Psychology and social data

Stephen Haggard & David Stillwell
24 September 2013, Social Media Week
Scientific approach to
personality prediction

“digital records of behavior can be used to
automatically and accurately pr...
What can we predict?
High
Outgoing & Active

Beerpong
Michael Jordan
Dancing
Socializing
Chris Tucker
I Feel Better Tan
Modeling
Cheerleading
T...
Yes

When Ur Single, All U See Is Happy Couples N
Wen Ur In A Relationship All U See Is Happy
Singles
Never Apologize For ...
Case Study: Integrations to 3rd
party front ends using
Business Applications
of

Psychological Data

CRM

SSP platforms
Brand Strategy
CRM ENHANCEMENT
JUSTGIVING.COM

NAME
DATE OF PRESENTATION
New ways to understand
CRM data
17 mn customer IDs with transaction history
Currently clustered in 13 sociio-demographic/ ...
Outcomes
Overall personality skew of customers: competitive
Yield predictors – alternative algorithm and model
Category mo...
Business Applications
of

Psychological Data

CRM
SSP platforms

Brand Strategy
Relentless Energy
Campaign Strategy
Energy Drinkers’ FB Likes
Lower and Upper age quartiles
oceans thirteen
flushed away
chicken run
saving the world
Prochoic...
Working with 100 billion Likes
Music choice is a personality index
Find similar personalities
Music-Personality scale
Dimension: agreeableness

Behemoth
Deicide
Dark Funeral
Gorgoroth

Phil Wickham
Kari Jobe
Kim Walk...
Case Study: Jabra for Grey
POWERPOINT TEMPLATE TITLE
SUB HEADLINE IN HERE

Lorem ipsum dolor sit amet, consectetuer adipiscing elit, sed diam nonummy...
the problem
know the personality of these people

…and use this to drive campaign insight, creative and media

When we don...
using psychometrics
• Data points for inner psychological landscapes
• Exploit non-rational side of consumer
instinct 

e...
myPersonality database
psychological data for beats by dr. dre Likers
psychometric data
for audio-tech sector

Distinctive sector
patterns in dimensions of
• Conscientiousness
• Agreeableness
...
constructed psychometric for Jabra
based on sectoral distinctive psychometric features

adjust for client aspirations: cou...
calibrate personalities: Jabra vs. beats by dr dre
openness

conscientiousness

extraversion

agreeablenes
s
stability
Thank you
Stephen Haggard
stephen@mypersonality.com
David Stillwell
david@mypersonality.com
Smarter Marketing using Psychological information layer from PersonalityHQ
Smarter Marketing using Psychological information layer from PersonalityHQ
Smarter Marketing using Psychological information layer from PersonalityHQ
Upcoming SlideShare
Loading in …5
×

Smarter Marketing using Psychological information layer from PersonalityHQ

534 views

Published on

Slides presented at Social Media Week 2013 (September) by PersonalityHQ. We have data and tools for unobtrusively appending an information layer about personality to customer records, brands and audience tools.

Published in: Marketing, Technology, Business
0 Comments
0 Likes
Statistics
Notes
  • Be the first to comment

  • Be the first to like this

No Downloads
Views
Total views
534
On SlideShare
0
From Embeds
0
Number of Embeds
3
Actions
Shares
0
Downloads
3
Comments
0
Likes
0
Embeds 0
No embeds

No notes for slide
  • Easiest vs. hardest
  • Examples, and why
  • Universe of Likes clustered and decomposed into 200 groups of LikesSky Sport, Wayne Rooney, Man U, England Football Team – call it “Top male sport”Ignorecolourfornow, coming to that in a minute, this cluster plot can be shaded for any characteristic eg social-dem or psycho-dem (here:conscientiousness turquoise low pink high)
  • Now add the psychological information from the surveysSimilarly fiddly bit of statistics to average and aggregate the effects Relentless likers – 65 have done me a personality survey
  • We can arrange all the music objects by overlap and put a layer of information about personality over themWhere you see similar colours clustering, that personality factor is predicting behaviour well. Here, agreeableness scores are not highly predictive. These guys are linked by shared habitsBut here, psychological similarity is a good link
  • Put Relentless and Monster in the map – Monster is in a different space, it is a small cluster of low AGR people in a predominantly high AGR music space. Hard to find closely connected music tastes for Relentless, though Monster can be helped by overlap, Relentless needs help from psychologyThe AGR score (blue: works alone, competitive) can be shared by different taste and behaviour groups
  • Better separation and more chance to hurt Red Bull without denting Monster
  • Smarter Marketing using Psychological information layer from PersonalityHQ

    1. 1. Psychology and social data Stephen Haggard & David Stillwell 24 September 2013, Social Media Week
    2. 2. Scientific approach to personality prediction “digital records of behavior can be used to automatically and accurately predict a range of highly sensitive personal attributes” March 2013 We have published a unique and peer-reviewed method, based on large data samples and advanced statistical methods, for predicting personality attributes
    3. 3. What can we predict?
    4. 4. High Outgoing & Active Beerpong Michael Jordan Dancing Socializing Chris Tucker I Feel Better Tan Modeling Cheerleading Theatre Flip Cup RPGs Fanfiction.Net Programming Anime Manga Video Games Role Playing Games Minecraft Voltaire Terry Pratchet Liberal & Artistic Oscar Wilde Charles Bukowski Sylvia Plath Leonardo Da Vinci Bauhaus Dmt The Spirit Molecule American Gods John Waters Plato Leonard Cohen NASCAR Austin Collie Monster-In-Law I don’t read Justin Moore ESPN2 Farmlandia The Bachelor Oklahoma State University Teen Mom 2 Conservative Extraversion Jason Aldean Tyler Perry Sephora Chiq Bret Michaels Clark Griswold Bebe I Love Being A Mom Harley Davidson Lady Antebellum Shy & Reserved Openness The Godfather Mozart Thunderstorms The Colbert Report Morgan Freemans Voice The Daily Show Lord Of The Rings To Kill A Mockingbird Science Curly Fries Low IQ Trait
    5. 5. Yes When Ur Single, All U See Is Happy Couples N Wen Ur In A Relationship All U See Is Happy Singles Never Apologize For What You Feel It’s Like Saying Sorry For Being Real I’m The Type Of Girl Who Can Be So Hurt But Still Look At You & Smile The Type Of Girl Who Is Willing To Brighten Your Day Even If I Can’t Brighten My Own <3 <3 We Don’t Talk Anymore And You Know What The Saddest Part Is We Used To Talk Everyday Come Here Nope [Grab Yu Closer] Gimme A Kiss Nope I’m Mad At Yu [Start Kissing] Tell Her She’s Pretty Hold Her Hand Kiss Her When She’s Angry Play With Her Hair Let Her Fall Asleep In Your Arms Kiss Her In The Rain Tell Her You Love Her But Waitheres The Catchyou Actually Have To Mean It You Need Anger Management Classes You Need Shut The Fukk Up Classes If I’m With You Then I’m With You I Don’t Want Anybody Else Bitch You Ain’t Pretty Your A Slut That’s Why All The Guys Talk To You I’m Sorry I Love You Apples To Apples The Helen Keller Card Deliberately Driving Slower When Being Tailgated Watching Peoples Lives Fall Apart Via Status Updates And News Feeds Every Time I See You A Voice In My Head Goes Dooouuuuccccheee Making Dirty Innuendos Out Of Perfectly Innocent Things Gene Wilder I Hate It When You’re With Mc Hammer And He Doesn’t Let You Touch Anything I Immediately Look In My Rear-view Mirror When I Pass A Cop The Joy Of Painting With Bob Ross No Parents separated at 21 Trait
    6. 6. Case Study: Integrations to 3rd party front ends using
    7. 7. Business Applications of Psychological Data CRM SSP platforms Brand Strategy
    8. 8. CRM ENHANCEMENT JUSTGIVING.COM NAME DATE OF PRESENTATION
    9. 9. New ways to understand CRM data 17 mn customer IDs with transaction history Currently clustered in 13 sociio-demographic/ functional segments • Big gesture • Support my family • Cause-passionate • Etc • Mapped onto to transactional records: poor fit 50,000 and growing FB logins - Likes harvested Possibility to append new information layer: personality
    10. 10. Outcomes Overall personality skew of customers: competitive Yield predictors – alternative algorithm and model Category model of audience segments reassessed/revised Cause allocator tool for promotions Validation of SM as rich data source Personality predictive values for non-FB IDs based on causes, giving behaviour.
    11. 11. Business Applications of Psychological Data CRM SSP platforms Brand Strategy
    12. 12. Relentless Energy Campaign Strategy
    13. 13. Energy Drinkers’ FB Likes Lower and Upper age quartiles oceans thirteen flushed away chicken run saving the world Prochoice making people smile brown university playing the drums thai iced tea cameras midnight cowboy time bandits stop human trafficking tibetan freedom boycott yellowstone Aspergers syndrome visit london aromatherapy bellydancing weird pictures
    14. 14. Working with 100 billion Likes
    15. 15. Music choice is a personality index
    16. 16. Find similar personalities
    17. 17. Music-Personality scale Dimension: agreeableness Behemoth Deicide Dark Funeral Gorgoroth Phil Wickham Kari Jobe Kim Walker Misty Edwards Low Dimension: Agreeableness (%) 18.8 47.1 56.8 High
    18. 18. Case Study: Jabra for Grey
    19. 19. POWERPOINT TEMPLATE TITLE SUB HEADLINE IN HERE Lorem ipsum dolor sit amet, consectetuer adipiscing elit, sed diam nonummy nibh euismod tincidunt ut laoreet dolore magna aliquam erat volutpat. Ut wisi enim ad minim veniam, quis nostrud exerci tation ullamcorper suscipit lobortis nisl ut aliquip. • ex ea commodo consequat. Duis autem vel eum iriure dolor in hendrerit in vulputate • velit esse molestie consequat, vel illum dolore eu feugiat nulla facilisis at vero eros et • accumsan et iusto odio dignissim qui blandit praesent luptatum zzril delenit augue • duis dolore te feugait nulla facilisi. Nam liber tempor cum soluta nobis eleifend option
    20. 20. the problem know the personality of these people …and use this to drive campaign insight, creative and media When we don’t know… • Anything more than a hypothetical persona • How their personality maps to product choice and behaviour • How to achieve the desired positioning in the sector
    21. 21. using psychometrics • Data points for inner psychological landscapes • Exploit non-rational side of consumer instinct  emotion  subconscious beats by dr. dre Likers on FB are 72 % more laid back and relaxed than the rest of the population
    22. 22. myPersonality database psychological data for beats by dr. dre Likers
    23. 23. psychometric data for audio-tech sector Distinctive sector patterns in dimensions of • Conscientiousness • Agreeableness • Stability
    24. 24. constructed psychometric for Jabra based on sectoral distinctive psychometric features adjust for client aspirations: counter-cultural, edge, authenticity, outsider
    25. 25. calibrate personalities: Jabra vs. beats by dr dre openness conscientiousness extraversion agreeablenes s stability
    26. 26. Thank you Stephen Haggard stephen@mypersonality.com David Stillwell david@mypersonality.com

    ×