̽��ֱ�� of Cambridge - Psychometrics Centre

Virtual investment experiment indicates informed consumers choose sustainable funds even with reduced returns

Anonymous — Tue, 22 Oct 2019 08:27:08 +0000

Research by the ̽��ֱ�� of Cambridge Institute for Sustainability Leadership (CISL) simulated real-world investment scenarios in order to analyse the extent the investing public values sustainability.

̽��ֱ��‘virtual investment experiment’ offered a unique, science-based rating format developed by CISL to help people understand easily the sustainable performance of funds. ̽��ֱ��study found a strong preference for sustainable investing even with a 2-3 per cent sacrifice in returns.

̽��ֱ��study also found that participants under 35 and inexperienced savers had a stronger preference for sustainable investment; while income, gender and education had no effect on preference. It also showed there was stronger preference for avoiding funds rated poorly for sustainability than for actively choosing funds with high sustainability, indicating avoiding negative environmental and social impacts is more influential in decision-making than the pursuit of positive impacts.

“ ̽��ֱ��study shows that people want more from their capital than only financial returns,” said Dr Jake Reynolds, Executive Director, Sustainable Economy, CISL. “Given the right information, they will avoid investments which harm people or the environment.

“In the real world most savers are not provided with that information; meaning they are unable to make positive choices. Given what we know about climate change, destruction of nature and high levels of inequality, that needs to change.”

‘Walking the talk: Understanding consumer demand for sustainable investing’ is a collaboration between CISL, the Department of Psychology and the Psychometrics Centre, and was commissioned by the Investment Leaders Group (ILG), which is convened by CISL.

̽��ֱ��behaviour of a sample of 2,000 US citizens was analysed to reveal insights into how their decision-making was influenced by the availability of information on the environmental and social performance of funds alongside traditional financial data.

Participants were asked to choose between pairs of funds whose fund factsheets included additional information related to sustainability. In order to simulate real-world behaviours, participants knew they had a chance of receiving a financial investment of $1,000 in the fund of their choice.

̽��ֱ��typical fund factsheets’ additional clear social and environmental impact information was based on a unique rating format called the Investment Impact Framework developed by CISL for the ILG. ̽��ֱ��Framework applies sound science to the measurement and communication of social and environmental fund performance.

“Our findings pave the way for more informed and more effective dialogue between the finance sector and the public about how capital should be invested,” said John Belgrove, Chair of the ILG and Senior Partner at Aon. “This couldn’t come at a more significant or appropriate time - when the world is looking to financial institutions to work towards the systemic change needed to tackle environmental and social sustainability, and climate change.”

Originally published on the CISL website.

A new study has shown that when given clear social and environmental performance data, consumers display an appetite for sustainable investment, even with lower returns.

People want more from their capital than only financial returns

Jake Reynolds

Austin Distel on Unsplash

Person using phone and laptop

̽��ֱ��text in this work is licensed under a Creative Commons Attribution 4.0 International License. Images, including our videos, are Copyright © ̽��ֱ�� of Cambridge and licensors/contributors as identified. All rights reserved. We make our image and video content available in a number of ways – as here, on our main website under its Terms and conditions, and on a range of channels including social media that permit your use and sharing of our content under their respective Terms.

Yes

Opinion: What can we learn about you from just one click?

sc604 — Tue, 14 Nov 2017 12:03:31 +0000

Whether you like it or not, almost every step you take online is recorded: the websites you visit, the purchases you make, the songs you listen to, the messages you post or read on social sites, and the pages you follow on Facebook. These digital footprints provide a treasure trove of data that can reveal not only what you like and how you see the world, but also who you are as a person.

In our research entitled “Psychological targeting as an effective approach to digital mass persuasion” published in the Proceedings of the National Academy of Science, we show that these digital footprints can be used to influence effectively the behaviour of large groups of people. By targeting consumers with persuasive messages that are tailored to their core psychological profiles (e.g. the degree to which they are extroverted or introverted) it is possible to significantly increase the likelihood that people will take a specific action, such as clicking on an ad or purchasing the promoted product.

̽��ֱ��basic principle behind this form of personalised persuasion is not new: marketing practitioners have long used behavioural and demographic data to target consumers with customised messages. What is new, however, is the ability to identify and target audiences based on psychological traits that reflect people’s preferences and needs at a much deeper and instinctual level. Prior targeting might have focused on demographic or behavioural attributes such as ‘women ages 18-45’ who searched for the term ‘Soccer World Cup on Google between 2-4pm’. Psychological targeting, however, can focus on a person’s fundamental character traits and psychological needs, which are known to explain and predict preferences in a broad variety of contexts.

Psychological targeting in action

Across three studies, we targeted more than 3.5 million users on Facebook. As of now, Facebook advertising does not allow marketers to directly target users based on their psychological traits. However, it does so indirectly by offering the possibility to target based on Facebook ‘Likes’. While previous research has shown that one can accurately predict people’s psychological traits after getting their permission to access to their Facebook profiles, we leveraged inherent features of the Facebook advertising platform to target our ads at consumer segments of different psychological profiles. For example, if liking ‘Socialising’ on Facebook correlates with the personality trait of extroversion, and liking ‘Stargate’ goes hand in hand with introversion, then targeting users associated with each of these Likes allows us to separately target extroverted and introverted audiences.

Then, we sent out persuasive appeals in the form of Facebook ads that either aligned with or ran counter to the users’ psychological profiles. Finally, we measured users’ reactions to the ads by counting which ad users clicked on (i.e. clicks) and whether users purchased the product promoted in the ad (i.e. conversions).

In one of the experiments, for instance, we chose an online beauty retailer and created customised ads that could be targeted toward either extroverts or introverts, as identified according to their Facebook Likes. We found that matching the content of persuasive messages to individuals’ psychological characteristics resulted in up to 40% more clicks and up to 50% more purchases than their mismatching or un-personalised messages. Extroverts responded more positively to advertising messages when the beauty retailer’s ad was focused on extroverted preferences and interests (e.g. showing a group of women in a social situation, dancing, and having fun, accompanied by ad copy saying: ‘Dance like no one’s watching (but they totally are)’). Meanwhile, introverts responded more positively to those ads that focused on introverted preferences (e.g. a single woman by herself in a quiet environment, enjoying her ‘me-time,’ accompanied by ad copy saying: ‘Beauty doesn't have to shout’).

Implications: the good and the bad

̽��ֱ��ability to influence the behaviour of large groups of people by tailoring persuasive messages to their psychological needs could be used to help people make better decisions, and lead healthier and happier lives. Human nature regularly encourages us to act in ways that focus on short-term benefits and neglect negative long-term consequences: just ask anyone who has ever tried to diet how difficult it is to resist the temptation of a chocolate bar and instead eat an apple. ̽��ֱ��same can be said about saving money: putting money aside for a rainy day is certainly less enjoyable in the moment than spending it on the new pair of shoes that caught your eye in a store window. So, how can psychological targeting help people overcome their human limitations?

Let’s take the example of saving money. Similar to the way psychological targeting can convince people to buy a product, it can also be used to convince people to save more. When targeting people identified as extroverts, ads could encourage them to imagine spending their savings on an exciting summer holiday with their friends in a vibrant and exhilarating city that allows them to pursue outgoing and social activities. Conversely, when targeting introverts, ads could highlight the ability to invest one’s savings in making their home a more comfortable refuge to escape the hectic outside world. In both cases, psychological targeting could help people to see the benefits of saving, and eventually save more.

On the other hand, psychological targeting could be used to exploit weaknesses in people’s character and persuade them to take action against their best interest. For example, online casinos could target ads at individuals who have psychological traits associated with pathological gambling. In fact, psychological targeting has been covered extensively in the context of its ability to influence the outcome of elections. While the veracity of these claims remains uncertain, our findings illustrate how psychological mass persuasion could be used to manipulate people to behave in ways that are neither in their best interest nor in the best interest of society.

Next steps: fuelling a critical debate

Our findings show that psychological targeting works. ̽��ֱ��technology is not science fiction; it exists today. To us, the most important discussion we need to have now is not what may or may not have happened in the past, but what we as individuals and as a society can and should do moving forward. Key questions that need to be answered in a critical public discourse are:

How do we as consumers and society-at-large want to use this new technology? In what settings do we want to facilitate its application, and when do we want to restrict it? For which purposes should we use it, for which should we not? Under which agreements should we be allowed to implement it, and with which required a degree of transparency?

̽��ֱ��reason we started this research was to provide empirical evidence for the effectiveness of psychological targeting. Our hope is that these findings can support the public debate on this topic by showing both the general public and key decision makers – such as elected officials and business leaders – just how important and timely this topic is. Our belief is that by having an open and transparent discussion, solutions and checks and balances can be developed in the form of policies, regulations and technological counter-measures, which will ensure that psychological targeting serves as a driver for good rather than evil.

Adapted from a story published on Columbia ̽��ֱ��’s website.

How effective is psychological targeting in advertising? Dr Sandra Matz, a former PhD student at Cambridge now based at Columbia ̽��ֱ��, and her co-authors, including Dr David Stillwell from the Cambridge Psychometrics Centre, have published a new study which demonstrates that companies only need one Facebook ‘like’ to effectively target potential customers.

Official White House Photo by Lawrence Jackson

Members of the audience take pictures as President Barack Obama participates in a town hall meeting moderated by CEO Mark Zuckerberg at Facebook headquarters in Palo Alto, Calif. April 20, 2011

̽��ֱ��text in this work is licensed under a Creative Commons Attribution 4.0 International License. For image use please see separate credits above.

Yes

Frankly, do we give a damn…? Study finds links between swearing and honesty

ps748 — Mon, 16 Jan 2017 11:49:49 +0000

Profanity is obscene language which, in some social settings is considered inappropriate and unacceptable. It often refers to language that contains sexual references, blasphemy or other vulgar terms. It’s usually related to the expression of emotions such as anger, frustration or surprise. But profanity can also be used to entertain and win over audiences.

There are conflicting attitudes to profanity and its social impact has changed over the decades. In 1939, Clark Gable uttering the memorable line “Frankly my dear, I don’t give a damn” in the film Gone with the Wind, was enough to land the producers a $5,000 fine. Nowadays our movies, TV shows and books are peppered with profane words and, for the most part, we are more tolerant of them.

As dishonesty and profanity are both considered deviant they are often viewed as evidence of low moral standards. On the other hand, profanity can be positively associated with honesty. It is often used to express unfiltered feelings and sincerity. ̽��ֱ��researchers cite the example of President-elect Donald Trump who used swear words in some of his speeches while campaigning in last year’s US election and was considered, by some, to be more genuine than his rivals.

Dr David Stillwell, a lecturer in Big Data Analytics at the ̽��ֱ�� of Cambridge, and a co-author on the paper, says: “ ̽��ֱ��relationship between profanity and dishonesty is a tricky one. Swearing is often inappropriate but it can also be evidence that someone is telling you their honest opinion. Just as they aren’t filtering their language to be more palatable, they’re also not filtering their views. ”

̽��ֱ��international team of researchers set out to gauge people’s views about this sort of language in a series of questionnaires which included interactions with social media users.

In the first questionnaire 276 participants were asked to list their most commonly used and favourite swear words. They were also asked to rate their reasons for using these words and then took part in a lie test to determine whether they were being truthful or simply responding in the way they thought was socially acceptable. Those who wrote down a higher number of curse words were less likely to be lying.

A second survey involved collecting data from 75,000 Facebook users to measure their use of swear words in their online social interactions. ̽��ֱ��research found that those who used more profanity were also more likely to use language patterns that have been shown in previous research to be related to honesty, such as using pronouns like “I” and “me”. ̽��ֱ��Facebook users were recruited from across the United States and their responses highlight the differing views to profanity that exist between different geographical areas. For example, those in the north-eastern states (such as Connecticut, Delaware, New Jersey and New York) were more likely to swear whereas people were less likely to in the southern states (South Carolina, Arkansas, Tennessee and Mississippi).

Reference

Gilad Feldman et al “Frankly, we do give a damn: ̽��ֱ��relationship between profanity and honesty” DOI:10.1177/1948550616681055

It’s long been associated with anger and coarseness but profanity can have another, more positive connotation. Psychologists have learned that people who frequently curse are being more honest. Writing in the journal Social Psychological and Personality Science a team of researchers from the Netherlands, the UK, the USA and Hong Kong report that people who use profanity are less likely to be associated with lying and deception.

Swearing is often inappropriate but it can also be evidence that someone is telling you their honest opinion. Just as they aren't filtering their language to be more palatable, they're also not filtering their views

David Stillwell

debaird

Swear word

̽��ֱ��text in this work is licensed under a Creative Commons Attribution 4.0 International License. For image use please see separate credits above.

Yes

Licence type:

Attribution-ShareAlike

How to read a digital footprint

fpjl2 — Tue, 23 Jun 2015 08:00:53 +0000

In 2007, Dr David Stillwell built an application for an online networking site that was starting to explode: Facebook. His app, myPersonality, allowed users to complete a range of psychometric tests, get feedback on their scores and share it with friends. It went viral.

By 2012, more than six million people had completed the test, with many users allowing researchers access to their profile data. This huge database of psychological scores and social media information, including status updates, friendship networks and ‘Likes’, is the largest of its kind in existence. It contains the moods, musings and characteristics of millions – a holy grail of psychological data unthinkable until a few years ago.

Stillwell and colleagues at Cambridge’s Psychometrics Centre provided open access to the database for other academics. Academic researchers from over 100 institutions globally now use it, producing 39 journal articles since 2011.

Meanwhile, the Cambridge Psychometrics team devised their own complex algorithms to read patterns in the data. Resulting publications caused media scrums, with a paper published in early 2015 generating nervous headlines around the world about computers knowing your personality better than your parents.

But how surprising is this really, given the amount we casually share about ourselves online every day? And not just through social media, but also through web browsing, internet purchases, and so on. Every interaction creates a trace, which all add up to a ‘digital footprint’ of who we are, what we do and how we feel.

We know that, behind closed doors, corporations and governments use this data to ‘target’ us – our online actions mark us out as future customers, or even possible terrorists – and, for many, this reduction in privacy is a disturbing fact of 21st-century life.

̽��ֱ��Cambridge researchers believe that the new era of psychological ‘big data’ can be used to improve commercial and government services as well as furthering scientific research, but openness is essential.

“If you ask a company to make their data available for research, usually it will go to some corporate responsibility office which deems it too risky – there’s nothing in it for them. Whereas if you tell them you can improve their business, but as part of that they make some data available to the research community, you find a lot more open doors,” says Stillwell, who co-directs the Centre.

Around half of the Centre’s current work involves commercial companies, who come to them for “statistical expertise combined with psychological understanding” – often in an attempt to improve online marketing, an area still in its infancy.

̽��ֱ��team has recently launched an interface called Apply Magic Sauce, based on the myPersonality results, which can be used as a marketing and research tool that turns digital ‘footprints’ into psycho-demographic profiles.

“If you use the internet you will be targeted by advertisers, but at the moment that targeting happens in the shadows and isn’t particularly accurate,” says Vesselin Popov, the Centre’s development strategist.

“We all have to suffer advertising, so perhaps it’s better to be recommended products that we might actually want? Using opt-in anonymous personality profiling based on digital records such as Facebook Likes or Last.fm scores could vastly improve targeted advertising and allow users to set the level of data-sharing they are comfortable with,” says Popov. “This data could then, with the permission of users, be used to enrich scientific research databases.”

Measuring psychological traits has long been difficult for researchers and boring for participants, usually involving laborious questionnaires. This will sound familiar to anyone who has used an employment agency or job centre. ̽��ֱ��team are now building on their previous work with algorithms to take psychometric testing even further into uncharted territory – video games. Job centres might be the first to benefit.

“A job centre gets about seven minutes with each job seeker every two weeks, so providing personalised support in that time is challenging,” explains Stillwell. “We are working with a company to build a game that measures a person’s strengths in a ‘gamified’ way that’s engaging but still accurate.”

In ‘JobCity’, currently an iPad proof of concept, users explore job opportunities in a simulated city. ̽��ֱ��game measures psychological strengths and weaknesses along the way, offering career suggestions at the end, and providing the job centre with feedback to help them guide the applicant. ̽��ֱ��team has tested the game with a group of under-25s and the results are promising.

For the Centre’s Director Professor John Rust, the team’s background in psychology means they don’t lose sight of the people within the oceans of data: “We’re dealing with organisations that are using ‘big data’ to make actuarial decisions about who gets lent money, who gets a job – you don’t want this left solely to computer engineers who just see statistics.”

“We want machines that can recognise you as a person. Much of the information for doing that already exists in the servers of Google, Facebook, Amazon, and so on. Your searches and statuses are all reflections of questions, experiences and emotions you have: all psychometric data. It’s the basis for a future where computers can truly interact with human beings.”

Cyberspace has, for Rust, opened a ‘Pandora’s box’ that’s taken psychological testing to a new level. But, he says, the current explosion in big data bears comparison to a previous shift that happened a century ago – the advent of IQ tests shortly before the First World War. Millions of servicemen were tested to determine role allocation within the military. Suddenly, says Rust, overexcited scientists had massive psychological datasets. IQ tests influenced societies long after the war, leading he says to some of the most shameful episodes of the 20th century including scientific racism and sterilisation of the ‘feebleminded’.

“Today you have another psychological big data situation being used to challenge a perceived global threat: terrorism. Government data scientists hunting would-be terrorists are enthusiastically adopting big data, but there will be social consequences again. In many ways, we already have Big Brother – whatever that now means,” Rust says.

“ ̽��ֱ��new psychological data revolution needs serious research, and ethical debates about it need to be happening in the public arena – and they’re not. We have a responsibility to say to people working on this in secret in companies and institutions: ‘You’ve got to come and discuss this in an open place’. It’s what universities are for.”

Inset images: Facebook's Infection (Ksayer1); Dr David Stillwell, Professor John Rust and Vesselin Popov ( ̽��ֱ�� of Cambridge).

Researchers are using social media data to build a picture of the personalities of millions, changing core ideas of how psychological profiling works. They say it could revolutionise employment and commerce, but the work must be done transparently.

Your searches and statuses are all reflections of questions, experiences and emotions you have: all psychometric data. It’s the basis for a future where computers can truly interact with human beings

John Rust

malavoda

Footprints

̽��ֱ��text in this work is licensed under a Creative Commons Attribution 4.0 International License. For image use please see separate credits above.

Yes

Licence type:

Attribution-Noncommerical

New index of children’s ‘school readiness’ highlights importance of family support

cjb250 — Wed, 27 May 2015 23:00:09 +0000

Researchers at the ̽��ֱ�� of Cambridge Centre for Family Research and Psychometrics Centre have completed a study in which they developed the simple questionnaire for teachers, dubbed the Brief Early Skills and Support Index (BESSI).

̽��ֱ��government has indicated that it wishes to introduce testing for all children at Reception (when they first enter school at age four) in September this year. These tests seek to provide baseline assessments of a child’s ‘school readiness.’ However, the proposals have been criticised by several teaching organisations as being too narrowly focused and likely to add to the difficulties of an already challenging period for both children and their teachers.

“If schools are to deliver the extra support needed to help children make a successful transition to school, some form of assessment is required, but the tests due to be introduced in September are not what teachers need: they are labour-intensive and potentially stressful for four-year-olds,” says Professor Claire Hughes from the Centre for Family Research, who led the research.

“Teachers need something that is brief but reliable and that harnesses their own skills and experience to identify children in need of extra support. A short teacher questionnaire such as the BESSI could provide all the necessary information and be easier to implement.”

̽��ֱ��Cambridge study was a study commissioned by Frank Field MP who, following his 2010 report, ̽��ֱ��Foundation Years: how to prevent poor children becoming poor adults set up and now chairs the Foundation Years Trust. Part of the Trust’s work is to develop, implement and promote life chance indicators, which are seen as playing a key role in driving policy and incentivising a focus on improving children’s long-term life chances.

̽��ֱ��BESSI questionnaire is unique in being both brief (one page) and broad (including, for example, items about the kinds of support children receive at home). A previous, much longer questionnaire, the Early Development Instrument (EDI), was designed by a Canadian research team and has enabled teachers in Australia to profile the development and wellbeing of more than 260,000 five-year-olds. This national census revealed worrying regional disparities in the proportion of children with ‘developmental vulnerabilities’, with clear policy implications for mobilizing extra support. However, the EDI is not appropriate for use in the UK because British children start formal schooling one year earlier than children almost everywhere else in the world – a significant time difference in terms of a child’s development and a source of concern for many.

Professor Hughes and colleagues carried out focus groups with teachers in Field’s Birkenhead constituency with a view to getting a first-hand view of variation in children’s school readiness. This highlighted an additional problem: a lack of consensus on how ‘school readiness’ should be defined.

Researchers in the USA have noted that for politicians, whose primary interest is in the extent to which schools produce employable young adults, school readiness hinges on achieving foundation skills in literacy and numeracy. As Professor Hughes explained, “For teachers, who face the more immediate challenge of 30 small children in a confined space, the obvious starting point is children’s behaviour and emotional and social development.”

Defining school readiness is also complicated by the fact that learning takes many forms – from ‘surface learning’ (e.g. letter recognition) to ‘deep learning’ (e.g. finding patterns or principles). Some theorists argue that the very term ‘school readiness’ is intrinsically unfair, in that it appears to place the burden of responsibility on the child. ̽��ֱ��Cambridge researchers noted that a lack of educational support at home was a frequent issue raised by teachers.

To address these various problems, the researchers developed and piloted the BESSI. So far, this has been tested in three waves involving schools and nurseries in the Wirral, in London and in Manchester. ̽��ֱ��first wave was with teachers of over 800 children in Reception, the second was with nursery staff working with a similar number of much younger children, and the third was with teachers of a further 270 children to check the reliability of BESSI ratings.

Amongst other factors, the BESSI provides information about children’s social and behavioural adjustment (e.g. are they able to play with other children or to wait their turn?) as well as measures of their daily living skills (e.g. can they use cutlery and can they go the toilet by themselves?) and language / cognitive skills. Importantly, it also captures variation in family support and includes items about reading, praise and fun at home. ̽��ֱ��findings around fun are particularly interesting as they indicate that parental support is not simply a matter of regular reading at home – although there may be a virtuous circle by which parents and children who have fun together are also more likely to read together.

As the researchers expected, some problems, such as distractibility and trouble sitting still, were very common, even among the older children in the sample. However, the BESSI also provided some surprising insights. First, not only were problems typically almost twice as common in boys as in girls, but these gender differences were also evident in family support. For example, compared with girls, boys received much lower ratings of ‘fun at home’.

Second, children from low-income families lagged behind their more affluent peers – but these differences were removed when scores for family support were taken into account. In other words, when families facing financial difficulties are still able to have fun together, the children appear better prepared for school – but teachers’ ratings indicated that fun at home was often lacking.

“We should not blame parents who provide low levels of support, or recast problems of inequality as a matter of parental responsibility, or let these findings detract from efforts to reduce inequality in order to give all children a fair start in life,” adds Professor Hughes. “Instead, our hope is that the BESSI will help educational professionals support all children, regardless of family background, who display difficulties during the transition to school or nursery.”

̽��ֱ��research was funded by the Westminster Foundation and the Foundation Years Trust.

Reference
Hughes, C et al. Measuring the foundations of school readiness: Introducing a new questionnaire for teachers – ̽��ֱ��Brief Early Skills and Support Index (BESSI). British Journal of Educational Psychology; 8 May 2015

̽��ֱ��importance of family support on a child’s ‘school readiness’ is highlighted in a study published this month in the British Journal of Educational Psychology. Researchers developed and piloted a new index that might provide a simple and stress-free alternative to the government’s proposed baseline assessments for four-year-olds starting school.

̽��ֱ��tests due to be introduced in September are not what teachers need: they are labour-intensive and potentially stressful for four-year-olds

Claire Hughes

Martin Abegglen

Back to school (crop)

̽��ֱ��text in this work is licensed under a Creative Commons Attribution 4.0 International License. For image use please see separate credits above.

Yes

Licence type:

Attribution-ShareAlike

Computers using digital footprints are better judges of personality than friends and family

fpjl2 — Mon, 12 Jan 2015 20:05:04 +0000

A new study, published today in the journal PNAS, compares the ability of computers and people to make accurate judgments about our personalities. People's judgments were based on their familiarity with the judged individual, while computer models used a specific digital signal: Facebook Likes.

̽��ֱ��results show that by mining Facebook Likes, the computer model was able to predict a person's personality more accurately than most of their friends and family. Given enough Likes to analyse, only a person's spouse rivalled the computer for accuracy of broad psychological traits.

Researchers at the ̽��ֱ�� of Cambridge and Stanford ̽��ֱ�� describe the finding as an "emphatic demonstration" of the capacity of computers to discover an individual's psychological traits through pure data analysis, showing machines can know us better than we'd previously thought: an "important milestone" on the path towards more social human-computer interactions.

"In the future, computers could be able to infer our psychological traits and react accordingly, leading to the emergence of emotionally-intelligent and socially skilled machines," said lead author Wu Youyou, from Cambridge's Psychometrics Centre.

"In this context, the human-computer interactions depicted in science fiction films such as Her seem to be within our reach."

̽��ֱ��researchers say these results might raise concerns over privacy as such technology develops; the research team support policies giving users full control of their digital footprint.

In the study, a computer could more accurately predict the subject's personality than a work colleague by analysing just ten Likes; more than a friend or a cohabitant (roommate) with 70, a family member (parent, sibling) with 150, and a spouse with 300 Likes.

Given that an average Facebook user has about 227 Likes (and this number is growing steadily), the researchers say that this kind of AI has the potential to know us better than our closest companions.

̽��ֱ��latest results build on previous work from the ̽��ֱ�� of Cambridge, published in March 2013, which showed that a variety of psychological and demographic characteristics could be predicted with startling accuracy through Facebook Likes.

In the new study, researchers used a sample of 86,220 volunteers on Facebook who completed a 100-item personality questionnaire through the 'myPersonality' app, as well as providing access to their Likes.

These results provided self-reported personality scores for what are known in psychological practice as the 'big five' traits: openness, conscientiousness, extraversion, agreeableness, and neuroticism— the OCEAN model. Through this, researchers could establish which Likes equated with higher levels of particular traits e.g. liking 'Salvador Dali' or 'meditation' showed a high degree of openness.

Users of the 'myPersonality' app were then given the option of inviting friends and family to judge the psychological traits of the user through a shorter version of the personality test. These were the human judges in the study—those listed on Facebook as friends or family expressing their judgement of a subject's personality using a 10-item questionnaire

Researchers were able to get a sample of 17,622 participants judged by one friend or family member, and a sample of 14,410 judged by two.

To gauge the accuracy of these measurements, the online personality judgements were corroborated with a meta-analysis of previous psychological studies over decades which looked at how people's colleagues, family and so on judge their personality. Researchers found their online values similar to the averages from years of person-to-person research.

In this way, the researchers were able to come up with accuracy comparisons between computer algorithms and the personality judgements made by humans. Given enough Likes, the computers came closer to a person's self-reported personality than their brothers, mothers or partners.

Dr Michal Kosinski, co-author and researcher at Stanford, says machines have a couple of key advantages that make these results possible: the ability to retain and access vast quantities of information, and the ability to analyse it with algorithms the techniques of 'Big Data'.

"Big Data and machine-learning provide accuracy that the human mind has a hard time achieving, as humans tend to give too much weight to one or two examples, or lapse into non-rational ways of thinking," he said. Nevertheless, the authors concede that detection of some traits might be best left to human abilities, those without digital footprints or dependant on subtle cognition.

̽��ֱ��authors of the study write that automated, accurate, and cheap personality assessments could improve societal and personal decision-making in many ways—from recruitment to romance.

" ̽��ֱ��ability to judge personality is an essential component of social living— from day-to-day decisions to long-term plans such as whom to marry, trust, hire, or elect as president," said Cambridge co-author Dr David Stillwell. " ̽��ֱ��results of such data analysis can be very useful in aiding people when making decisions."

Youyou explains: "Recruiters could better match candidates with jobs based on their personality; products and services could adjust their behaviour to best match their users' characters and changing moods.

"People may choose to augment their own intuitions and judgments with this kind of data analysis when making important life decisions such as choosing activities, career paths, or even romantic partners. Such data-driven decisions may well improve people's lives," she said.

̽��ֱ��researchers say that this kind of data mining and its inferences has hallmarks of techniques currently used by some digital service providers, and that—for many people— a future in which machines read our habits as an open book on a massive scale may seem dystopian to those concerned with privacy.

It's a concern shared by the researchers. "We hope that consumers, technology developers, and policy-makers will tackle those challenges by supporting privacy-protecting laws and technologies, and giving the users full control over their digital footprints," said Kosinski.

Take the Facebook personality test yourself here: applymagicsauce.com

Researchers have found that, based on enough Facebook Likes, computers can judge your personality traits better than your friends, family and even your partner. Using a new algorithm, researchers have calculated the average number of Likes artificial intelligence (AI) needs to draw personality inferences about you as accurately as your partner or parents.

People may choose to augment their own intuitions and judgments with this kind of data analysis when making important life decisions

Wu Youyou

Ksayer1

Facebook's Infection

Some example personality traits and associated Likes

Liberal & artistic	Shy & reserved	Cooperative	Calm & relaxed
TED	J-pop	Life of Pi	Ferrari
John Coltrane	Minecraft	the Bible	Volunteering
̽��ֱ��Daily Show	Wikipedia	smiling	Usain Bolt
Atheism	̽��ֱ��X-Files	Bourne Identity	Kayaking

̽��ֱ��text in this work is licensed under a Creative Commons Licence. If you use this content on your site please link back to this page. For image rights, please see the credits associated with each individual image.

Yes

Licence type:

Attribution-ShareAlike

Digital records could expose intimate details and personality traits of millions

fpjl2 — Mon, 11 Mar 2013 18:49:49 +0000

New research, published today in the journal PNAS, shows that surprisingly accurate estimates of Facebook users’ race, age, IQ, sexuality, personality, substance use and political views can be inferred from automated analysis of only their Facebook Likes - information currently publicly available by default.

In the study, researchers describe Facebook Likes as a “generic class” of digital record - similar to web search queries and browsing histories - and suggest that such techniques could be used to extract sensitive information for almost anyone regularly online.

Researchers at Cambridge’s Psychometrics Centre, in collaboration with Microsoft Research Cambridge, analysed a dataset of over 58,000 US Facebook users, who volunteered their Likes, demographic profiles and psychometric testing results through the myPersonality application.

Users opted in to provide data and gave consent to have profile information recorded for analysis. Facebook Likes were fed into algorithms and corroborated with information from profiles and personality tests.

Researchers created statistical models able to predict personal details using Facebook Likes alone. Models proved 88% accurate for determining male sexuality, 95% accurate distinguishing African-American from Caucasian American and 85% accurate differentiating Republican from Democrat. Christians and Muslims were correctly classified in 82% of cases, and good prediction accuracy was achieved for relationship status and substance abuse – between 65 and 73%.

But few users clicked Likes explicitly revealing these attributes. For example, less that 5% of gay users clicked obvious Likes such as Gay Marriage. Accurate predictions relied on ‘inference’ - aggregating huge amounts of less informative but more popular Likes such as music and TV shows to produce incisive personal profiles.

Even seemingly opaque personal details such as whether users’ parents separated before the user reached the age of 21 were accurate to 60%, enough to make the information “worthwhile for advertisers”, suggest the researchers.

While they highlight the potential for personalised marketing to improve online services using predictive models, the researchers also warn of the threats posed to users’ privacy. They argue that many online consumers might feel such levels of digital exposure exceed acceptable limits - as corporations, governments, and even individuals could use predictive software to accurately infer highly sensitive information from Facebook Likes and other digital ‘traces’.

̽��ֱ��researchers also tested for personality traits including intelligence, emotional stability, openness and extraversion. While such latent traits are far more difficult to gauge, the accuracy of the analysis was striking. Study of the openness trait – the spectrum of those who dislike change to those who welcome it – revealed that observation of Likes alone is roughly as informative as using an individual’s actual personality test score.

Some Likes had a strong but seemingly incongruous or random link with a personal attribute, such as Curly Fries with high IQ, or That Spider is More Scared Than U Are with non-smokers.

When taken as a whole, researchers believe that the varying estimations of personal attributes and personality traits gleaned from Facebook Like analysis alone can form surprisingly accurate personal portraits of potentially millions of users worldwide.

They say the results suggest a possible revolution in psychological assessment which – based on this research – could be carried out on an unprecedented scale without costly assessment centres and questionnaires.

“We believe that our results, while based on Facebook Likes, apply to a wider range of online behaviours.” said Michal Kosinski, Operations Director at the Psychometric Centre, who conducted the research with his Cambridge colleague David Stillwell and Thore Graepel from Microsoft Research.

“Similar predictions could be made from all manner of digital data, with this kind of secondary ‘inference’ made with remarkable accuracy - statistically predicting sensitive information people might not want revealed. Given the variety of digital traces people leave behind, it’s becoming increasingly difficult for individuals to control.

“I am a great fan and active user of new amazing technologies, including Facebook. I appreciate automated book recommendations, or Facebook selecting the most relevant stories for my newsfeed,” said Kosinski. “However, I can imagine situations in which the same data and technology is used to predict political views or sexual orientation, posing threats to freedom or even life.”

“Just the possibility of this happening could deter people from using digital technologies and diminish trust between individuals and institutions – hampering technological and economic progress. Users need to be provided with transparency and control over their information.”

Thore Graepel from Microsoft Research said he hoped the research would contribute to the on-going discussions about user privacy: “Consumers rightly expect strong privacy protection to be built into the products and services they use and this research may well serve as a reminder for consumers to take a careful approach to sharing information online, utilising privacy controls and never sharing content with unfamiliar parties.”

David Stillwell from Cambridge ̽��ֱ�� added: “I have used Facebook since 2005, and I will continue to do so. But I might be more careful to use the privacy settings that Facebook provides.”

For more information, please contact fred.lewsey@admin.cam.ac.uk

Research shows that intimate personal attributes can be predicted with high levels of accuracy from ‘traces’ left by seemingly innocuous digital behaviour, in this case Facebook Likes. ̽��ֱ��study raises important questions about personalised marketing and online privacy.

Similar predictions could be made from all manner of digital data, with this kind of secondary ‘inference’ made with remarkable accuracy

Michal Kosinski

Cambridge Psychometrics Centre

Graphic from mypersonality app

This work is licensed under a Creative Commons Licence. If you use this content on your site please link back to this page.

Yes

Are we being sold online?

fpjl2 — Sat, 27 Oct 2012 08:00:06 +0000

One in every nine people on Earth is on Facebook and the average Briton devotes an entire day to the site each month. Personal information, much of it volunteered, has become so prevalent and readily available that for many it constitutes the most powerful marketing tool in human history. ̽��ֱ��question is, how is this information being used, and by whom? And, should we be worried?

Listen to the debate here:

From 3:30pm on Saturday afternoon (27 October) at the Faculty of Law, a panel of experts will explore the questions that surround the dream of global connectivity, and the nightmare of human commodity, as part of this year’s Festival of Ideas.

From social interactions, entertainment, shopping, and gathering information, almost any human activity you can think of is now mediated digitally. As such, these behaviours can easily be recorded and analysed, fuelling the emergence of personalised search engines, recommender systems, and targeted online marketing.

This raises highly sensitive questions about privacy and data ownership. Who should have access to such an extraordinarily powerful reservoir of information, and where it should be stored?

“ ̽��ֱ��widespread availability of extensive records of individual behaviour, and the desire to learn more about customers and citizens presents serious challenges to future society, particularly in relation to trust,” says Michal Kosinski, Director of Operations for the ̽��ֱ��’s Psychometrics Centre and Leader of the e-Psychometrics Unit.

“Trust between consumers and corporations, governments and their citizens, families even can be seriously harmed once people realize how exposed they are in the digital environment. It can all still seem quite innocent, with Facebook ‘likes’ and photos of friends, but new research is starting to show that this seemingly harmless information can be used to make very accurate inferences of highly sensitive traits.”

Kosinski, one of the panellists, spends much of his time cultivating and analysing the increasingly immense tracts of data in order to show the precision with which estimations can be made about personality traits, such as openness, extroversion and stability.

“Never before have we had access to such comprehensive behavioural data about consumers,” says Kosinski. “A marketing revolution is upon us, a completely new dimension is added through the combination of scientifically robust personality tests and other demographic information.”

̽��ֱ��other panellists are William Dutton, Professor of Internet Studies at the ̽��ֱ�� of Oxford’s Internet Institute, Nick Pickles, Director of the civil liberties and privacy campaign group Big Brother Watch, and Mariam Cook, Senior Digital Consultant at PR firm Porter Novelli.

“ ̽��ֱ��web connects us more closely than ever before, giving organisations and brands the capability to understand us, target us, and to fulfil our needs and desires in increasingly sophisticated ways,” says Cook. “This presents many fantastic opportunities for marketers, and potential delights for those formerly known as the audience, but it also means great responsibility lies on our shoulders.”

“This presents a challenge - how to balance the apparently conflicting ideals of privacy and openness in all of our data dealings.”

But for Nick Pickles, the increasingly heard motto ‘if we're not paying to use a service, then we're the product’ is at the very core of this issue: “Our personal data is the oil of the internet age and yet we have grown oblivious to how our every movement is being monitored and analysed for commercial gain.”

“As an entire generation outsources it's privacy to social media companies, I believe strengthening individual privacy will soon become a social necessity and a commercial imperative.”

Panel discussion ‘Are we being sold online?’ starts at 3.30pm on Saturday 27 October at the Faculty of Law. With Michal Kosinski, Cambridge's Psychometrics Centre; Professor William Dutton, Oxford Internet Institute; Nick Pickles, Big Brother Watch; Mariam Cook, Porter Novelli and the Chair, Spencer Kelly, Click presenter.

A panel discussion for the Festival of Ideas examines whether social media giants are profiting from our willingness to share the most intimate details of our lives online, and whether we should be worried by this compromise to our privacy.

Never before have we had access to such comprehensive behavioural data about consumers.

Michal Kosinski

Ed Yourdon from flickr

Thinkin' about the code

This work is licensed under a Creative Commons Licence. If you use this content on your site please link back to this page.

Yes

̽��ֱ�� of Cambridge - Psychometrics Centre

Virtual investment experiment indicates informed consumers choose sustainable funds even with reduced returns

Opinion: What can we learn about you from just one click?

Frankly, do we give a damn…? Study finds links between swearing and honesty

How to read a digital footprint

New index of children’s ‘school readiness’ highlights importance of family support

Computers using digital footprints are better judges of personality than friends and family

Liberal & artistic

Shy & reserved

Cooperative

Calm & relaxed

Digital records could expose intimate details and personality traits of millions

Are we being sold online?