social networks

06

Examples of Data Science Activities

Knowledge portals

Our users and visitors

Classification of our content

Keyword generation for events

Abstract

FormatTitle

...

EVENTS WITH KEYWORDS

(training set)

WORD PROCESSING

(stopwords, expressions)

STATISTICALINDICATORS

(frequency, word length, position,)

PREDICTIVE MODELS (machine learning)

CLASSIFIER(80% precision)

Search and recommendation systems

Search

Integrating data from 6.000 events, 500 exhibitions and art catalogues and 5.000 Library items

RecommendationsUsing meaningfull words in the title and keywords.

Interactive web graphs

Twitter networks and real time sentiment analysis

Training and education

Data Science methods

Big Data technologies

PhD in Social Sciences, department of sociology

Develop analitical and visual framework for the social analysis of Big Cultural Data from libraries, archives and museums

Photo with CC BY-SA 2.0 licence taken from https://www.flickr.com/photos/seiho/

datamonster.co

• the is to ...learn all you

can about your data…from where it was first created.

•Embrace the broader reality…all the information that is yet to be stored in technology.”

Looking ahead

Artificial

intelligence

Looking ahead

"The best prophet of the future is the past." Lord Byron

Thanks

lmartinez@march.es

@luismart

es.linkedin.com/in/luismartinezuribe

top related