Towards Responsible Content Mining: A Cambridge perspective

Cambridge University Press,
Cambridge, UK, 2016-12-14
Towards Responsible Content Mining:
A Cambridge perspective
Peter Murray-Rust1,2
[1]University of Cambridge
[2]TheContentMine
pm286 AT cam DOT ac DOT uk
Researchers, publishers, governments, citizens,
companies want mining. How can we communally
get rid of barriers? Cambridge has a unique role

(2x digital music industry!)
ContentMine is an OpenLocked Non-Profit company

Scholarly publishing is “Big Data”
[2] https://en.wikipedia.org/wiki/Mont_Blanc#/media/File:Mont_Blanc_depuis_Valmorel.jpg
586,364 Crossref DOIs [1] per month (2015-07)
2.5 million (papers + supplemental data) /year [citation needed]*
each 3 mm thick
 4500 m high per year [2]
* Most is not Publicly readable
[1] http://www.crossref.org/01company/crossref_indicators.html
1 year’s scholarly output!

30 June 2016
Announcing new support for Text and Data Mining
We're pleased to announce we have updated our Terms and Conditions to
provide greater support for users to Text and Data Mine (TDM) academic
journal and book content. The new Terms and Conditions allow non-
commercial users to text and data mine any content that they are
authorized to access.
The results of the TDM can be made publicly available providing that no
original content is reproduced except within the limits of what is allowed
under copyright law. The full conditions can be found here:
http://journals.cambridge.org/action/terms
Cambridge University Press
http://admin.cambridge.org/cm/about-us/news/announcing-new-support-text-and-data-mining/

Topics
• What is ContentMining (TDM)
• People!
• Examples: science and tools
• What we could do in Cambridge
Slides at http://slideshare.net/petermurrayrust/

TDM: What France, Europe and UK must do
• ACTIVELY ENCOURAGE Mining and researchers
• INVEST in people, tools, resources, training
• ENCOURAGE cooperative publishers
• PROTECT researchers from other publishers

Typical medical paper
From http://journals.plos.org/plosmedicine/article/authors?id=10.1371/journal.pmed.1002150
(licence CC-BY)

Typical scholarly text
http://journals.plos.org/plosmedicine/article/authors?id=10.1371/journal.
pmed.1002150 (licence CC-BY)

Content Mining can save lives
• Search for papers with “Ebola” and “Liberia”

Towards Responsible Content Mining: A Cambridge perspective

http://www.nytimes.com/2015/04/08/opinion/yes-we-were-warned-about-
ebola.html
We were stunned recently when we stumbled across an article by European
researchers in Annals of Virology [1982]: “The results seem to indicate that
Liberia has to be included in the Ebola virus endemic zone.” In the future,
the authors asserted, “medical personnel in Liberian health centers should be
aware of the possibility that they may come across active cases and thus be
prepared to avoid nosocomial epidemics,” referring to hospital-acquired
infection.
Adage in public health: “The road to inaction is paved with research
papers.”
Bernice Dahn (chief medical officer of Liberia’s Ministry of Health)
Vera Mussah (director of county health services)
Cameron Nutt (Ebola response adviser to Partners in Health)
A System Failure of Scholarly Publishing

HTML PDFtranslational-psychological-treatment-the-feeling-safe-programmediv/41B7E0911A95B6995605BAB

What is “Content”?
http://www.plosone.org/article/fetchObject.action?uri=info:doi/10.1371/journal.pone.01113
03&representation=PDF CC-BY
SECTIONS
MAPS
TABLES
CHEMISTRY
TEXT
MATH
contentmine.org tackles these

Examples
• Bag of words
• Chemistry
• Zika
• Phylogenetics

Bag of Words
Theses from HAL repository

“… simulated by 21cmFAST is in principle independent”
“it is a feature of the 21cmFAST code, and
is explained in §3.1.”
SciCodes[1]: Searching for software in arXiv[1]
[1] Proposal to LJ Arnold Foundation (Alice Allen ASCL and PMR)
Using the semi-numerical simulation, 21cmFAST,
[2] arxiv.org: the physics/maths/astronomy.. Preprint server
The language identifies the software!
arxIv has >500 mentions of “21cmFast”

http://chemicaltagger.ch.cam.ac.uk/
• Typical
Typical chemical synthesis

Automatic semantic markup of chemistry
Could be used for analytical, crystallization, etc.

Multisegment diagram
Whitespace
“corridors”
Superpixel
Bounding box
Semantic
labels

Evolutionary (phylogenetic) trees
• International Journal Systematic and
Evolutionary Microbiology
• Diagrams from 4300 independent articles

OCR (Tesseract)
Norma (imageanalysis)
(((((Pyramidobacter_piscolens:195,Jonquetella_anthropi:135):86,Synergistes_jonesii:301):131,Thermotoga
_maritime:357):12,(Mycobacterium_tuberculosis:223,Bifidobacterium_longum:333):158):10,((Optiutus_te
rrae:441,(((Borrelia_burgdorferi:…202):91):22):32,(Proprinogenum_modestus:124,Fusobacterium_nucleat
um:167):217):11):9);
Semantic re-usable/computable output (ca 4 secs/image)

Supertree created from 4300 papers

Search for 200 articles with “Zika”
file:///Users/pm286/workspace/projects/zika/full.dataTables.html

https://rawgit.com/ContentMine.amidemos/master/zika/full.dataTables.html
Search on publicly accessible papers on “Zika”

<dictionary title="tropicalVirus">
<entry term="ZIKV" name="Zika virus"/>
<entry term="Zika" name="Zika virus"/>
<entry term="DENV" name="Dengue virus"/>
<entry term="Dengue" name="Dengue virus"/>
<entry term="CHIKV" name="Chikungunya virus"/>
<entry term="Chikungunya" name="Chikungunya virus"/>
<entry term="WNV" name="West Nile virus"/>
<entry term="West Nile" name="West Nile virus"/>
<entry term="YFV" name="Yellow fever virus"/>
<entry term="Yellow fever" name="Yellow fever virus"/>
<entry term="HPV" name="Human papilloma virus"/>
<entry term="Human papilloma virus"
name="Human papilloma virus"/>
</dictionary>
Terms co-ocurring with “Zika”

ContentMine believes in young people

ContentMine Workshops on Mining
Chris Kittel, CM, atMozfest 2015
Stefan Kasberger, CM

6 ContentMine Fellows for 6 months

Neo Christopher Chung
 Warsaw, Computational Biology
 Wants to find out geographic and temporal differences in the use of genomic software tools

Paola Masuzzo
 Ghent, Computational Omics and Systems Biology
 Wants to mine literature around cell migrations and invasion to create 1) collection of
minimum requirements, 2) check for nomenclatura consistency and 3) construct a knowledge map

Alexandra Bannach-Brown
 Edinburgh, Neuroscience
 Problem: huge body of works in animal studies about depressions. systematic review is the main
approach for getting insight.
 Wants: identify papers in systematic review of depressive behaviour in animals. What
drugs, what methods, what outcomes and signs/phenotypes. Use outcomes for document
clustering.
 and expedite scientific advances."
 Corpus: 70.000 Papers

Alexandre Hannud Abdo
 “Our goal is to mine facts from global health research and provide automated referenced
summaries to practitioners and agents who don’t have the means or the time to navigate the
literature.
 From Brazil, Life Sciences, works on project about evolution of oncology
 Wants: extract facts from cancer research conference papers and global health papers
OPEN NOTEBOOK RESEARCH

Alexandre Hannud Abdo
 “Our goal is to mine facts from global health research and provide automated referenced
summaries to practitioners and agents who don’t have the means or the time to navigate the
literature.
 From Brazil, Life Sciences, works on project about evolution of oncology
 „I am extremely happy to join this first cohort of ContentMine Fellows. I participated in a
ContentMine workshop in 2014 and have been following the progress of the project ever since,
looking for an opportunity to collaborate which now materializes.“
 Problem: Get text and metadata out of old conference proceedings and measure the evolution of
ideas and practice using entity analysis, especially trends.
 Wants: extract facts from cancer research conference papers and global health papers. Extracting
topics (innovations, developments) and comparing the two types of publications. Find out which
facts from conferences get later on published in articles.
 Has some issues with software

Guanyang Zhang
 Biology, Arizona
 „My ContentMine Fellowship project will focus on mining weevil-plant associations from literature
records.“
 „Motivation. Comprising ~70,000 described and 220,000 estimated species, weevils
(Curculionoidea) are one of the most diverse plant-feeding insect lineages and constitute nearly
5% of all known animals.“
 „Knowledge of host plant associations is critical for pest management, conservation, and
comparative biological research. This knowledge is, however, scattered in 300 years of historical
literature and difficult to access.“
 Weevil-plant association network graph made with Google Fusion Table. Each blue circle is a weevil
tribe and yellow circle a plant genus. The size of a circle represents the number of associations.

Lars Willighagen
 15 years old NL
 Wants: extract data about conifers (relations to chemicals, height etc.)
 Outcome: database with webpage containing conifer properties
 Table Facts Visualiser DEMO
 Card DEMO
 Word Cloud
 „ I applied to this fellowship to learn new things and combine the ContentMine with two previous
projects I never got to finish, and I got really excited by the idea and the ContentMine at large.“

Polly has 20 seconds to read this paper…
…and 10,000 more

ContentMine software can do this in a few minutes
Polly: “there were 10,000 abstracts and due
to time pressures, we split this between 6
researchers. It took about 2-3 days of work
(working only on this) to get through
~1,600 papers each. So, at a minimum this
equates to 12 days of full-time work (and
would normally be done over several weeks
under normal time pressures).”

Infrastrucure
• ContentMine has had to build nearly
everything
• Interoperates with SciPy, R-OpenSci, GitHub …
• Fully Open (CC BY, Apache 2)

• CRAWL the web for scientific documents
(articles, grey literature, repositories)
• quickSCRAPE pages (text, graphics, images, data)
• NORMA-lize page to semantic form
…Open semantic science …
• MINE pages with your methods and tools (AMI)
• CAT-alogue results in searchable index
• Automate daily process (CANARY)
contentmine.org Infrastructure

catalogue
getpapers
query
Daily
Crawl
EuPMC, arXiv
CORE , HAL,
(UNIV repos)
ToC
services
PDF HTML
DOC ePUB
TeX XML
PNG
EPS CSV
XLSURLs
DOIs
crawl
quickscrape
norma
Normalizer
Structurer
Semantic
Tagger
Text
Data
Figures
ami
UNIV
Repos
search
Lookup
CONTENT
MINING
Chem
Phylo
Trials
Crystal
Plants
COMMUNITY
plugins
Visualization
and Analysis
PloSONE, BMC,
peerJ… Nature, IEEE,
Elsevier…
Publisher Sites
scrapers
queries
taggers
abstract
methods
references
Captioned
Figures
Fig. 1
HTML tables
30, 000 pages/day
Semantic ScholarlyHTML
Facts
CONTENTMINE Complete OPEN Platform for Mining Scientific Literature

• Chris Hartgerink
Tilburg University (NL)
• Reproducible Science
• Extracting statistical information
• Helping authors check
reported results
• Detecting problematic study
results (e.g., clinical trials)

[1]
[1] STATCHECK from Chris Hartgerink

“Symmetry [is] indication of
potential publication bias”
Machines are BETTER than humans here
Can we believe meta-analyses of clinical trials?

file:///Users/pm286/workspace/svg2xml/targe
t/table/ada2PH1Total.html
ContentMine converts PDF to HTML5
Perfect for machines!
PDF table 
HTML5 table Horrible for machines!

The Royal Society
Data mining
We support the stance that the right to read is the right to mine. We believe that the ability to use
computers to extract information from scholarly material is one of many tools available to researchers, and we support
this activity on our journals.
Members of subscribing institutions have our permission to mine journal content for
either commercial or non-commercial purposes. We ask that you respect the copyright of the
original papers, and where possible cite original works when you reuse them.
Text and data mining is an exception to the usual copyright restrictions which researchers can benefit from. The
exception (s.29A of the Copyright, Designs and Patents Act 1988 (CDPA)) allows copies to be made of any copyright
material for the purpose of computational analysis.
If a researcher wants to share TDM results that contain some copyright-protected element from the original
work, for example in a publication, then that is possible in certain circumstances. For example, the
Quotation exception (s.30 of the Copyright, Designs and Patents Act 1988 (CDPA)) allows the copying and use of
portions of someone else’s work to illustrate a point being made.
Please also bear in mind that our servers have finite capacity, and to help us manage the system load we ask that you
let us know when you intend to carry out any mining activity. Our technology provider sets a limit on downloads from
our sites, beyond which an automatic lock-out is triggered. By working together, we can help you to complete your
project and achieve your research goals without being blocked by technical restrictions.
https://royalsociety.org/journals/ethics-policies/data-sharing-mining/

OUP1 Data Mining Policy
http://www.oxfordjournals.org/en/help/third-party-data-mining.html
… we are happy to accommodate TDM for non-
commercial use. Although researchers are not required
to request permission for non-commercial text-mining,
OUP is happy to offer consultation … including avoidance
of any technical safeguards triggers OUP has in place
1 Oxford University Press

@Senficon (Julia Reda) :Text & Data mining in times of
#copyright maximalism:
"Elsevier stopped me doing my research"
http://onsnetwork.org/chartgerink/2015/11/16/elsevi
er-stopped-me-doing-my-research/ … #opencon #TDM
Elsevier stopped me doing my research
Chris Hartgerink

I am a statistician interested in detecting potentially problematic research such as data fabrication,
which results in unreliable findings and can harm policy-making, confound funding decisions, and
hampers research progress.
To this end, I am content mining results reported in the psychology literature. Content mining the
literature is a valuable avenue of investigating research questions with innovative methods. For
example, our research group has written an automated program to mine research papers for errors in
the reported results and found that 1/8 papers (of 30,000) contains at least one result that could
directly influence the substantive conclusion [1].
In new research, I am trying to extract test results, figures, tables, and other information reported in
papers throughout the majority of the psychology literature. As such, I need the research papers
published in psychology that I can mine for these data. To this end, I started ‘bulk’ downloading research
papers from, for instance, Sciencedirect. I was doing this for scholarly purposes and took into account
potential server load by limiting the amount of papers I downloaded per minute to 9. I had no intention
to redistribute the downloaded materials, had legal access to them because my university pays a
subscription, and I only wanted to extract facts from these papers.
Full disclosure, I downloaded approximately 30GB of data from Sciencedirect in approximately 10 days.
This boils down to a server load of 0.0021GB/[min], 0.125GB/h, 3GB/day.
Approximately two weeks after I started downloading psychology research papers, Elsevier notified my
university that this was a violation of the access contract, that this could be considered stealing of
content, and that they wanted it to stop. My librarian explicitly instructed me to stop downloading
(which I did immediately), otherwise Elsevier would cut all access to Sciencedirect for my university.
I am now not able to mine a substantial part of the literature, and because of this Elsevier is directly
hampering me in my research.
[1] Nuijten, M. B., Hartgerink, C. H. J., van Assen, M. A. L. M., Epskamp, S., & Wicherts, J. M. (2015). The
prevalence of statistical reporting errors in psychology (1985–2013). Behavior Research Methods, 1–22.
doi: 10.3758/s13428-015-0664-2
Chris Hartgerink’s blog post

http://onsnetwork.org/chartgerink/2016/02/23/wiley-also-stopped-my-doing-my-research/
Wiley also stopped me (Chris Hartgerink) doing my research
In November, I wrote about how Elsevier wanted me to stop downloading scientific articles for my research. Today, Wiley
also ordered me to stop downloading.
As a quick recapitulation: I am a statistician doing research into detecting
potentially problematic research such as data fabrication and
estimating how often it occurs. For this, I need to download many scientific articles, because my research
applies content mining methods that extract facts from them (e.g., test statistics). These facts serve as my data to answer my research
questions. If I cannot download these research articles, I cannot collect the data I need to do my research.
I was downloading psychology research articles from the Wiley library, with a maximum of 5 per minute. I did this using the tool quickscrape,
developed by the ContentMine organization. With this, I have downloaded approximately 18,680 research articles from the Wiley library,
which I was downloading solely for research purposes.
Wiley noticed my downloading and notified my university library that they detected a compromised proxy, which they
had immediately restricted. They called it “illegally downloading copyrighted content
licensed by your institution”. However, at no point was there any investigation into whether my user credentials were
actually compromised (they were not). Whether I had legitimate reasons to download these articles was never discussed.
The original email from Wiley is available here.
As a result of Wiley denying me to download these research articles, I cannot collect data from
another one of the big publishers, alongside Elsevier. Wiley is more strict than Elsevier by immediately condemning the
downloading as illegal, whereas Elsevier offers an (inadequate) API with additional terms of use (while legitimate access
has already been obtained). I am really confused about what the publisher’s stance on content mining is, because Sage
and Springer seemingly allow it; I have downloaded 150,210 research articles from Springer
and 12,971 from Sage and they never complained about it.

Julia Reda, Pirate MEP, running ContentMine
software to liberate science 2016-04-16

University of Cambridge, and
ContentMine/OKI
• Work with benign publishers to establish protocols
and legal certainty
• Meeting/workshop in Cambridge (March 2017)
• Some publishers welcoming Mining:
– Cambridge University Press
– International Union of Crystallography
– Oxford University Press
– The Royal Society
– ?Springer, ?Sage

What France, UK and Europe must do
• ACTIVELY encourage Mining and researchers
• INVEST in tools, resources, training
• ENCOURAGE cooperative publishers
• PROTECT researchers from aggressive publishers
• Need ACTIONS, not WORDS or it will be too late

Credits for pictures
Lars: https://commons.wikimedia.org/wiki/File:Conifer_cone_park.jpg
https://commons.wikimedia.org/wiki/File:Hylobius_abietis_up.jpg
Guanyan: https://upload.wikimedia.org/wikipedia/commons/4/47/Adult_citrus_root_weevil,_Diaprepes_abbreviatus.jpg
Paola: https://commons.wikimedia.org/wiki/File:Four_steps_of_cell_migration.png
https://commons.wikimedia.org/wiki/File:Cellmigrationmodels.png
Alexandra: https://de.wikipedia.org/wiki/Rat_Park#/media/File:Wistar_rat.jpg
https://en.wikipedia.org/wiki/Laboratory_mouse#/media/File:Scid_mouse.jpg
Ale https://commons.wikimedia.org/wiki/File:Mouth_and_oropharynx_cancers_world_map_-_Death_-_WHO2004.svg
https://commons.wikimedia.org/wiki/File:Lung_cancer_US_distribution.gif
https://en.wikipedia.org/wiki/Liver_cancer#/media/File:Liver_cancer_world_map-Deaths_per_million_persons-WHO2012.svg

Towards Responsible Content Mining: A Cambridge perspective

More Related Content

What's hot (20)

Viewers also liked (9)

Similar to Towards Responsible Content Mining: A Cambridge perspective (20)

More from petermurrayrust (18)

Recently uploaded (20)

Towards Responsible Content Mining: A Cambridge perspective