International Journal of Trend in Scientific Research and Development (IJTSRD)

Volume 5 Issue 4, May-June 2021 Available Online: www.ijtsrd.com e-ISSN: 2456 – 6470

Personality Prediction using Logistic Regression

Surya Narayan Sharma1, Dr. Kamalraj Ramalingam2
1Department of Master of Computer Applications, School of CS and IT,
2Associate Professor, Department of Master of Computer Applications, School of CS and IT,
1,2Jain Deemed to be University, Bangalore, Karnataka, India

ABSTRACT How to cite this paper: Surya Narayan

Human personality has played a significant role in the growth of both Sharma | Dr. Kamalraj Ramalingam
individuals and organisations. Using standard questionnaires or reviewing the "Personality Prediction using Logistic
curriculum vitae are two ways to assess human personality (CV).Recruiters Regression"
used to manually shortlist/filter a candidate's CV based on their criteria. We Published in
present a framework in this paper that automates the eligibility review of International Journal
candidates during the recruitment process. Based on the uploaded CV, the of Trend in Scientific
system evaluates professional eligibility. The framework employs the TF-IDF Research and
Algorithm for machine learning. Furthermore, by reviewing the scores Development (ijtsrd),
obtained in various fields, the resulting scores aid in determining the qualities ISSN: 2456-6470, IJTSRD41307
of the candidates. The use of graphs to analyse a candidate's success makes it Volume-5 | Issue-4,
easier to assess his or her personality and aids in proper CV analysis. As a June 2021, pp.447-450, URL:
result, the framework lends a hand in the recruitment process, allowing the www.ijtsrd.com/papers/ijtsrd41307.pdf
candidate's CV to be shortlisted and a reasonable decision to be reached.
Copyright © 2021 by author (s) and
KEYWORDS: Personality Evaluation, Big five model of Personality, Machine International Journal of Trend in Scientific
learning, Curriculum Vitae Analysis Research and Development Journal. This
is an Open Access article distributed
under the terms of
the Creative
Commons Attribution
License (CC BY 4.0)
(http://creativecommons.org/licenses/by/4.0)

I. INTRODUCTION II. LITERATURE SURVEY

In terms of jobs, choosing the best candidate for the job from The interrelationships among the Big Five personality
a large pool of applicants has long been a challenge [1]. factors (Openness, Conscientiousness, Extraversion,
Traditional methods include administering personality and Agreeableness, and Neuroticism) were examined in this
professional eligibility assessment assessments, conducting paper according to Liden et al.[9]
interviews, and holding group discussions. Employees' web
Psychometric analysis is used to choose the best candidate
handles are now exposed to even more relevant information
based on the results of psychometric tests and the needs of
about them as a result of the introduction of social media [2].
the company[8]. Using the Alberta Context Tool survey
Recruiters, on the whole, are uninterested in such detail.
results, protocols for psychometric analysis were proposed.
Traditional recruiting strategies include an aptitude test
followed by an interview. Traditional methods are time- The Big Five Personality Model (also known as the Five
consuming, and they can lead to unequal candidate Factor Model) was used to predict the candidate's
selections. The most important aspect that represents an personality, which involves Openness, Conscientiousness,
individual is personality, which changes over time [3]. Extraversion, Agreeableness, and Neuroticism [10].
Dealing with them is a time-consuming process, so we
The CV was analysed using recommendation based on
devised a method for identifying personalities and making
machine learning techniques. Various assessment methods
recommendations [4].
have been used in the literature [4]. One method has been
Kessler et al. [5] suggested a method that distinguishes and described in which a tool called "Career Mapper" is used to
categorises candidates based on their importance by make CV recommendations. It verifies that the user profile is
analysing unstructured text documents (job offers). Pasquale complete.
De Meo[6] proposes another XML-based multi-agent
The use of different filters is normally involved in the
recommender framework that relies on rich user profiles for
recommendation. Among them are content and
support. The proposed system was a multi-agent
collaboration. Usage of Fo-DRA for content-based
recommender system that exploited user profiles via XML to
suggestions is one of the alternatives to Content-Based
improve recruitment services in a personalised manner.
Recommender[1]. The similarities among users are a key
Another method proposed by Mohammad MehradSadra et
feature of Collaborative Based Recommender [11-13].
al. employs NLP for resume standardisation using a
modelling language approach[7]. Despite their widespread According to Liden et al., the interrelationships among the
use, these techniques have flaws in terms of structure, Big Five personality factors (Openness, Conscientiousness,
inconsistent CV formats, and contextual details[8]. Extraversion, Agreeableness, and Neuroticism) were

@ IJTSRD | Unique Paper ID – IJTSRD41307 | Volume – 5 | Issue – 4 | May-June 2021 Page 447
 International Journal of Trend in Scientific Research and Development (IJTSRD) @ www.ijtsrd.com eISSN: 2456-6470
explored in this paper to test for the existence of a GFP. It is
also worth noting that the inclusion of a GFP did not mean
that other personality variables lower in the hierarchy lost
value[9].
III. PROPOSED SYSTEM
IV. PROPOSED STATEMENT
We list some of the limitations based on the survey
mentioned above.
1. Traditional methods of hiring typically include job
seekers completing physical resumes and performing
interviews. But, with the recent increase of applications,
the number of candidates continues to overwhelm
employers. Machine learning algorithms are used to
create the models that will be tested in the proposed
automated candidate grading system.
2. In recent years, the value of manual interviews and
resumes in human resources has increased. It is
important to devise a solution that will reduce or
expedite the workload of the HR department.
V. SOLUTION
The proposed framework would have a transparent method,
allowing for a more efficient way to short list submitted
candidate CVs from a large number of applicants. In our
Fig 1: Implementation Steps
paper, we propose a machine learning algorithm for
personality assessment and CV analysis. This method offers VI. WORKING OF THE SYSTEM
an expert workforce for the company, assisting the HR 1. train_model class: It includes two methods for training
department in selecting the best applicant for the specific job the model and predicting the outcome by providing different
profile. Knowledge is highly valued in our culture. You have a values. a. train technique: It reads a csv file with the dataset
better chance of achieving in school and in life if you have a for training the algorithm and builds a model using Logistic
high IQ. Psychometric questions are often used to predict Regression. For training the model, it employs a variety of 7
personality. values.
The Candidate have to fill a form with all details and they A. train method: It reads a csv file with the dataset for
have to rate themselves in terms of Openness, Neuroticism, training the algorithm and builds a model using Logistic
Conscientiousness, Agreeableness, Extraversion based on Regression. For training the model, it employs a variety of 7
which the system predicts their personality. values.
B. test method: It predicts a person's personality by passing
an array of values containing gender, age, and the other five
personality characteristics.
2. main method: We begin by creating an object of the train
model class and then train the model by invoking the class's
train method. Then we initialize a variable with a Tk object
and design the system's landing page with labels and a press.
A button called Predict Personality is developed, which
invokes the predict person process.
3. predict_person method: We close the root tkinter
window and build a new top level window with the
appropriate size and attributes. The window's heading is
labelled, followed by different labels and their entries. To
choose a resume file, the user must press the Choose File
button, which then calls the Open file process, which
requires a button argument. Various entries are used in the
predict person system to predict the personality. When you
press the Submit button, all of the values are passed to
prediction result.
4. Open File method: It tries to open the directory with the
default address, name, and file types, but fails if no file is
selected. After the try except block, the method replaces the
name of the choose file button in the predict person method
with the base name of the file so that the user is aware of the
selected file.

@ IJTSRD | Unique Paper ID – IJTSRD41307 | Volume – 5 | Issue – 4 | May-June 2021 Page 448
 International Journal of Trend in Scientific Research and Development (IJTSRD) @ www.ijtsrd.com eISSN: 2456-6470
5. prediction_result method: This method begins by Neuroticism- High level shows anxiety and stress. Low level
closing the previous tkinter window that was used to collect shows emotionally stable.
data from the user. Following that, it invokes the model
VIII. RESULT AND DISCUSSION
object's test method and stores the result returned by the
method. Following that, it parses all of the information from
the resume and stores it in a variable, followed by a try
except block that attempts to delete the name and validate
the mobile number from the information retrieved from the
resume. The data sent by the user is then printed on the
console. Following that, the method displays a full-screen
window with all of the parsed information and expected
personality on the GUI window, as well as the description of
each personality trait
6. check_type method: It transforms strings and numbers
into the desired format, as well as lists and tuples in string.
VII. THE BIG FIVE PERSONALITY MODEL
Individual personality traits are expressed in how people
view themselves on social networking sites. The Five-Factor
Model (FFM) uses such knowledge to categorise OCEAN Fig 3: Application form
characteristics, which can then be used by other teams. The Form in Fig 3 takes various inputs from user and submit
According to reports, deeper knowledge of personality data it to prediction model which will predict the personality.
to obtain specific information remains a hot research
subject[14].

Fig 4: Final Result

On result page, all the manipulated information and
predicted result will be displayed based on the response
received in Fig 3.
IX. CONCLUSION AND FUTURE SCOPE
We introduced an organization-oriented recruiting method
in this project to assist the human resource department in
short listing the best applicant for a particular job profile.
The framework can be used in a variety of business sectors
that need expert candidates, reducing the workload on the
Fig 2: Ocean Model human resources department. With content and collective
filtering, a machine learning methodology was used in data
Personality characteristics such as openness, analysis. Furthermore, the predicted personality aid in
conscientiousness, extraversion, agreeableness, and determining the characteristics of candidates and the HR
neuroticism are assessed using the OCEAN model. department makes a fair and reasonable decision.
Openness- openness to new experiences demonstrates a Further, we can modify the existing system by integrating AI
level of intellectual curiosity for imagination and adoption of structure to provide significantly improved functionalities.
new ideologies, as well as a preference for diversity and Many more machine learning classification algorithms can be
novelty. High levels indicate a desire for innovation and a implemented to provide significantly improved functionality
wide range of interests, while low levels indicate a [15]. Furthermore, the application's reliability and
preference for conventionality and familiarity. consistency can be tested and analysed.
Conscientiousness- Conscientious people are organised, tidy, ACKNOWLEDGEMENT:
meticulous, and punctual. Low level is thought to be I want to communicate my genuine inclination and
spontaneous and adaptable, but it can also be untrustworthy commitment to Dr. Dinesh Nilkhant, Dr. M N Nachappa, Dr.
and sleazy. High level is thought to be obsessive and Bhuvana J, Dr. Laxmi J V N, Dr. Gangothri R and Prof. Dr.
obstinate. Kamalraj Ramalingamand venture facilitators for their viable
Extraversion- person who likes to start conversation, enjoys steerage and steady motivations all through my examination
meeting new people, feels energized when around other work. Their convenient bearing, to talco-activity and moment
people. perception have made my work productivity.

Agreeableness- person who is genuinely interested in other

people, cares for others, and helps those in need

@ IJTSRD | Unique Paper ID – IJTSRD41307 | Volume – 5 | Issue – 4 | May-June 2021 Page 449
 International Journal of Trend in Scientific Research and Development (IJTSRD) @ www.ijtsrd.com eISSN: 2456-6470
REFERENCES [8] Squires, J. E., et al., A protocol for advanced
[1] Almalis, N. D., et al. FoDRA—A new content-based job psychometric assessment of surveys. Nursing research
recommendation algorithm for job seeking and and practice, 2013. 2013.
recruiting. in 2015 6th International Conference on
[9] Van der Linden, D., J. te Nijenhuis, and A. B. Bakker,
Information, Intelligence, Systems and Applications
The general factor of personality: A meta-analysis of
(IISA). 2015. IEEE.
Big Five intercorrelations and a criterion-related
[2] Menon, V. M. and H. Rahulnath. A novel approach to validity study. Journal of research in personality, 2010.
evaluate and rank candidates in a recruitment process 44(3): p. 315-327.
by estimating emotional intelligence through social
[10] Mesurado, B., et al., EXTROVERSION: NATURE,
media data. in 2016 International Conference on Next
DEVELOPMENT AND IMPLICATIONS TO
Generation Intelligent Systems (ICNGIS). 2016. IEEE.
PSYCHOLOGICAL HEALTH AND WORK LIFE.
[3] Ombhase, M., et al., Automated Personality Psychology of Extraversion, 2014: p. 1-13.
Classification using Data Mining Techniques. Pillai
[11] Balabanović, M. and Y. Shoham, Fab: content-based,
Institute of Information Technology, 2017.
collaborative recommendation. Communications of the
[4] Lai, V., et al. CareerMapper: An automated resume ACM, 1997. 40(3): p. 66-72.
evaluation tool. in 2016 IEEE International Conference
[12] Bergman, L., et al. International workshop on
on Big Data (Big Data). 2016. IEEE.
recommendation and collaboration (recoll 2008). in
[5] Kessler, R., et al. Job offer management: how improve Proceedings of the 13th international conference on
the ranking of candidates. in International Symposium Intelligent user interfaces. 2008.
on Methodologies for Intelligent Systems. 2009.
[13] Sarwar, B., et al. Item-based collaborative filtering
Springer.
recommendation algorithms. in Proceedings of the
[6] De Meo, P., et al., An XML-based multiagent system for 10th international conference on World Wide Web.
supporting online recruitment services. IEEE 2001.
Transactions on Systems, Man, and Cybernetics-Part
[14] Popkins, N. C., The five-factor model: Emergence of a
A: Systems and Humans, 2007. 37(4): p. 464-480.
taxonomic model for personality psychology. Great
[7] Sadr, M. M., The role of personality traits predicting Ideas in Personality, Northwestern University, 1998.
emotion regulation strategies. International Academic
[15] Liu, H. and L. Yu, Toward integrating feature selection
Journal of Humanities, 2016. 3(4): p. 13-24.
algorithms for classification and clustering. IEEE
Transactions on knowledge and data engineering,
2005. 17(4): p. 491-502.

@ IJTSRD | Unique Paper ID – IJTSRD41307 | Volume – 5 | Issue – 4 | May-June 2021 Page 450