Automated Personality Classification

A
Project Report
Submitted in partial fulfillment of the requirement for the award of degree of

Bachelor of Engineering
In
Computer Science & Engineering

Submitted to
RAJIV GANDHI PROUDYOGIKI VISHWAVIDYALAYA,
BHOPAL (M.P.)

Guided by Submitted By
Prof. Deepak Patidar Mehek Tiwari(0875CS131072)
Misha Mathur(0875CS131074)
Pooja Yadav(0875CS131094)
Priyanka Kokate(0875CS131105)

DEPARTMENT OF COMPUTER SCIENCE & ENGINEERING

ACROPOLIS TECHNICAL CAMPUS,
INDORE (M.P.) 452001
2016-2017
 Declaration
I hereby declared that the work, which is being presented in the project entitled
Automated Personality Classification partial fulfillment of the requirement for the
award of the degree of Bachelor of Engineering in Computer Science & Engineering,
submitted in the department of Computer Science & Engineering at Acropolis Technical
Campus, Indore is an authentic record of my own work carried under the supervision of
Prof. Deepak Patidar. I have not submitted the matter embodied in this report for award
of any other degree.

Mehek Tiwari (0875CS131072)

Misha Mathur(0875CS131074)
Pooja Yadav (0875CS131094)
Priyanka Kokate(0875CS131105)

Prof. Deepak Patidar

Supervisor
 Project Approval Form
I hereby recommend that the project prepared under my supervision by Prof. Deepak
Patidar

Automated Personality Classification

be accepted in partial fulfillment of the requirement for the degree of Bachelor of

Engineering in Computer Science & Engineering.

Prof. Deepak Patidar

Recommendation concurred in

Project Coordinator

Head
 Acropolis Technical Campus
Department of Computer Science & Engineering

Certificate
The project work entitled Automated Personality Classification submitted by Mehek
Tiwari (0875CS131072), Misha Mathur (0875CS131074), Pooja Yadav (0875CS131094),
Priyanka Kokate (0875CS131105) is approved as partial fulfillment for the award of
the degree of Bachelor of Engineering in Computer Science & Engineering by Rajiv
Gandhi Proudyogiki Vishwavidyalaya, Bhopal (M.P.).

Internal Examiner External Examiner

Name: Name:

Date: Date:
Acknowledgement
The completion of any inter-disciplinary project depends upon cooperation, co-ordination
and combined efforts of several sources of knowledge. We are grateful to Prof. Deepak
Patidar for his even willingness to give us valuable advice and direction; whenever
weapproached him with a problem.We are thankful to him for providing immense guidance
for this project.We are also thankful to Prof.Brajesh Chaturvedi, Department of
Computer Science & Engineering, for his immense guiding in Structural Design Part of
our project.We are also thankful to Dr. Abhishek Singh Rathore & Prof. Nandkishore
Sharma ,Department of Computer science &engineering,for his immense guiding in our
project.We are also thankful to Dr. S.C Sharma,Director,ATC and all the staff members
for their immense cooperation and motivation of completing out the project.

Mehek Tiwari (0875CS131072)

Misha Mathur (0875CS131074)
Pooja Yadav (0875CS131094)
Priyanka Kokate (0875CS131105)
Abstract
The automated personality classification (APC) is defined as a task of assigning personality
characteristics (traits) to a person, based on information about that person, and the content
that person produced. Basically in this project, we investigate important aspects of this
problem and give an overview of the existing solutions that solve it. As a scientific
contribution, we present a hierarchical classification of the existing solutions to this
problem. We also propose several new research directions regarding the problem of APC.
Firstly, we investigate possible improvements of the existing solutions to the problem of
APC, for which we use different combinations of the APC corpora, psychological trait
measurements, and learning algorithms. Afterwards, we consider extensions of the APC
problem and the related tasks, such as dynamical APC and detecting personality
inconsistency in a text. This entire research is performed in the context of social networks
and data mining algorithms.

The way people communicate be it verbally, visually, or via text is indicative of personality
traits. In social media the concept of the status update is used for individuals to
communicate to their social networks in an always-on fashion. In doing so individuals
utilize various kinds of speech acts that, while primarily communicating their content, also
leave traces of their personality dimensions behind. We human-coded a set of Facebook
status updates from the my Personality dataset in terms of speech acts label and then
experimented with surface level linguistic features including lexical, syntactic, and simple
sentiment detection to automatically label status updates as their appropriate speech act.
We apply supervised learning to the dataset and using our features are able to classify with
high accuracy two dominant kinds of acts that have been found to occur in social media.

So Basically the project is all about studying the personality traits of different people by
behavior, Text, Speech and all.
Table of Content

1. Introduction

1.1 Motivation

1.1.1 Solution Approach

1.2 Thesis Goals

1.3 Thesis Objectives

1.4Overiew of the Proposed Work

1.5 Report Organization

2. General Background

2.1 General Definition

3. Literature Review

3.1 Related published Work

3.2Comparative Study

3.3 Summarize

4 Problem Statement

5 Proposed Solution for Future

6 Conclusion

Appendix A: Project Synopsis

Appendix B: Guide Interaction Report (*Dully Signed by Guide)

1.Introduction
Personality is a set of individual differences that are affected by the development of an
individual: values, attitudes, personal memories, social relationships, habits, and skills. The
word "personality" originates from the Latin persona, which means mask. Personality is
usually broken into components called the Big Five, which are openness to
experience, conscientiousness, extraversion, agreeableness, and neuroticism (or emotional
stability).Personality classification is one of the problems considered by personality
psychology, a branch of psychology. The focus of this field is the study of personality and
individual differences. The problem of automated personality classification is considered
based on information from the following content: textual content that the person wrote and
meta information about a person received on request, through social networks or other
means. There are studies that also include speech, analysis of facial characteristics,
gestures and other aspects of behavior, but they are not the subjects of our study.

1.1 Motivation
The standard approach to solving the APC problem based on the aforementioned content
is described in the following steps: A. Gathering the corpus data, B. Determination of the
personality characteristics of the participants, and C Building the model.

Although the efforts to classify personality traits can be a particularly useful Endeavour,
the detection of personality and/or behavior in conversation using natural language, as it
turns out, is a rather difficult task. For example, in serious games in which communication
occurs in chat rooms, players may discuss different ideas than others they are chatting
with during conversation. Likely, they area also exposed to or affected by the different
personalities or moods of other players during communication. On the other hand, players
may demonstrate various personality characteristics (such as those related to helping,
leading, or aggression)that may result in varied behavioral indicators within conversation.
This research builds upon previous interdisciplinary research works regarding personality
as it pertains to the design of intelligent interactive systems.
1.1.1 Solution Approach
Automated personality classification (APC) can be applied to the current available data to
classify or predict the user personality characteristics based on the past classifications. The
data already available on different databases can be used to train the learning machines to
classify the data. Once the machines are trained they can be used to predict the personality
based on its learnings. The systems are very useful in government agencies where large
datasets needs to be reduced to smaller ones to reduce the work load. These systems can
also be used in ad selling on different social media base on the users personality and
demographics. It is important to record the human identification features and classify the
individuals based on certain features. In various demographic and forensic investigations
it is helpful to classify people according to the demographic features such as their gender,
age. A lot of research has been done in the past and continuously been done because tracing
and identifying humans is the need of hour.

1.2 Thesis Goal

So the goal of this research area is to infer personality traits from the writing of
individuals, and to do so in an automated way, en masse. You are probably envisioning a
million applications: the prediction is fuzzy but could revolutionize advertising, where
any gain in prediction is very effective. A service could emerge, with guaranteed
anonymity, for people to find out how others probably see them, or to assess their
acquaintances given the data freely provided to them. This could augment the judgment
of people who have difficulty perceiving others, or who have zero acquaintance with
another, such as on dating websites. Corporate recruiters and governments could find
those most likely to be evil terrorists or Wall Street psychopaths by examining writing
samples. Another application, which someone has already started to explore, is in
recommender systems: find internet reviews of products written by people similar to the
searcher in terms of human personality. Similar matching occurs on dating websites, but
the methods are primitive. Also predicting focused personality sub-facets may be more
useful for the most targeted applications, but has not been done yet.
1.3 Thesis Objective
The Objective of the study was to find correlation between user personality and variety
oflinguistic factors within the text chat feature of the game, as well other behavior. Work
has been done to relate a variety of observations to personality, for example voice pitch
and gesture.Another application, which someone has already started to explore, is in
recommender systems: find internet reviews of products written by people similar to the
searcher in terms of human personality. Similar matching occurs on dating websites, but
the methods are primitive. Also predicting focused personality sub-facets may be more
useful for the most targeted applications, but has not been done yet.This area of research
restricts the analysis of behavior to written text, with the end in mind of predicting the
personality scores given by established self-assessment questionnaires. Such a restriction
is not debilitating; the kind of personality-expressive human behavior studied the most is
possibly linguistic in nature or is well described by participants in speech or writing.

1.4 Overview of proposed work

The problem of automated personality classification (APC) is defined as a task of assigning
personality characteristics (traits) to a person, based on information about that person, and
the content that person produced. Observing someones personality can be quite useful in
user interface design, recommender systems, marketing, employment decisions, and
understanding team interactions.

The goal of the project to classify the personality of a person by the data provided by him
on a social networking sites or to classify his personality on the basis of his handwriting or
the posts he does on twitter or Facebook.

The goal of our project is to automatically classify the personality of a person not manually.

The proposed solution for this is that fetch the persons data from his social networking
accounts for e.g. from facebook, twitter etc analyze the posts , the images shared by him
the classify him on the basis of five big models of the personality models. Then provide

his personality that exactly what is his personality that is he aggressive ,emotional
,extrovert ,introvert etc .
1.5 Report Organization
In this paper, new ideas regarding the problem of automated personality classification are
presented. We proposed some general directions for improvement of all existing solutions.
Afterwards, we gave a brief overview of some selected existing solutions and discussed
about their possible specific enchantments. We also acknowledged extensions of APC and
possible usages of APC for solving related problems. Solutions to the problem of APC
could be used to solve other problems, whenever solving the problem of APC can draw
some conclusions regarding those problems. In our future work we will consider actual
implementations of some of the proposed ideas. We also want to put efforts in finding and
implementing new ideas related to the social network algorithms. Our opinion is that, in
the near future, the APC is going to be heavily exploited, directly or indirectly inside
recommender systems, social networks and expert systems. Therefore, this paper,
conceived as an initial analysis research, could announce new scientific and practical work
related to the problem of APC.
2. General Background
Personality classification is one of the problems considered by personality psychology, a
branch of psychology. Personality type refers to the psychological classification of
different types of individuals. Personality types are sometimes distinguished
from personality traits, with the latter embodying a smaller grouping of behavioral
tendencies.

2.1 General Definition

The Big Five personality traits, also known as the five factor model (FFM), is a model
based on common language descriptors of personality (lexical hypothesis). These
descriptors are grouped together using a statistical technique called factor analysis (i.e. this
model is not based on experiments).The five factorshave been defined as openness to
experience, conscientiousness, extraversion, agreeableness, and neuroticism.

(i) Openness to experience

Openness is a general appreciation for art, emotion, adventure, unusual ideas, imagination,
curiosity, and variety of experience. People who are open to experience are intellectually
curious, open to emotion, sensitive to beauty and willing to try new things. They tend to
be, when compared to closed people, more creative and more aware of their feelings. They
are also more likely to hold unconventional beliefs.

(ii) Conscientiousness
Conscientiousness is a tendency to show self-discipline, act dutifully, and aim for
achievement against measures or outside expectations. It is related to the way in which
people control, regulate, and direct their impulses. High scores on conscientiousness
indicate a preference for planned rather than spontaneous behavior.The average level of
conscientiousness rises among young adults and then declines among older adults.

(iii) Extraversion
Extraversion is characterized by breadth of activities (as opposed to depth), surgency from
external activity/situations, and energy creation from external means. The trait is marked
by pronounced engagement with the external world. Extraverts enjoy interacting with
people, and are often perceived as full of energy. They tend to be enthusiastic, action-
oriented individuals. They possess high group visibility, like to talk, and assert themselves.

Introverts have lower social engagement and energy levels than extraverts. They tend to
seem quiet, low-key, deliberate, and less involved in the social world. Their lack of social
involvement should not be interpreted as shyness or depression; instead they are more
independent of their social world than extraverts. Introverts need less stimulation than
extraverts and more time alone. This does not mean that they are unfriendly or antisocial;
rather, they are reserved in social situations.

(iv) Agreeableness
The agreeableness trait reflects individual differences in general concern for social
harmony. Agreeable individuals value getting along with others. They are generally
considerate, kind, generous, trusting and trustworthy, helpful, and willing to compromise
their interests with others. Agreeable people also have an optimistic view of human
nature.

Disagreeable individuals place self-interest above getting along with others. They are
generally unconcerned with others' well-being, and are less likely to extend themselves for
other people. Sometimes their skepticism about others' motives causes them to be
suspicious, unfriendly, and uncooperative.

(v) Neuroticism
Neuroticism is the tendency to experience negative emotions, such as anger, anxiety, or
depression. It is sometimes called emotional instability, or is reversed and referred to as
emotional stability.
3. Literature Review
3.1 Related published Work

Personality in Computer-Based Learning Environments

There are numerous reasons personality traits should be considered in CBLE.
For example, even at a very basic level, attitudes toward computers can be related to
personality types such that those displaying higher scores on neuroticism may have
greater computer related anxiety . Also, it is useful to consider differences in students or
group dynamics into account during learning in CBLE. ITS are good examples to
measure the ability of students against human tutoring methods as well as needs of
learners . This task should not be taken lightly, however, as for both human tutor and ITS,
it is difficult to accurately assess both the cognitive and emotional states of individual
learners. Similarly, it is a rather complex process to categorize personality traits solely
from natural language user input in CBLE.[2]

Emotion Detection Using Learys Rose Frameboard

Researchers have had some success on the de Learyous gaming project .To our knowledge
, this is the only research that has been done specifically on the automatic classification of
sentences based on Learys Rose for emotion detection.
DeLearyous researchers described a methodology for a serious gaming project which aims
at developing an environment in which users can improve their communication skills by
interacting with a virtual character in written natural language (Dutch). In order to apply
Learys framework, they classified the input sentences into one of four possible emotion
classes (above, below, opposed,together). They applied several machine learning
algorithms SVM, Naive Bayes, and Conditional Random Field (CRF) to obtain the
classification performance. For this, they used different features set from their dataset
(unigrams, lemma trigrams and dependency structures). They obtained 52.5 % accuracy,
around 25 % over the baseline. The researchers noted, however, that the manually
annotated sentences used to compile their training set were labeled by one human annotator
and thus may have been susceptible to issues with reliability.[2]
 Automatic Detection of Personality
In other research found that identification of personality (Big Five in speech)
by automatic analysis performed better than the baseline. Their analysis confirms previous
findings linking language and personality and also reveals many new128 F. Keshtkar et al.
linguistic and prosodic markers. However, there was a limitation in their method in that
speech recognition, such as prosodic features.
In addition, there has been other research conducted in order to let a machine learner
determine the appropriate sentiment/emotion class. For instance, and attempted to classify
LiveJournal posts according to their mood using SVM trained with frequency features
(word counts, POScounts), length-related features(length of posts/sentences, etc.),
semantic orientation features (using WordNet to calculate the distance of each word to a
set of manually classified keywords) and special symbols (emoticons).[1]

Learys Interpersonal Frame Board

Learys Interpersonal Circumplex (or Learys Rose Frame Board) has been used By
researchers for decades as a foundation for categorizing personality through the discourse.
The Circumflex defines characteristics according to two dimensions: the above-below axis
represents variation from dominant (above) to submissive (below) whereas the opposed-
together axis represents variations of cooperation from accommodating (together) to
opposition (opposed) . Based on these two dimensions, the Rose can easily be separated
into four quadrants and then further split into eight different categories .132 F. Keshtkar et
al.[3]

Fig: 1 Learys Diagram

 The Big Five Personality, Learning Styles,and Academic Achievement
Personality and learning styles are both likely to play significant roles in influencing
academic achievement . College students (308 undergraduates) completed the Five Factor
Inventory and the Inventory of Learning Processes and reported their grade point average.
Two of the Big Five traits, conscientiousness and agreeableness, were positively related
with all four learning styles (synthesis analysis, methodical study, fact retention, and
elaborative processing), whereas neuroticism was negatively related with all four learning
styles.[5]
In addition, extraversion and openness were positively related with elaborative processing.
The Big Five together explained 14 % of the variance in grade point average (GPA), and
learning styles explained an additional 3 %, suggesting that both personality traits and
learning styles contribute to academic performance. Further, the relationship between
openness and GPA was mediated by reflective learning styles (synthesis-analysis and
elaborative processing). These latter results suggest that being intellectually curious fully
enhances academic performance when students combine this scholarly interest with
thoughtful information processing. Implications of these results are discussed in the context
of teachingtechniques and curriculum design .Using Personality and Cognitive Ability to
Predict Academic Achievement Beaujean et al., conducted a study on the relationship
between cognitiveability, personality, and academic achievement in post-secondary
students, usinglatent variable models. By testing both simple and complex relationships,
they found that cognitive ability and personality predicted reading achievement
independently, but that they interact when predicting math achievement, at least in the
 Figure 2: Big Five Use

Conscientiousness and Openness to Experience domains.

In addition to self-assessed personality, a few researchers incorporate human

judged personality in their studies. Although not usually in the context of automated
analyses of text corpora, there exists a body of work consisting of human-judged
personality assessments correlated with expressions of text and other artifacts
provided by users of such systems as social networking websites and cell phone
networks. These features are sometimes viewed as validating the human judges or
showing what the human judges are capable of when somewhat starved for
information, while conversely at other times, assuming the accuracy of the
observers, viewed as validating the text features. Including human (observer)
judged personality in addition to the self-assessments is laudable because it allows
one to examine such questions.
Some attention was given to the issue of cross-situational behavior and how it
effects personality assessment. A longstanding criticism of personality psychology
is that the behavior it describes may be largely situational rather than an individual
difference. One of their goals was to show that the text features they were interested
in were fairly stable despite varying situations. The authors were interested in
assuring the authors situation did not significantly effect the rate at which they
expressed their personality through these text features. For this reason they
introduced a phase of their study involving the writing of some additional small
groups of study participants: briefly, a sample of 15 residential patients in a
 substance abuse treatment setting, 34 summer school students, and 40 randomly
selected, highly published social psychologists. Ultimately they conclude that
although usage varied between topics, writers are consistent in their use of word
categories whenever writing about a given topic. Thus began prediction of human
personality from features extracted from their writings.[6]
People spend a considerable amount of effort in order to form and to manage
impressions, especially in the initial stage of social interactions. Nowadays, this
fundamental process has been modified by the usage of new communication
technologies. So- cial networking technologies, such as Facebook, offer new ways
for self-presentations. Several studies reported that Facebook users engage in
actively creating, maintaining and modifying an image of selves by adjusting their
profiles, including descriptions and pic- tures, joining groups and displaying their
likes and dislike .Hence, the Facebook profile page can be considered as a
mediated representation of the Facebook user. Although users may betempted to
enhance their self-presentations, friends who are both offline and online keep
Facebook users self-presentations in check. Indeed, misrepresentation on profile
pages can have serious offline consequences.
Moreover, social psychology research has also highlighted that personality plays
an important role in the way people manage the image. While the big five factor
model measures the individual tendencies, the interpersonal circumplex measures
the attitude towards others. The big five factors they convey in self-presentations.
model defines personality along 5 bipolar scales that can be turned into binary
classes: extroversion (sociable vs shy) emotional stability (secure vs neurotic)
agreeableness (friendly vs ugly) con- scientiousness (organized vs careless)
openness to experience (in- sightful vs unimaginative). Researchers have tried to
obtain information about the personality of human beings through direct means
such as the EPQ-R questionnaire, but they have also used indirect methods.
Because personality is considered to be stable over time and throughout different
situations, specialized psychologists are able to infer the personality profile of a
subject by observing the subjects behavior.
 One of the sources of knowledge about the behavior the of individuals is written
text. The results showed differences between the two sub-types of samples. Based
on these differences, it was found that extroverts use more punctuation and
exclamation signs, produce texts with more words, make more references to social
situations, and use a greater number of positive words. Introverts, in contrast, are
more likely to use the first-person singular, express themselves using more
emotionally negative words, and use more coordinating conjunctions. The
researchers also made lists of frequently used bigrams for both groups. Automated
handwriting analysis can be used to examine personal traits of candidates during
interviews accurately as the accuracy of an analyst highly depends on his skill set.
Handwriting also termed as brain-writing is a useful measure in identifying the
characteristic personality traits of an individual. Handwriting analysts also known
as graphologists can examine an individuals handwriting to predict the personality
traits of the writer.[7]

3.2 Comparative Study

Our Proposed system will provide information about the personality of the user. Based on
the personality traits provided by the user, System will match the personality traits with the
data stored in database. System will automatically classify the users personality and will
match the pattern with the stored data. System will examine the data stored in database and
will match the personality traits of the user with the data in database. Than system will
detect the personality of the user. Based on the personality traits of the user, system will
provide other features that are relevant to the users personality.

(a) Economic Feasibility

This system will help advertisement people to market their products based
on the personality of the user which in turn provide income to the firm who
is using this system. This system can be embedded with social sites, as many
users can buy and sell their product using these social networks.

(b) Operational Feasibility

 This system is more reliable, maintainable, affordable and producible.
These are the parameters which are considered during design and
development of this project. During design and development phase of this
project there was appropriate and timely application of engineering and
management efforts to meet the previously mentioned parameters.

(c) Technical Feasibility

The back end of this project is SQL server which stores data related to
personality traits and other details which is related to this project. There are
basic requirement of hardware to run this application. This system is
developed in .Net Framework using C#. This application will be online so
this application can be accessed by using any device like (Personal
Computers, Laptop and with some hand held devices).
3.3 Summarize
1) Automated Personality Classification (APC) is used to detect the personality of the
person.
2) Personality of the user is compared with previous data on server, based on this data
system will detect the personality of the user.
3) Personality is typically assessed along five dimensions known as the Big Five:
(a) Extraversion vs. Introversion (sociable, assertive, playful vs. aloof,
reserved, shy)
(b) Emotional stability vs. Neuroticism (calm, unemotional vs. insecure,
anxious)
(c) Agreeableness vs. Disagreeable (friendly, cooperative vs. antagonistic,
faultfinding)
(d) Conscientiousness vs. Unconscientiously (self-disciplined, organized
vs. inefficient, careless)
(e) Openness to experience (intellectual, insightful vs. shallow,
unimaginative)
4) System will examine the personality of the user based on personality traits and will
specify user belongs to which personality. Based on his personality, system will
display other features which is relevant to his personality.
4. Problem Statement
The problem of automated personality classification (APC) is defined as a task of assigning
personality characteristics (traits) to a person, based on information about that person, and
the content that person produced. Observing someones personality can be quite useful in
user interface design, recommender systems, marketing, employment decisions, and
understanding team interactions. Lately researchers have conducted experiments to infer
author personality from text corpora posted by the public on the Internet, such as on social
network websites, blogs, and reviews of products or services, as well as other offline
sources. They are able to use the information extracted from these texts to predict (both by
classification and regression) the personality questionnaire scores of the authors. The focus
of this area is on inferring author personality from text; the assumption is that personality
predicts behavior important for myriad applications.

We come across areas where we have access to large amounts of person behavioral data.
This data can help us classify persons using Automated personality classification (APC).
In this project, we propose an advanced APC automated personality classification system.
We here use learning algorithms along with advanced data mining to mine user
characteristics data and learn from the patterns. This learning can now be used to
classify/predict user personality based on past classifications. The system analyses vast
user characteristics and behaviours and based on the patterns observed, it stores its own
user characteristics patterns in a database. The system now predicts new user personality
based on personality data stored by classification of previous user data. This system is
useful to social networks as well as various ad selling online networks to classify user
personality and sell more relevant ads. Also the system is useful for government agencies
to observe user personality and predict new user personality on a large scale.
5. Proposed solution
For future work, we want to include an extended experiment of the methods pro-posed in
current research to sentiment analysis, opinion mining, as well as emotion detection in
other domains. Also, we want to extend the method in this work to apply in Big-Five
personality detection. It will help us to not only detect the players behaviors but also to
detect introvert and extrovert players and a focus on approaches with POS features might
be useful.
Handwriting Analysis for Detection of Personality Traits
Sample Training set will be generated using 100 samples of handwriting, which will be
examined by a professional.

Handwriting Vector matrix Data set

sample

Traits1 Traits n

Automatic Personality from Facebook Profile Pictures

Researchers have also focused on personality prediction from small corpora of social
network data, like Twitter and Facebook, exploiting either linguistic features in status
updates, social features such as friends count, and daily activity. . Our paper also uses data
from a social network; however it adopts a novel approach using visual features extracted
from Facebook profile pictures in order to classify subjects traits
6. Conclusion
We have developed a dataset containing personality excerpts based on Learys Rose
Frameboard. By this, we have developed automatic personality detection that shows are
more efficient than that of human judges. Consequently, we have presented three
automated methods to personality detection, based on understanding from research in
natural language processing, machine learning, and psychology characteristic. We
conducted that while text classification based on n-gram (UNIGRAMS, BIGRAMS) is the
best particular detection approach, a combination-method such as LIWC and Subjective
Lexicons features along with n-gram features can achieve better performance.
We Have successfully exploited a Bag-of-Visual-Words technique to automatically predict
personality and interaction styles from profile pictures in Facebook. To meet this
requirement, it will be necessary to fully develop the classifier and the prototype but this
work is still in an early stage although it is a great starting point for future analysis. A lot
of work needs to be done prior having more conclusive results. However, so far, we are
proud to say that the first objective is achieved. A lot of time has been needed for
Researching on different papers, understanding the possible ways of identifying
personalities and their link with happiness. one paper has proposed a methodology to
predict the accurate personality traits of an individual from the features extracted from
handwriting using a machine learning approach. The present study had aimed at
unravelling how personological typifications were the basis for differing emotion
regulation strategies in context of identifying personality types more prone to affect
regulation difficulties. It was hypothesized that Introverted Feeling Judging Type females
would have higher difficulties in Emotional Regulation as compared to Extraverted Feeling
Judging Type females.
References
[1]S. Argamon, S. Dhawle, M. Koppel, and J. Pennebaker. Lexical predictors of
personality type. In in 2005 Joint Annual Meeting of the Interface and the Classification
Society of North America, 2005.
[2] S. Bai, T. Zhu, and L. Cheng. Big-five personality prediction based on user behaviors
at social network sites. arXiv preprint arXiv:1204.4809, 2012.
[3] J. Block. The five-factor framing of personality and beyond: Some ruminations.
Psychological Inquiry, 21(1):225, 2010.
[4] T. Buchanan, J.A. Johnson, and L.R. Goldberg. Implementing a five-factor personality
inventory for use on the internet. European Journal of Psychological Assessment,
21(2):115127, 2005.
[5] L.E. Buffardi and W.K. Campbell. Narcissism and social networking web sites.
Personality and social psychology bulletin, 34(10):13031314, 2008.
[6] F. Celli and L. Rossi. The role of emotional stability in twitter conversations. EACL
2012, page 10, 2012.
[7] G. Chittaranjan, J. Blom, and D. Gatica-Perez. Whos who with big-five: Analyzing
and classifying personality traits with smartphones. In Wearable Computers (ISWC), 2011
15th Annual International Symposium on, pages 2936. IEEE, 2011.
[8] P.T. Costa and R.R. McCrae. Neo pi-r professional manual. Odessa, FL: Psychological
Assessment Resources, 396:65365, 1992.38
[9] PT Costa Jr and RR McCrae. Toward a new generation of personality theories:
Theoretical contexts for the five-factor model. The five factor model of personality:
Theoretical perspectives. Hrsg.: JS Wiggins. New York, pages 5187, 1996.
[10] W. Daelemans, S. Buchholz, J. Veenstra, et al. Memory-based shallow parsing. In
Proceedings of CoNLL, volume 99, pages 5360. Bergen: Association for Computational
Linguistics, 1999.
[11] D. Estival, T. Gaustad, S.B. Pham, W. Radford, and B. Hutchinson. Author profiling
for english emails. In Proceedings of the 10th Conference of the Pacific Association for
Computational Linguistics, pages 263272, 2007.
[12] D. Estival, T. Gaustad, S.B. Pham, W. Radford, and B. Hutchinson. Tat: an author
profiling tool with application to arabic emails. In Proceedings of the Australasian
Language Technology Workshop, pages 2130, 2007.
[13] A.J. Gill, S. Nowson, and J. Oberlander. What are they blogging about? personality,
topic and motivation in blogs. In Proceedings of the Third International ICWSM
Conference, 2009.
[14] J. Golbeck, C. Robles, M. Edmondson, and K. Turner. Predicting personality from
twitter. In Privacy, security, risk and trust (passat), 2011 ieee third international conference
on and 2011 ieee third international conference on social computing (socialcom), pages
149156. IEEE, 2011.
[15] J. Golbeck, C. Robles, and K. Turner. Predicting personality with social media. In
Proceedings of the 2011 annual conference extended abstracts on Human factors in
computing systems, pages 253262. ACM, 2011.
[16] T. Holtgraves. Text messaging, personality, and the social context. Journal of
Researchin Personality, 45(1):9299, 2011.
[17] O.P. John, R.W. Robins, and L.A. Pervin. Handbook of personality: theory and
research. The Guilford Press, 2008.39
[18] C. Leacock, G. Towell, and E. Voorhees. Corpus-based statistical sense resolution. In
Proceedings of the ARPA Workshop on Human Language Technology, pages 260
265,1993.
[19] Kim Luyckx and Walter Daelemans. Using syntactic features to predict author
personality from text. In Proceedings of Digital Humanities 2008 (DH 2008), pages 146
149, 2008.
[20] F. Mairesse, M.A. Walker, M.R. Mehl, and R.K. Moore. Using linguistic cues for the
automatic recognition of personality in conversation and text. Journal of Artificial
Intelligence Research, 30(1):457500, 2007.
[21] M.R. Mehl, S.D. Gosling, and J.W. Pennebaker. Personality in its natural habitat:
manifestations and implicit folk theories of personality in daily life. Journal of personality
and social psychology, 90(5):862, 2006.
[22] S. Nowson. Identifying more bloggers: Towards large scale personality classification
of personal weblogs. In In Proceedings of the International Conference on Weblogs and
Social. Citeseer, 2007.
[23] J. Oberlander and A.J. Gill. Language with character: A stratified corpus comparison
of individual differences in e-mail communication. Discourse Processes, 42(3):239270,
2006.
[24] J. Oberlander and S. Nowson. Whose thumb is it anyway?: classifying author
personality from weblog text. In Proceedings of the COLING/ACL on Main conference
poster sessions, pages 627634. Association for Computational Linguistics, 2006.
[25] B. Pang and L. Lee. Opinion mining and sentiment analysis. Now Pub, 2008.
[26] S.V. Paunonen and M.C. Ashton. Big five factors and facets and the prediction of
behavior. Journal of personality and social psychology, 81(3):524, 2001.
[27] J.W. Pennebaker and L.A. King. Linguistic styles: language use as an individual
difference. Journal of personality and social psychology, 77(6):1296, 1999.40
[28] S. Picazo-Vela, S.Y. Chou, A.J. Melcher, and J.M. Pearson. Why provide an online
review? an extended theory of planned behavior and the role of big-five personality traits.
Computers in Human Behavior, 26(4):685696, 2010.
[29] L. Qiu, H. Lin, J. Ramsay, and F. Yang. You are what you tweet: Personality
expression and perception on twitter. Journal of Research in Personality, 2012.
[30] A. Roshchina, J. Cardiff, and P. Rosso. User profile construction in the twin
personality-based recommender system. Sentiment Analysis where AI meets Psychology
(SAAIP), page 73, 2011.
[31] 1 S. Bai, T. Zhu, and L. Cheng. Big-five personality prediction based on user
behaviors at social network sites. arXiv preprint arXiv:1204.4809, 2012.
[32] FazelKeshtkar, Candice Burkett, Haiying Li and Arthur C. Graesser.
[33]Handwriting Research Corporation http://www.handwriting.com/facts/history.htm
[34] O. Aran and D. Gatica-Perez. Cross-domain personality prediction: from video blogs
to small group meetings. In Proceedings of the 15th ACM on International conference on
multimodal interaction, pages 127130. ACM, 2013
Appendix A:Synopsis
Project Team:
Enrol. Number Name Mob No Email

0875CS131072 MishaMathur 7354599284 [email protected]

0875CS131074 Mehek Tiwari 8435949809 [email protected]

0875CS131094 PoojaYadav 9926014993 [email protected]

0875CS131105 Priyanka Kokate 8269782047 [email protected]

1.Introduction-

In this project, we propose an advanced APC automated personality classification system.

We here use learning algorithms along with advanced data mining to mine user
characteristics data and learn from the patterns. This learning can now be used to
classify/predict user personality based on past classifications. The system analyses vast
user characteristics and behaviors and based on the patterns observed, it stores its own user
characteristics patterns in a database. The system now predicts new user personality based
on personality data stored by classification of previous user data. This system is useful to
social networks as well as various ad selling online networks to classify user personality
and sell more relevant ads. Also the system is useful for government agencies to observe
user personality and predict new user personality on a large scale.

2.Rationale-

This system will help many firms to market their products and also helps
them to target the right customers.
Many users will get to know about their personality based on their
personality traits.
This system is useful for the social networking sites which help these sites
to increase their rating scale.
 As the results are based on previous data stored in database, so the system
will provide with appropriate result.

3. Objectives

Automated Personality Classification (APC) is used to detect the

personality of the person.
Personality of the user is compared with previous data on server, based on
this data system will detect the personality of the user.
Personality is typically assessed along five dimensions known as the Big
Five:
Extraversion vs. Introversion (sociable, assertive, playful vs. aloof,
reserved, shy)
Emotional stability vs. Neuroticism (calm, unemotional vs.
insecure, anxious)

Agreeableness vs. Disagreeable (friendly, cooperative

vs.antagonistic, faultfinding)

Conscientiousness vs. Unconscientiously (self-disciplined,

organized vs. inefficient, careless)
Openness to experience (intellectual, insightful vs. shallow,
unimaginative)
System will examine the personality of the user based on personality traits
and will specify user belongs to which personality. Based on his personality,
system will display other features which is relevant to his personality.

4.Methodology (summary of the project)

We conduct a set of experiments to examine whether automatically trained

models can be used to recognize the personality of unseen subjects. Our
approach can be summarized in five steps:
1. Store Data related to personality in database.

2. Collect associated personality characteristics for each participant.

3. Extract relevant features from the texts.

 4. Display features relevant to his personality traits.
5. Personality and User Behavior.

5. Contribution of the Project

a. Innovativeness
Automatic detection of personality by the system itself on the basis of past
survey.
b. Usefulness
This system can be helpful for firms to identify the personality of the
interviewee based on the personality traits of the interviewee.
This system is useful for the firms for marketing their products and helps
them to target the correct customers.

c. Market Potential
This system will help advertisement people to market their products based
on the personality of the user which in turn provide income to the firm who
is using this system. This system can be embedded with social sites, as many
users can buy and sell their product using these social networks.

6. Technical Details

Software Requirements:

Windows 7/8/10
SqlYog
Android

Hardware Components:
Processor Dual Core
Hard Disk 50 GB
Memory 1GB RAM
Internet Connection
7.Expected Outcome
The project will be able to provide appropriate result to a person related to the his/her
personality.