By Caroline Ball, Trustee of Wikimedia UK
Abstract
Wikipedia is the world’s largest information source, used
daily by millions of individuals around the world – yet such
is its uniqueness and dominance that rarely is the question asked:
what exactly is Wikipedia? This article sets out to explore the
different categories of source that Wikipedia could be defined as
(primary, secondary or tertiary) alongside the varied ways in which
Wikipedia is used, which defy easy categorization, exemplified by a
broad-ranging literature review and focusing on the English
language Wikipedia. It concludes that Wikipedia cannot easily be
categorized in any information category but is defined instead by
the ways it is used and interpreted by its users.
Introduction
What is Wikipedia?
At first pass, it seems like a remarkably simple question with a
remarkably simple answer. The average reader knows exactly what
Wikipedia is, how to access it and has probably used it on multiple
occasions. Almost certainly, if asked, the average reader could
explain what Wikipedia is.
Wikipedia is a crowdsourced online encyclopaedia, indeed, the
online encyclopaedia. It is one of many projects owned by the
Wikimedia Foundation, a non-profit organization based in San
Francisco and founded in 2003 to fund Wikipedia (itself launched in
2001) and other such wiki projects, which include media site
Wikimedia Commons, dictionary and thesaurus Wiktionary, the
knowledge base Wikidata and wikis for books, quotes, travels, a
newspaper, tutorials and courses.1 However,
Wikipedia is the oldest, largest, and almost certainly best known,
of all the Wikimedia projects.
In terms of coverage, usage, currency and public awareness, its
nearest online rival, Encyclopaedia Britannica, does not even
come close. Encyclopaedia Britannica contains an
estimated 120,000 articles;2 as
of writing, the English language Wikipedia contains 6,552,009 and
rises by roughly 17,000 articles a month.3 How the
two compare in terms of perception, accuracy, bias and reliability
is another issue entirely, one that has been amply addressed
elsewhere.4
Much research has also been done on Wikipedia and its sister
projects, and how it is used for, by and within education and
research communities and the wider public – as an information
source,5 a
teaching and learning tool,6 a source
of Big Data,7 an
example of crowdsourcing,8 as a
collaborative dissemination tool for museums and
archives9 and many
other uses.
However, little of this research has taken its analysis of
Wikipedia one step further to reflect on how that varied use might
provide insight into Wikipedia’s own ambiguous position as an
information source; it generally proceeds from the assumption that
there is a clear-cut definition of what exactly Wikipedia is.
For example, the focus on how dependable, accurate or biased
Wikipedia is in comparison to other information sources rests on
the assumption that Wikipedia can be compared to other equivalent
information sources. Part of what this literature review intends to
highlight is that there is no resource equivalent to Wikipedia,
that it stands apart as a unique experiment in crowdsourced
information production, synthesis and retrieval (what Mehdi et al.
describe as a ‘multi-purpose knowledge
base’,10 and that
it straddles the traditional categories of primary, secondary and
tertiary sources, requiring what Magnus describes as ‘new
epistemic methods and strategies’11.
Taking an in-depth look at each of these categories, this review
will draw on published research to assess how Wikipedia’s
content, and the various uses to which different users can put it,
conforms to each category and what the implications are for our
understanding of Wikipedia.
To begin with, we must break Wikipedia down into its many
component parts to adequately discern the whole: what we term
‘Wikipedia’ comprises more than just the most obvious
and visible element, the articles. There is the site itself,
Wikipedia, as a collective term comprising the entire contents,
from articles to talk pages, policies, guidelines, statistics,
documentation and user pages. There are the individual articles,
what we usually think of as defining ‘Wikipedia’. There
are the references and onward links, directing users to further
reading and citational evidence. There is the data that Wikipedia
generates – statistics on almost every element of creation
and use. There are Wikipedia’s own policies, guidelines and
templates. All of these elements are ‘Wikipedia’, and
all are used in various different ways, depending on the user and
the need.
Methodology
This literature review is not intended to be systematic and
relies on mapping the themes of the intended research against the
corpus of literature available, as opposed to identifying and
evidencing all relevant existing research. The intention is to be
illustrative of the varied research on Wikipedia usage, rather than
to provide an exhaustive exploration of it. This review was not,
therefore, conducted according to the relevant principles of
systematic reviews. However, a rigorous search methodology and
strategy was employed.
A wide range of multi-disciplinary databases were searched, both
full-text and index, for articles detailing research based on,
referring to or utilizing data and information from Wikipedia
(including but not exclusive to EBSCO databases, Emerald,
SpringerLink, ScienceDirect, Ovid, Wiley, Taylor & Francis, CINAHL
Ultimate, IEEE and Scopus).
To ensure the relevance and sensitivity of the search, search
terms were limited to the title and the abstract of records, where
the database allowed the option to search these fields. Results
were excluded if Wikipedia was not the primary focus of the
article, if the article was not available in English or did not
refer to the English-language Wikipedia.
Serendipitous discoveries of relevant research were also made
via the WikiResearch Twitter account @WikiResearch, the
‘Wiki-research-l’ mailing list and the Wikimedia
Research biannual reports.
Wikipedia as tertiary
source
We shall begin with the most obvious categorization of Wikipedia
– as a tertiary source. This is how encyclopaedias have
traditionally been defined throughout the ages and indeed how
Wikipedia defines itself: ‘Wikipedia is a tertiary source:
Wikipedia summarizes descriptions, interpretations and analyses
that are found in secondary sources, or bases such summaries on
tertiary sources’,12 although
in quoting Wikipedia’s own definition of itself in this
manner I am in fact using Wikipedia as a primary source, thereby
undercutting that initial apparently clear-cut definition almost
immediately!
Many articles describe Wikipedia as a tertiary source without
comment.13 However,
there is no standard dictionary definition of what a tertiary
source is, how it functions or is used. Wikipedia’s
definition is one, but this research has provided others:
‘when literature is primarily used as a source to locate
primary and secondary sources, and does not provide any new
information, then it is called as tertiary
source’;14 ‘the primary function of
tertiary source is to aid the searcher of information in the use of
primary and secondary sources of
information’;15 ‘the synthesizing of primary
and secondary sources’.16
There can be little doubt that Wikipedia articles synthesize or
summarize primary and secondary sources, and that, theoretically at
least, these articles serve as a means of locating those
sources.
One of the three core content policies of Wikipedia is
verifiability, alongside that need for a neutral point of view and
the ban on original research, i.e. research that has not been
published elsewhere17 –
except when it comes to research about itself – undercutting
that easy definition again. Wikipedia articles must reference
published secondary or primary sources to verify facts or claims
within articles – statements missing this means of
verification are flagged with a ‘citation needed’ tag
and the article itself may contain a ‘needs additional
citations for verification’ template at its head, as a means
of warning users of the potentially misleading or inaccurate (or at
the least, unverifiable) statements contained within a given
article.
One of Wikipedia’s key elements, and one that has itself
given rise to a great deal of research, is the issue of notability
– a subject must be considered notable enough to be covered
by sufficient secondary sources.18 An
article without sources will be flagged for speedy deletion.
However, who or what is considered notable is often the subject of
a great deal of debate and varying perspective, and the
‘notability’ policy is often used to the detriment of
female subjects and topics.19 It does
however highlight the significant importance Wikipedia places on
independent verifiable sources for its content.
An essential element of a tertiary source is that it is
considered a means to further information, not an end, as per the
previous definitions by Wikipedia, Durai and others. Wikipedia has
been described as a ‘bridge’ to further
information,20 a
‘gateway’ through which the world seeks
knowledge,21 a
‘means, not an end’.22 One
would expect therefore to see Wikipedia users’ behaviour
reflect this.
Whilst this is a neglected area of research, and one rich with
possibility for future investigation, a recent study logged all
access clicks for links for external references within Wikipedia
during a one-month period and found ‘overall engagement with
citations is low: about one in 300 pageviews results in a reference
click (0.29% overall; 0.56% on desktop; 0.13% on
mobile)’.23
Follow-up research estimated that Wikipedia generated 43 million
clicks a month to external websites,24 i.e.
users following article citations to their source. However, that
initially impressive-looking statistic needs to be balanced against
Wikipedia’s estimated average monthly pageviews of roughly 7
billion,25 demonstrating
that again less than 1% of users follow citations to their
source.
This research demonstrates that most users (over 99%) do not use
Wikipedia as a ‘bridge’, ‘a gateway’ or as
a means to discovering primary and secondary sources, thereby
undermining those apparently clear-cut assumptions about Wikipedia
as a tertiary source, as defined by Grathwohl, Cronon, Durai and
Malipatil and Shinde above.
Wikipedia as secondary
source
Wikipedia defines a secondary source as a ‘document or
recording that relates or discusses information originally
presented elsewhere,’ containing ‘analysis, evaluation,
interpretation, or synthesis of the facts, evidence, concepts, and
ideas taken from primary sources’.26
This would appear to be the most obvious of categories into
which to fit Wikipedia. There is no question that most of the
material contained within Wikipedia articles comes from elsewhere,
serving as a summary of the published material on a particular
topic. This is an essential element of Wikipedia’s ‘no
original research’ policy: Wikipedia articles must report and
summarize verifiable facts, backed up by published material,
largely in pursuit of another of Wikipedia’s core policies,
that of the ‘neutral point of view’. Including
analysis, evaluation or interpretation in articles necessarily
opens the door to bias and perspective (although research has shown
that this is still not entirely successful, and that Wikipedia
tends to lean leftwards).27
However, intent is one thing; the reality of its use is
something else. Evidence explored below suggests that Wikipedia is
still frequently cited as a source, both within the academic
community and outside of it, despite comments such as Bould et
al.’s that ‘citing Wikipedia or any other tertiary
source in the academic literature opposes literary
practice’.28
This indicates blurred lines between the widely accepted
perception of Wikipedia as a tertiary resource and the way in which
it is used alongside secondary sources such as textbooks and
journal articles. Indeed, a study by Meers, Gibbons and
Laws29 identified a complex interaction
between what they refer to as ‘official’ (journals,
textbooks etc.) and ‘unofficial’ knowledge (Wikipedia,
websites etc.), with students switching frequently between the two
and using the information from one to inform their understanding of
the other.
Many studies have focused on student use of Wikipedia as an
information source,30 with
upwards of 87% reporting using it.31 One
study even demonstrated that Wikipedia was the most used resource
– and the library the least – among medical
students.32 It has
also been used as a means of educating students on issues of
systemic bias in information sources.33
Of course, it is not just students using Wikipedia. Estimating
the scale of citations of Wikipedia itself as a source across
published research is almost impossible, largely because there is
no mechanism for assessing metrics for a crowdsourced resource with
no named author, or indeed even an accepted naming convention.
(Searching for ‘authors’ within references on articles
about Wikipedia within a bibliographic database such as Scopus
highlights this issue – ‘Wikipedia’,
‘Contributors, W.’, ‘Wikipedia
contributors’, ‘contributors, W.’,
‘Anonymous’, ‘Wikipedia, C.’,
‘Wikipedia.org’ and others are all used to
a greater or lesser extent.) However, given the volume of research
focusing on Wikipedia’s use within specific contexts, it is
clearly widespread and growing.34
Several studies have concentrated on citations to Wikipedia
within scholarly publishing,35 with a
study by Bould et al.36 particularly demonstrating that
citations to Wikipedia were not restricted to low or no impact
factor journals but could be found in journals with high impact
factors. A study by Tomaszewski and McDonald37 found
that the highest usage was within the sciences and the lowest
within arts and humanities.
Wikipedia use is not just restricted to the academic world. In
the legal field, for example, several articles have discussed the
practice of Wikipedia being cited as a source within judicial
opinions38 –
sometimes as a source of information on legal procedure and
precedent, or more frequently as a source of facts. However, this
latter practice resulted in at least one case being dismissed as a
result.39 Use of
Wikipedia in this context is rarely presented as a
positive,40 but the
practice clearly was and continues to be widespread enough to be
the subject of academic research. Intriguingly, one of the articles
cited above even specifically describes Wikipedia as a secondary
source.41
There is also research equating Wikipedia with traditional
secondary sources of information such as textbooks, either
implicitly or explicitly. For example, numerous articles have
focused on comparing the accuracy of information within Wikipedia
on a particular topic with similar information contained within
textbooks – in pharmacology,42 history,43 medicine,44 sociology45 –
a comparison that only makes sense if the two resources are
considered to be comparable.
An intriguing study by Rahdari et al.46 even
focused on how concepts of smart learning could be used to provide
recommendations for external supporting material, namely Wikipedia
articles, when students were finding e-textbook material
challenging to understand, again equating the two.
Wikipedia as primary
source
One topic in which there can be no question that Wikipedia
serves as a primary source is that of Wikipedia itself.
As can be seen from this review alone, there is no way of
writing about Wikipedia without referring frequently to the content
it puts out about itself – from its own policies and
guidelines to the statistics about the site, articles and its
usage. There can be no denying that whilst ‘citing Wikipedia
or any other tertiary source in the academic literature opposes
literary practice’, as Bould et al. have argued,
‘Wikipedia may be the most appropriate source to cite …
in situations in which Wikipedia is used as part of the scientific
methods’.47 Note the
implicit acceptance of the definition of Wikipedia as solely a
tertiary source.
For example, a search within the bibliographic database Scopus
for references of the page ‘Wikipedia:
Statistics’,48 which
contains data and statistics for various elements of Wikipedia,
including edits, views, size, growth, editors, demographics, etc.,
returned 155 individual journal articles. A similar search on
Wikipedia’s page on its notability guidelines49 returns
33 journal articles. With these instances as examples, it is
noticeably clear that Wikipedia is being used and referenced as a
primary source, at least when it comes to content that relates to
itself. (As a further example, Wikipedia as a source has been cited
eight times in this literature review.)
Part of the core tenet of Wikipedia is transparency. Because
everything about Wikipedia is openly available, from its guidance
and policies to its inner workings and data, it can serve as an
immensely useful source of data for vast swathes of research.
Wikipedia editing and pageview activities have been used as a
tool to predict everything from movie box-office
success50 to
electoral results51 and
stock market movement.52 Studies
have investigated how Wikipedia pageviews can correlate with
official tourism indicators,53 how
copyright restrictions affect citations and knowledge
reuse54 or to
determine whether the ‘Ice Bucket Challenge’ increased
people’s awareness of ALS.55
One area in which Wikipedia data (most particularly statistics
allowing for the tracking, quantification and geolocating of
pageviews) has been heavily drawn upon is in the field of health
research. Wikipedia is the most used resource globally for medical
information,56 by both
members of the public57 and
healthcare professionals,58 and as
such can provide an enormous source of information on both
individual and group information-seeking behaviour and the
implications and motivations of that behaviour.59
For example, research has focused on the use of trends in, and
analysis of, Wikipedia searches and pageviews as an indicator of
global disease outbreaks,60 from
measles,61 influenza62 and
swine flu63 –
to even predicting deaths from coronavirus.64
Further evidence could be drawn from almost any field of study
– in sociology, for example, exploring the democratic
creation of knowledge and the concurrent promises and
pitfalls65 or the
under-representation of women.66
In the field of conservation, Wikipedia pageviews have been used
for exploring the cultural importance of global
reptiles,67 to
evaluate public interest in protected areas68 and
online sentiment towards iconic species.69
Data harvested from Wikipedia has informed demographic studies
on social media use and topic diversity,70 in
disambiguating and specifying social actors in big data by using
Wikipedia as a data source for demographic
information,71 even in
assessing the life expectancy of professional occupations via the
mean age of death data available via Wikipedia
biographies!72
Focusing on citations in the reverse direction, some research
has focused on academic citations within Wikipedia articles as a
means of evidencing the reach and dissemination of research within
the wider general public, alongside more traditional academic
citation-focused measurements.73
Several studies have compared references to research from
Wikipedia alongside Facebook, Twitter and other social media
resources and found strong correlation between these altmetrics and
the UK Research Excellence Framework (REF) reviewers’ scores,
indicating that altmetrics from sources such as Wikipedia could be
used as a formal means of assessing the impact of scholarly
research.74
Conclusion
Drawing on published research demonstrating the variety of ways
in which Wikipedia has been, and continues to be, used (many of
which defy the initial simple categorization of Wikipedia as a
tertiary source), this review has hopefully demonstrated how the
everyday usage of Wikipedia by millions of individuals globally
differs markedly from the stated intentions and function of the
encyclopaedia itself.
The concept of variation theory is frequently used to explain
how different learners, participating in the same learning
experience and with access to the same learning materials, can come
to understand a concept differently.75 In this
context, it can be used to demonstrate how an object of learning
(i.e. Wikipedia) ‘changes shape during its way from the
intended (planned), enacted (offered) and lived (discerned) object
of learning’.76
As can be seen from the research drawn on within this literature
review, many of the uses Wikipedia can be put to could almost
certainly not have been foreseen by founders Jimmy Wales and Larry
Sanger when they set out to ‘pretty single-mindedly [aim] at
creating an encyclopaedia’,77 since
these uses have resulted from the way it has been structured
(enacted) and the lived experience of those using it. This review
can begin to serve as an explanation of how individuals’
understanding of Wikipedia’s categorization as an information
source can, according to variation theory, similarly differ based
on a range of distinct factors, but in this context, most
particularly how they use Wikipedia. Leaving the world of
literature review and theory behind and moving into practice,
further research would seem to be required on how an
individual’s use of Wikipedia is shaped by their own
understanding of what kind of source it is and how it should be
used, both for education, research and general knowledge
seeking.
Abbreviations and Acronyms
A list of the abbreviations and acronyms used in this and
other Insights articles can be accessed here – click on
the URL below and then select the ‘full list of industry
A&As’ link: http://www.uksg.org/publications#aa.
Competing interests
The author is a trustee of Wikimedia UK, which is an unpaid
voluntary position.
The post Defying easy categorisation: Wikipedia as primary,
secondary and tertiary resource appeared first on WMUK.
The 
The legacy 
►
►
online.
with 
subtitles) from Dr Uçum on the critical role that
OpenStreetMap data has played in ensuring high quality public
health programming in one of the tent cities for displaced people
in Turkey as part of the earthquake response.
A link to the user’s 
