Wikipedia:Beware the myth of Wikipedia written by passing strangers

Beware the myth of Wikipedia written by passing strangers. There is the mistaken notion of Wikipedia being written mainly by one-edit users, or short-term editors, who never returned in later months (not true). It has been a pervasive, misleading myth that Wikipedia was somehow written by passing strangers who added massive content and never returned to edit again. Some illusions, of active one-edit users, can be attributed to people who often change usernames or use rotating dynamic IP addresses. However, the monthly editor-activity statistics confirm how the top 9,500 editors (8%) make 87% of all edits, such as in May 2013. Among such large numbers of edits, it is unrealistic to think people making 87% of edits are not also contributing the majority of content (they are), as if somehow possessed of a mindset to merely adjust the text written by short-term visitors. People who edit every week are exactly the type to add details and expand pages every week.

Alluring myths

Various myths of strangers writing polished articles are alluring, such as saying, "Einstein flunked out of math class" (not true), when the reality is that Einstein quit secondary school to enter college, directly, but at first failed the math entrance exam, until tutored, to pass the re-test. Then Einstein worked with major leaders in theoretical physics, when developing the Special Theory of Relativity. Some people want to believe most inventions are made by college dropouts with independent insight; however, many advances are made by educated people, often working in pairs or teams. Even Thomas Edison hired other people to experiment to find new ideas, or bought the patents of other researchers.

Who writes Wikipedia

As for WP editing, many articles have been created, in coordinated sets, by wp:WikiProjects, such as 12,500 articles from the Catholic Encyclopedia or 22,272 articles from the 1911 Encyclopaedia Britannica, and over 210,000 articles (5% of WP pages) have been created by just 10 users (see "50 recently active wikipedians" in stats-EN). The overall monthly editor-activity statistics follow the typical patterns for a large population of users, such as the 80/20 Rule, but more like 90/10 (meaning 90% of edits are made by 10% of users), where statistics for May 2013 (stats-EN) confirm 8% of users (9,491) made ~87% of edits (2.8 million of 3.2M), which includes Bot edits (because strangers are not running Bots). Likewise, the top 17% (19,156 editors) made 93% of all edits in May 2013.

Then, consider how the 87% of edits, by power users, also include clever edits to run templates and match style guidelines, which most strangers would be unlikely to do. Hence, note the power users make ~87% of edits and most of the rewrites to match format guidelines and template features. The idea of a WP written mainly by one-edit users is just a misleading myth, which ignores the real difficulties of writing sourced, formatted text.

Written by power users, not passing strangers

The myth, that newcomers provided most text, was debunked when checking thousands of pages and authors. Instead, power users write most content and format the style of most pages. In fact 5% of WP pages (210,000 articles) were written by only 10 people (see top editors in: stats-EN). Today, as 8% of editors make 87% of all edits, that massive 87% includes new articles and expanded text. To understand Wikipedia, think logically about the whole. If WP were written mostly by passing strangers, then there would be no incentive to invite newcomers, because they would already be editing, but they are not. Instead, many new articles today arrive as complete pages with infoboxes+categories, as if sprung fully grown from the "head of Zeus" as written by power users. The power users edit the protected pages, decide the rules, develop the templates, revert the edits, and wp:AfD-delete all pages they dislike. Newcomers are lucky to "get a word in edgewise". The power users are doing everything, as newcomers work in the shadows.

The power users are the ones who would most use better software, in 87% of all edits each month.

Analysis of monthly edits

The counts of edits made by one-edit, 3-edit, 5-edit or 10-edit users can be calculated by subtracting the higher-edit users. For May 2013:

Edits ≥	1	3	5	10	25	100	250	1000	2500	10000
May 2013	114,405	50,164	33,174	19,156	9,491	3,321	1453	247	52	3
Apr 2013	114,222	50,394	33,533	19,448	9,590	3,307	1449	240	54	4
Mar 2013	116,261	50,453	33,276	19,076	9,266	3,349	1424	209	47	4

Using the editor levels from the table for May 2013, the maximum counts are as follows:

• most non-5 edits = (114405 - 50164)*2 + (50164 - 33174)*4 = 196,442 edits [1-4 by group]
• most non-10 edits = (114405 - 50164)*2 + (50164 - 33174)*4 +(33174 - 19156)*9 = 322,604 edits [2, 4 or 9 by group]
• most non-25 edits = (114405 - 50164)*2 + (50164 - 33174)*4 +(33174 - 19156)*9 +(19156 - 9491)*24 = 554,564 edits [up to 24 in 4th group]

Because it is an artificial concept, of all editors stopping at one edit below the next-higher count, then the max numbers are adjusted, to center, by multiplying the maximum edits by 75%, as more realistic of edit-counts for each set of users.

See also

• wp:VPIL - wp:Village pump (idea lab) for discussing new ideas or inventions
• wp:PROPS - wp:Village Pump for proposals