How many “users” are on the internet?
Before answering, somebody has to define user.
A server log counts requests. A social network counts accounts. A survey counts people. Those numbers can all be correct while describing completely different populations.
That distinction matters whenever somebody tries to estimate how much online activity is human, synthetic, or abandoned.
One person can become many records
A single person can own several social accounts, use multiple browsers and devices, run scripts, operate a business page, and make thousands of page requests in one day.
The reverse also happens. One account may represent a company, family, newsroom, project, or team rather than one individual. A bot may control many accounts. An organization may generate millions of automated requests without possessing anything resembling millions of “users.”
Pew Research Center described this problem directly when discussing social-media data: researchers often struggle to translate accounts into people because an account may be a person, a duplicate account, or an automated account. Its discussion of social-media research methods also notes a broader sampling problem: platforms that are easiest to study are not necessarily representative of everyone online.
Even basic profile counts can multiply one human identity. Pew found as far back as 2009 that more than half of adult social-network users in its survey had two or more profiles, usually spread across different services. The exact percentage is historical, but the measurement problem never went away.
Requests are even farther from people
Network traffic is another layer removed.
One page load can trigger dozens of requests for images, JavaScript, fonts, APIs, ads, and analytics. A crawler can generate millions of requests while representing one automated system. A mobile app may poll an API repeatedly while its owner does nothing.
So a statement like “bots generated more requests than humans” cannot be converted into “there are more bots than people.” It is comparing events to actors.
Likewise, “there are 500 million accounts” does not establish 500 million distinct people. Accounts can be duplicated, dormant, shared, organizational, compromised, automated, or abandoned.
A useful estimate names the unit
Good population claims are boringly specific.
Instead of saying “half the internet is bots,” a careful study might say that a defined percentage of HTTP requests observed by a security provider were classified as automated during a particular year. Or that a percentage of sampled accounts on one platform showed behavior consistent with automation. Or that survey respondents reported using a service.
Those are different statements because they answer different questions.
Dead Internet Theory discussions often become confusing at exactly this point. A number describing traffic gets compared with a number describing accounts, then both get interpreted as a number describing people.
The arithmetic may be flawless. The categories are not.
Before asking whether the internet is populated by humans or machines, the first useful question is simpler: What exactly are we counting?