Face Shape and Personality

Principal Investigator(s): View help for Principal Investigator(s) Alexander Kachur, BestFtMe ltd; Denis Davydov, Modern University for the Humanities

Version: View help for Version V1

Version Title: View help for Version Title Test dataset

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. https://doi.org/10.3886/E109082V1

Project Description

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: Human face; Big Five personality traits; Face and Behavior; Face; Machine Learning; Face and Personality

Geographic Coverage: Russian Federation

Time Period(s): 2016 – 2018

Universe: Anonymous participants volunteers recruited through social network advertisements completed Big Five questionnaire and provided face photo.

Data Type(s): experimental data; survey data

Collection Notes: Validation dataset containing randomly selected 10% (1290) of paticipant.

Methodology

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: 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:

Agreeableness

Conscientiousness

Extraversion

Neuroticism

Openness

Related Publications

Download this project

Published Versions

V1 [2019-03-27]

Export Metadata

Dublin Core

DDI 2.5

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.