Search openICPSR

Find and share social, behavioral, and health sciences research data.

  • Search terms can be anywhere in the study: title, description, variables, etc.
  • Because our holdings are large, we recommend using at least two query terms:
    rural economy
    home ownership
    higher education
    ghana adolescents
  • Keywords help delimit the breadth of results. Therefore, use as many as required to achieve your desired results:
    elementary education federal funding
  • Our search will find studies with derivative expressions of your query terms: A search for "nation" will find results containing "national"
  • Use quotes to search for an exact expression:
    "social mobility"
  • You can combine exact expressions with loose terms:
    "united states" inmates
  • Exclude results by using a MINUS sign:
    elections -sweden -germany
    elections -sweden -germany
  • On the results page, you will be able to sort and filter to further refine results.
  • Please note that your search queries only openICPSR data holdings.
Name File Type Size Last Modified
test_predict_ID.csv text/csv 173.3 KB 03/27/2019 10:38:AM

Project Citation: 

Kachur, Alexander, and Davydov, Denis. Face Shape and Personality. Ann Arbor, MI: Inter-university Consortium for Political and Social Research [distributor], 2019-03-27.

Project Description

Summary:  View help for Summary Applying Machine Learning, we are looking for a number of elusive lincks between appearance and behavior. The dataset obtained after the moderation of images and validation of questionnaires. The test (holdout) dataset included self-reported and predicted from face shape by a ML algorithm the ​​Big Five personality traits for  505 males  and 740 females. 

Scope of Project

Subject Terms:  View help for Subject Terms Human face; Big Five personality traits; Face and Behavior; Face; Machine Learning; Face and Personality
Geographic Coverage:  View help for Geographic Coverage Russian Federation
Time Period(s):  View help for Time Period(s) 2016 – 2018
Universe:  View help for Universe Anonymous participants  volunteers recruited through social network advertisements completed Big Five questionnaire and provided face photo.
Data Type(s):  View help for Data Type(s) experimental data; survey data
Collection Notes:  View help for Collection Notes Validation dataset containing randomly selected 10% (1290) of paticipant.


Sampling:  View help for Sampling
The initial sample included 25,202 participants who completed the questionnaire and uploaded a total of 77,346 photographs. The final dataset after the data screening procedures comprised 12,447 valid questionnaires and 31,367 associated photographs. 
This is a Validation dataset containtd randomly selected 10% (1290) of paticipant.
The participants ranged in age from 18 to 60 (59.4% females, M= 27.61, SD = 12.73 and 40.6% man M= 32.60, SD = 11.85).
Data Source:  View help for Data Source Participants were anonymous volunteers recruited through social network advertisements. They did not receive any financial remuneration, but they were provided with a free report on their Big Five personality traits. The data were collected online using a dedicated research website and a mobile application. Participants completed the questionnaires, reported their age and gender, and were asked to upload their photographs.
Scales:  View help for Scales

Related Publications

Published Versions

Export Metadata

Report a Problem

Found a serious problem with the data, such as disclosure risk or copyrighted content? Let us know.

This material is distributed exactly as it arrived from the data depositor. ICPSR has not checked or processed this material. Users should consult the investigator(s) if further information is desired.