five-factor-e 1.3.0

Big 5 IPIP-NEO Personality Traits

Five Factor E Library 📦

This project assesses a person's 🗣 personality based on an inventory of questions. The project uses the Big Five theory using the IPIP-NEO-120 and IPIP-NEO-300 model developed by Professor Dr. John A. Johnson, this is free representation of NEO PI-R™.

"The IPIP-NEO is not identical to the original NEO PI-R, but in my opinion it is close enough to serve as a good substitute. More and more people are beginning to use it in published research, so its acceptance is growing." - Dr. Johnson

The main idea of the project is to facilitate the use of Python developers who want to use IPIP-NEO in their projects. The project is also done in pure Python, it doesn't have any dependencies on other libraries.

Notes: The project is based on the work of Dhiru Kholia, and is an adaptation of Neural7 for a version that can be reused in other projects of the company.

Synopsis 🌐

A little theory, the The Big Five or Five Factor is made up of 5 great human personalities also known as the O.C.E.A.N. Are they:

• Openness
• Conscientiousness
• Extraversion
• Agreeableness
• Neuroticism

To compose each great personality there are 6 traits or facets, totaling 30 traits. The user must answer a questionnaire of 120 or 300 single-choice questions. The user must answer an inventory of questions where each answer can have a unique and mandatory choice with 5 options:

• Very Inaccurate
• Moderately Inaccurate
• Neither Accurate Nor Inaccurate
• Moderately Accurate
• Very Accurate

For more information to demystify the Big Five, please see the article: Measuring the Big Five Personality Domains

Notes: User-selected answers follow the position:

Option	Array
Very Inaccurate	1
Moderately Inaccurate	2
Neither Accurate Nor Inaccurate	3
Moderately Accurate	4
Very Accurate	5

Installation 🚀

The simplest way is to use PIP, like the command:

$ pip install five-factor-e

How to use 🔥

The answers must be in a standardized json, you can enter this template in the project folder data. To calculate the Big Five use the code snippet below:

from ipipneo import IpipNeo

IpipNeo(question=120).compute(sex=<>, age=<>, answers=JSON_STANDARD)

As an example you can load the project json to test.

import json, urllib.request

data = urllib.request.urlopen("https://raw.githubusercontent.com/neural7/five-factor-e/main/data/IPIP-NEO/120/answers.json").read()
answers = json.loads(data)

Calculate the Big Five for a 40-year-old man:

IpipNeo(question=120).compute(sex="M", age=40, answers=answers)

For a 25 year old woman:

IpipNeo(question=120).compute(sex="F", age=25, answers=answers)

Tests 🏗

For the tests it is necessary to download the repository. To run the unit tests use the command below:

$ ./run-test

If you want to make an assessment by answering the inventory of questions, just run:

$ python3 quiz.py

About data 📊

Inside the data data directory, there are examples of questions and answers. The most important is the response data entry which must follow the pattern of this file. Example:

{
   "answers":[
      {
         "id_question":50,
         "id_select":5
      },
      {
         "id_question":51,
         "id_select":2
      }
   ]
}

Notes: The order of answers does not affect the result.

The id question field refers to the question in this file. Obviously you may want to change the form of the questions, we are working on the English, Portuguese and Spanish translations.

Credits 🏆

• Dr John A. Johnson
• Dhiru Kholia

License 🙋

• https://ipip.ori.org/newPermission.htm

Resources 📗

• https://github.com/kholia/IPIP-NEO-PI
• http://www.personal.psu.edu/j5j/IPIP/ipipneo300.htm
• http://www.personal.psu.edu/~j5j/IPIP/ipipneo120.htm
• http://www.personal.psu.edu/faculty/j/5/j5j/
• https://ipip.ori.org/
• https://osf.io/tbmh5/

Authors 👨‍💻

• Ederson Corbari
• Marcos Ferretti