text mining: the next data frontier. beyond open access

Presentation’s Subtitle

#openminted_eu

beyond Open Access

Text Mining: the next data frontier

Natalia ManolaAthena Research & Innovation Centre

OpenCon Satellite Berlin, 25 Nov 2016

A few sobering facts on content production


● 1,8 billion websites & 3,46 billion internet users, on 25 September 2016.

● 24 million wireless sensors and actuators worldwide (553% up, between 2011and 2016)

● 16 zettabytes of useful data (16 Trillion GB) by 2020

● YouTube claims to upload 24 hours of video every minute, making the site ahugely significant data aggregator.

● Every second, on average, around 6,000 tweets are tweeted on Twitter, whichcorresponds to over 350,000 tweets sent per minute, >500 million tweets perday and around 200 billion tweets per year.

● 74,200,000 pages existed on Facebook, with 7 million apps and websitesintegrated with Facebook on 30/5/2016

2

… And some facts on scientific literature


The global research community generates ~2.5 million new scholarly articles per year (English only)

The STM report (2015)

… some 90% of papers … are never cited (82% in the humanities)… of those articles that are cited, only 20 percent have actually been read… 50% of papers are never read by anyone other than their authors, referees and journal editors

Lokman I. Meho, The rise and rise of citation analysis, 2007

… one paper published every 12seconds… 70,000 papers published on a single protein, the tumor suppressor p53

Spangler et al, Automated Hypothesis Generation based on Mining Scientific Literature, 2014

3

How can we make sense of this data?


4

Emerging solutions

Machine readingprocess textual sources, organise and classify in various dimensions, extract main (indexical) information items,

… and “understanding” identify and extract entities and relations between entities, facilitate the transformation of unstructured textual sources into structured data

… and predictingenable the multidimensional analysis of structured data to extract meaningful insights and improve the ability to predict


5

However, …Multitude of solutions catering for different

Text Types NewswireScientific LiteratureTweets/blogsPatentsClinical/medical recordsTextbooks, monographsOnline forums….

LanguagesEnglish French GermanSpanishPortugueseItalianPolish….

TasksTranslationInformation ExtractionSemantic SearchQuestion AnsweringSentiment AnalysisSummarizationKnowledge Discovery….

DomainsFinance/BusinessHealthBiologySocial SciencesHumanities….

Creating a fragmented landscape


6

A glimpse on the TDM landscape


7

Resource: FutureTDM project (www.fututetdm.eu)

What can we do?

8

1. Share content• Document literature content• Share in a meaningful way: what does Open Access really mean?

IPR and licensing• Study IPR restrictions for reuse of sources as well as possible exceptions• Promote clarity and standardisation of legal rights and obligations

Challenges• Rights statement vs. Open licenses (for repositories)• No access to full text. We live in a metadata world• No standard protocols, formats and APIs for access and retrieval• No capacity to handle extra traffic


9

Proposed solution : Make TDM enabled hubs


10

Literature Repositories

OA Journals

Data Repositories

Aggregators

ArchivesMetadata

Full textData

OpenAIRE

CORE

PMC Europe

…

Guidelines APIs

TDM

Research networks

WIkiPedia/Media/Research

…

2. Share TDM Services• Document language processing/text mining services and workflows in a

meaningful way for domain discipline researchers• Document language/knowledge resources, data categories taxonomies,

provenance information

Interoperable services• Common way of presenting annotated results• Combine services into workflows• Combine content and language resources with services and workflows• Combine automatic and manual/crowdsourcing annotation services

IPR and licensing• Translate the legal & policy aspects into specifications for lawful user-to-

service and service-to-service interactions

Challenges• Bring text miners close to the researcher problems and needs• Semantic interoperability (not just technical)


11

OpenMintedEstablish an open and sustainable Text and Data Mining (TDM) platform and infrastructure where

researchers can discover, collaboratively create, share and re-use knowledge from a wide range of text based

scientific and scholarly related sources.


12

A step from Open Access to Open Science

HIGH LEVEL ARCHITECTURE


13

Policies & guidelines

Register and Discover TDM Services and tools

Link to Content hubs

Run a TDM job and share results

Get people’s knowledge - Crowdsourced Annotation

Our Services

14


Build your own service – Combine components into a Workflow and SHARE

Our UsersEnd users• Researchers, data base curators, Research Infrastructure

operators• Novice: use services to advance their science• Advanced: use TDM components into complex workflows


15

Content and service providers- Publishers, libraries, scientific data base centres, …- TDM researchers- SMEs


Scholarly Comm.Feature extractionData citationResearch analytics

Life Sciences

Curation of databases and lexica in Chembolomics &neuroinformatics

Agriculture

Extracting information from tables for food safety alerts

Social Sciences

Data citation

Community Driven

16

From the very beginning…Requirements, content, barriers, expected outcomes.

… to the very end Create applications, validate and evaluate the results.

Examples of OpenAIRE TDM services we want to share

17

@openaire_eu

18

Discover research in context


19

Research Trends and correlations

Text and data mining with domain specific knowledge

Interactive visualization for drill-down information

…

Trends in science

Correlations of funding programmes

Within a funder, oracross countries


What will it look like?

20

the openminted registry


21

Browse tdm resources & tools/services


22

Register, document, share tools


23

Create your corpus, annotate, share


24

How does this all bind together?


25

OpenAIRE

CORE

CrossRef

… OpenMinted REGISTRY

CLARIN

META-SHARE

OpenMinted WORKFLOWS

TDM TOOLSRepositories

(OA) Journals

Other textual resources e.g. medical records, PSI

How DOES open Science help?

Language resources

…

What’s next

Participate with your ideas• Give us your feedback on our pending guidelines and APIs• Provide us with your TDM requirements – we have the

experts to consult you• Register your TDM services• Test out the system when it comes live (spring)

Watch out for• OpenAIRE’s datathons, tenders and challenges (60K in total)• OpenMinTeD’s tenders and challenges (240K in total)


26

twitter.com/openminted_eu

facebook.com/openminted

bit.do/openmintedlinkedin

vimeo.com/openminted

bit.do/openmintedplus

THANK YOU!

Natalia [email protected]

twitter.com/openminted_eu

facebook.com/openminted

bit.do/openmintedlinkedin

vimeo.com/openminted

bit.do/openmintedplus27