Psychometric Profiling: An Explanation and History

After revelations about the role of Cambridge Analytica in election influence surfaced, one of the company's most touted tactics — psychometric profiling — has become a matter of public interest. This piece aims to explain how psychometric profiling works in straightforward terms, to highlight a few present-day examples, and to elucidate its origins.

Methodological Explanation

The goal of psychometric profiling is to measure the psychological faculties of subjects of interest as accurately as possible. The gold standard in psychology for explaining differences between people is the OCEAN model, also called the "Big Five" or the "Five Factor Model". OCEAN is an acronym of five personality traits: openness, contentiousness, extraversion, agreeableness, and neuroticism. The OCEAN model is “claimed to represent the basic structure underlying the variations in human behavior and preferences”.

These profiles of behavior and preference paint an intimate picture of an individual or population's mental tendencies and proclivities, and a growing body of research has demonstrated that data from our digital lives can be used to build extremely accurate psychometric profiles at scale. Cambridge University PhD Michal Kosinski showed that digital records that were easy to access in 2013 could be used to ascertain sensitive traits about people, including information about their personality. How did he arrive at this finding?


The schematic above shows a simplified pipeline for psychometric profiling based on Facebook data as conducted in Kosinski's aforementioned research. In practice information on intimate traits need not be self-reported. It can be extracted from enticing, game-like online quizzes that sell new insights about ourselves. It can also simply be observed directly, inferred, or purchased from data brokers. Recent research on psychometric profiling has led to three major findings. First, simple statistical models can uncover individuals' psychological information from rather ubiquitous digital footprints. Second, computers are better at judging personality from data than humans are. Finally, ads tailored to psychological profiles are more effective than ads that are not.*

Kosinski followed this idea the following year and co-authored a literature review paper concluding that "pervasive records of digital footprints can be used to infer personality". In 2015, his widely-cited finding that computers are better predictors of personality than humans attracted headlines by comparing how computer models of personality stacked up against friends, co-workers, and partners of the users in question.

Each of OCEAN's five super-dimensions are comprised of primary factors that tend to be correlated with one another. Open individuals, for instance, are those who exercise creativity, imagination, and tolerance. They like change, are receptive to new ideas, and tend to like art. The rationale is that on the margin — that is, if you were to take two people identical in every single way except one — the person who likes art tends to be more open than her hypothetical twin who doesn't. Her sense of openness represents a different mode of reasoning and decision-making from her counterpart. Advertisements that engage with ideas (appealing to curiosity), fantasy (imagination), aesthetics (art), and feelings (excitation) will resonate with her motivational system more so than with her closed twin. One study conducted by researchers in Canada and published in 2012 found that customizing advertisements to recipient's psychological profiles improves the ad's performance in a controlled lab setting. In 2017, Kosinski and a team of other business school professors tested those findings in a real-world setting by building psychometrically-informed ads for actual brands and assessed their performance in a real-world setting. They describe the significance of their results as follows:

Building on recent advancements in the assessment of psychological traits from digital footprints, this paper demonstrates the effectiveness of psychological mass persuasion – that is, the adaptation of persuasive appeals to the psychological characteristics of large groups of individuals with the goal of influencing their behavior.

Adding such psychological customization to ads already tailored with respect to topical content, framing, tone, channel (e.g., TV vs. online), placement, frequency, and the standard micro-targeting demographics suite (age, race, sex, location, education level, income, occupation, movie preferences, etc.) boosts the chance of successfully altering a desired behavior — in this case, a vote.

Examples & Case Studies

As the demand for psychometric profiling heats up among for-profit companies and political campaigns, a number of private companies in addition to Cambridge Analytica aim to capitalize on the moment. A host of startups including Affectiva, RealEyes, and Sensum are vying to capture the rewards of the psychologically-informed ad market. Established firms, too, have entered the mix. The market research company Nielsen acquired neuromarketing company Innerscope in 2015. Auto manufacturer Ford conducted experiments in Vietnam with mobile ads timed precisely at emotional moments of sporting events and observed boosts in retail sales that far exceeded their expectations.

Leveraging psychometric data requires the ability to collect, mine, and make inferences upon troves of data, and the Advertising Research Foundation recognized Cambridge Analytica in its "big data" category for such work in 2017. The winning campaign, which describes using sophisticated machine learning methods to identify and target persuadable voters, served Donald Trump's campaign days before polls closed, and ARF awarded Cambridge Analytica the gold prize over for-profit firms.


As Alexander Tayler, Cambridge Analytica's Chief Data Officer stated:

It’s not about tricking people into voting for a candidate who they wouldn’t otherwise support. It’s just about making marketing more efficient.

Cambridge Analytica has openly advertised these "advanced machine learning techniques" in the context of psychometric profiling.


Cambridge Analytica purportedly pitched its business to MasterCard, the NY Yankees, and the Joint Chiefs of Staff. Its parent company, Strategics Communications Laboratory, was started in 1993 by Nigel Oakes, ad advertising specialist who "argued that traditional advertising was incapable of effecting the type of mass opinion shifts necessary for social change". He then launched an offshoot, Behavioral Dynamics Institute, a research effort focused on group dynamics and decision-making before SCL was repackaged as a "psychological warfare" specialist twelve years after its founding. Today, Nix also leads SCL, which is believed to work for the Commerce Department, the National Traffic Safety Administration, for a company that sells gold coins to listeners of conservative talk radio, and for the Pentagon on "counter-radicalization". In addition to Donald Trump and Ted Cruz, Cambridge Analytica also provided services to ten other candidates in the 2016 American election.

Consumer credit reporting agency Experian also advertises its psychometric data. The data broker holds data on over a billion individuals in Europe and the US and earned over 4.6B USD in revenue in 2015. Among the many offerings of Experian Marketing Services is Audience IQ, a one-stop shop for marketers that apparently can "influence voting behavior by interweaving demographic, psychographic, and attitudinal" characteristics. Both the Conservative and Labour parties in the UK are Experian clients.


Among Experian's other offerings is its Audience Guide, whose tagline is "Get inside the mind of your consumers". The Guide describes categories defined by consumer self-concepts and political persuasions.



IBM also launched its own psychometric services. IBM Watson's Personality Insights promises to "gain insight into how and why people think, act, and feel the way they do" by conducting natural language processing on text. Below is an analysis of the Pope's personality based on his Twitter feed. According to the full results, he is deemed genial and empathetic, unlikely to have a gym membership, and unlikely to prefer style when buying clothes. Perhaps the Pope would beg to differ.


The Backstory

The origins of OCEAN date back to the late 19th century, when the first attempts to classify human personality were documented. A few decades later, pioneer Edwards Bernays became famous for his ideas built upon this psychological research.

As depicted in the 2002 British TV doc-series Century of the Self, Bernays gained notoriety for being the first person to put into practice the foundational ideas propounded by Sigmund Freud, his uncle. In 1929, Bernays worked with tobacco companies and spearheaded a campaign that led to increased cigarette sales among women under the guise of gender equality. He also helped frame Guatemala as a communist threat to the USA in order to increase support for the Cold War, ultimately leading to an overthrow of the Guatemalan government in 1954. He later referred to the scheme as the engineering of consent. Hailed today as the father of public relations, in 1928, he published Propaganda, a work combining insights from psychology and communication in the context of mass manipulation. In it, he wrote in the opening):

The conscious and intelligent manipulation of the organized habits and opinions of the masses is an important element in democratic society. Those who manipulate this unseen mechanism of society constitute an invisible government which is the true ruling power of our country.

Bernays's ideas are ingrained in the design and infrastructure of advertising, and psychometric profiling is a continuation of a tradition to employ personal information in the service of a desired outcome. Lester Wunderman, a marketing executive who coined the term "direct marketing" in the 1960s argued that there are two ways to sell anything — either via mass marketing or personalized advertising. While mass media advertises goods, personalized advertising is a service that identifies a person's needs and addresses that need at the right moment. Recent trends toward psychographic ads aligns with the advertising industry's decades-long investment in personalized advertising to predict and cater to consumer needs and — better yet — supply-induced desires.

These dynamics have intensified with the advent of the internet, which, in fact, has always lent itself to data collection and surveillance. As Yasha Levine claims and argues in his book, Surveillance Valley: The Secret Military History of the Internet, "The internet, going back to its first incarnation as the ARPANET military network, was always about surveillance, profiling, and targeting". He also asserts that Cambridge Analytica is no exception with respect to around-the-clock data collection, and that the internet's advertising-centric business model means virtually all major tech companies are culpable:

So if we’re going to view the actions of Cambridge Analytica in their proper light, we need first to start with an admission. We must concede that covert influence is not something unusual or foreign to our society, but is as American as apple pie and freedom fries. The use of manipulative, psychologically driven advertising and marketing techniques to sell us products, lifestyles, and ideas has been the foundation of modern American society, going back to the days of the self-styled inventor of public relations, Edward Bernays. It oozes out of every pore on our body politic. It’s what holds our ailing consumer society together. And when it comes to marketing candidates and political messages, using data to influence people and shape their decisions has been the holy grail of the computer age, going back half a century.

Let’s start with the basics: What Cambridge Analytica is accused of doing—siphoning people’s data, compiling profiles, and then deploying that information to influence them to vote a certain way—Facebook and Silicon Valley giants like Google do every day, indeed, every minute we’re logged on, on a far greater and more invasive scale.

Advertisers know that online data collection paints only a partial picture. Connecting online and offline identities was once contentious, but it's now standard practice, as mobile devices full of sensors generate digital footprints of otherwise offline activities. While some critics still cast doubt on the validity of OCEAN, which can build inferences upon online and offline data, several research teams arrived at it independently, and it is commonly used in psychological research today, as in Kosinski's work on inferring personality from digital footprints.

In the context of elections, campaigns can harness psychographic data towards less savory ends like voter suppression and forms of influence that are buried in data and difficult to detect. In this respect, the advertising-centric, data-driven business model has realized its biggest, highest-stakes market. This is the market for ideas, and psychometric profiling is an essential ingredient that can be used to achieve a wide array of goals. As Alexander Nix, alluding to SCL's government-contracted work, has stated:

Persuading somebody to vote in a certain way is really very similar to persuading a 14- to 25-year-old boys in Indonesia to not join Al Qaeda.

Interestingly, after taking credit for Donald Trump's victory in November 2016, Cambridge Analytica has downplayed its use of psychometric methods, even claiming that such methods were never used. Today, it is not Bernays or tobacco companies attempting to leverage psychology for persuasion but the likes of Experian, IBM, Cambridge Analytica, and other companies levering data from the internet. As investigations into psychometric profiling and data collection continue, efforts to enhance their influence will too.

Varoon Bashyakarla is a data scientist and researcher at the Tactical Technology Collective. His past statistical undertakings led him to a variety of domains: public health, public safety, sports, finance, and cybersecurity. After working as a data scientist in Silicon Valley, he is now living in Berlin and exploring how personal information is used for political influence.


I would like to thank Stephanie Hankey and Laura Ranca for their feedback on this piece.


* Icons from "The Noun Project" by zidney