A rule based approach towards detecting human temperament

International Journal of Computer Science & Information Technology (IJCSIT) Vol 7, No 1, February 2015
DOI:10.5121/ijcsit.2015.7109 85
A RULE BASED APPROACH TOWARDS DETECTING
HUMAN TEMPERAMENT
ShomoyeAbiodun R1
and ShomoyeAdekunle I2
1
Department of Computer Science, Oduduwa University, Ipetumodu, Nigeria
2
Department of Math and Stat, Federal Polytechnic, Ilaro, Nigeria.
ABSTRACT
This paper presented a rule based system for detecting human temperament.. The system was developed to
provide support for an expert psychologist in properly predicting the temperament of an individual as well
as given advice to the user. The system does this by following specified rules. Of this, we have deduced
some features that makes up known temperament types from which the system can accurately classify the
user‘s temperament based on the person‘s characters. Also, our work is solely limited to temperament, any
expert advice sought from and given by the system is limited to this scope.
KEYWORDS
Temperament,,Sanguine, Choleric, Phlegmatic andMelancholic.
1. INTRODUCTION
This paper presents a Rule Engine Approach towards Detecting Human Temperament, reverse
reasoning technique was developed to help people know their temperaments type and assessing
their temperament at any point in time. In the course of our work, some issue was raised and dealt
with which leads to the development of this system, part of which are:
 What method can be used to ascertain ones temperament and mood in a non-expert
environment? How can we determine one temperament with a system and it would be
acceptable by an expert. It should be known that if a man is fully aware of his
temperament, he can learn easily to direct, control himself among people and this will
bring about good relationship with other within his or her environment.
 Which human character, behavior and method should be consider by a system to
ascertain the type of temperament a person is exhibiting? This looks uncomplicated on
the surface but it becomes much complex as humans exhibit traits of different
temperament types. For this, we introduced a reversed approach to solving the problem.
 What method should be used to get the necessary information from a person’s feeling and
compare it with existing knowledge, can these be well indexed and easily retrieved? This
has also been well addressed in our work and led to the design and development of this
system.
Our system provides an intelligent assistance to users which involves detecting the temperament
and also at the same time providing a useful advice to the user on how to manage their
temperament among others. We were able to achieve this after gathering through a vivid study of
people’s natural inclination rather than their present practice, acquired by effort and self-control.
The questions developed from this study was used as our knowledge system. This question were
tested against the predefined characteristic of the several forms of temperament to ascertain which

86
of the questions belongs to a form. It is from this knowledge system that our developed system
draws its conclusion and accurately classify the temperament type of an individual. This we
believe is important and significant as knowing one‘s temperament and getting psychological
advice can go a long way in helping individuals relate and co-exist properly with people around
them easily without dispute. A great advantage of our system is that it does all what an expert
psychologist will do i.e temperament detection and also offers counselling.
2 . HUMAN TEMPERAMENT
Temperament are inborn characteristic in human life, they are the reasons for everything human
does in his/ her environment. Behavior is a very important part of an animal‘s observable features
and is mostly defined as what an animal does and how it does it, provided it is observable and
measureable.
They are four basic human temperament, these are:
 Sanguine: fun-loving and extroverted
 Choleric: ambitious and opinionated
 Melancholic: introspective.
 Phlegmatic: cool, calm and collected.
2.1 SANGUINE
People that exhibit sanguine character are said to be with abundance of blood. A sanguine person
does not penetrate the depth, essence of things and happenings; does not embrace the whole. He
loves light work which attracts attention, where there is no need of deep thought, or great effort.
A sanguine person is fun-loving, he loves activities that involve a lot of energy. A sanguine
person is unstable and encounters frequent alterations of mood say from happy to sad and sad to
happy. He is fashionable and is happy when praised.
Abbey can be categorised as a sanguine because he exhibits the following characters:
 He is creative and artistic types.
 He is self-composed
 He takes decision as early as possible
 Is talkative, frank, sociable and expresses emotions readily
 His decisions are often wrong.
2.2. CHOLERIC
A Choleric person is fundamentally ambitiousandleader-like.He is a hard driving who always aim
toaccomplish any goals set… he has a lot ofenergy,aggression, and/or passion, and tries to
enforce it in others. Because of his leadership spirit, he desire control, and are best at jobs that
demand strong control, authority, require quick decisions and instant attention. He care little for
the feelings of others.
2.3. PHLEGMATIC
A person exhibiting Phlegmatic temperament is usuallyrelaxed and quiet. Because of the relaxed
mind they are best in positions of conflict resolution,mediation and unity. The Phlegmatic is
mostly a female who tends to be the CCC(cool, calm and collected) easygoing, tolerant of others,

87
well-balanced, kind, usually do havesympathy for others,have the ability to hide emotions, is
happily reconciled to life, take things steadily i.e not in a hurry, do have many friends, try to
avoid conflict, inoffensive, quiet but witty, agreeable and intuitive, they are very peaceful, patient
and adaptable, they are reluctant, indecisive and a worrier.
2.4. MELANCHOLIC
A person exhibiting melancholic temperament iseasily embarrassed, self-conscious and timid. He
is always saidto be shy and often introverted. He is shy of standing before a group and when
forced to, finds it very difficult. He prefers to work, play all alone. He finds it difficult to form
acquaintances readily; prefers few number of friends.
3. MODULES OF THE PROPOSED SYSTEM
The striking feature of our system is the ability to test user based on multiple form of
temperament. This was achieved by testing the user with factors that intersect between two
different forms of temperament. A knowledge base was developed from the informationobtained.
The knowledge base is designed based on the set of rules.
The If-Then rules of the rule-base which can be classified into two categories:
(1) Several features of the four different forms of temperament
(2) Users response to questions asked
The former rules are concerned with the characteristic of several forms of temperament. In the
later, the answers provided by the user will be enquired, then based on those preferences the
knowledge base will be developed. On the basis of the details from the user and the knowledge
base, the type of temperament will be decided. There are 3 modules.
1. Developing Rule based knowledge-base
2. Collecting detailed information from the User through a user interface
3. Giving back the required information to the user
First step is to collect the information about different temperaments and store it in the
knowledge-base, this was achieved through the use of secondary data. Then rules are formed
based on the knowledge-base and the facts extracted. The developed system will get some
necessary information from the as system input and based on his information provided and the
facts in the knowledge base, the user will be provided with the needed information.
3.1. DEVELOPING RULE BASED KNOWLEDGE-BASE
In this module design of the system by constructing the following components:
1. Knowledge-base
2. Inference Engine
3. User Interface
Knowledge-base will contain all the extracted information that is necessary about the different
forms of temperament. The information will be collected manuallyand entered into the
knowledge-base. The system holds a collection of general principleswhich can potentially be
applied to any problem - these are stored in the knowledge base.

88
This information is processed by the inference engine. Inference Engine is a knowledge processor
which is modeled after the expert reasoning. The inference engine developed is a rule-based
reasoning which follows the backward reasoning technique. The essence of a rule-based
reasoning system is that it goes through a series of cycles. In each cycle, it attempts to pick an
appropriaterule from its collection of rules, depending on the present circumstances, and to use it
as described above. Because using a rule produces new information, it's possible for each new
cycle to take the reasoning process further than the cycle before. This is rather like a human
following a chain of ideas in order to come to a conclusion.
3.2. DATA REPRESENTATION: RELATIONAL KNOWLEDGE-BASE
Our data was gotten from several psychological textbook as they relate to the several forms of
temperaments and recently asked questions on temperament. For example, if an index case has 5
characteristics, all these characters will be check through the stored characters in the knowledge
base. This follows the backward chain reasoning technique, where the user’s response has an
equal probability of being any of the four forms of temperament. This was further broken down
into two after the first response from the user has been match against the knowledge based. The
output from this, categories the temperament into two
Choleric or melancholic temperament.
Sanguine or phlegmatic temperament
If this has been achieved, another question will emerge, this question will now be the basis to
further simplify the temperament from a group of two temperament to a single temperament. The
output of this stage is the respondent’s temperament.
The beautiful factor about our system is the ability to solve problem arising from individual
having mix temperament. Mixed temperaments are those in which one temperament
predominates and another temperament also manifests itself. We were able to provide solution to
this with the ability of our system to provide counselling advice to the user which will require
further inquiry into the respondent’s family trait.
Another very practical way to determine one's temperament consists in considering one's
reactions to offenses, by asking questions like:
Doctor: Can you forgive when offended?
Respondent:usually I cannot forget insults
Doctor: Do you bear grudges and resent insults
Respondent: I brood over them; to think of them excites me anew;
If the answer provided by the respondent to the questions are: I bear a grudge for a long time,
several days, weeks if somebody has offended me; I try to evade those who have offended me,
avoid speaking to them, e.t.c., then one is either choleric or melancholic temperament.
If the answers are otherwise i.e I do not harbor ill will; I don’t bear grudge cannot be angry with
anybody for a long time; I forget actual insults very soon and easily; I sometimes decide to show
anger, but I cannot do so, not even for a long time, at most an hour or two — if such is the
answer, then one is either sanguine or phlegmatic.
After detecting that one is of the choleric or melancholic temperament the following questions
needs to be answered to ascertain which temperament the person belongs to:
 Am I quickly excited at offenses?
 Do I extremely show my resentment by words or action?

89
 Do I feel reluctant to oppose an insult instantly and retaliate?
The explanation above, when presented in a suitably readable format, is as follows.
Do I react immediately and vehemently or slowly and superficially to a strong and hash
impression made upon me?
Figure 1. Sample of the Rule
Figure 2. Architecture of the System
4. DETAILS FROM USER THROUGH A USER INTERFACE
The user communicates with the expert system through the user interface which was designed
with JAVA Object Oriented ProgrammingLanguage. It allows the user to respond to some
questions which has been carefully selected , supply information and receive advice. The aim is to

90
provide the same form of communication provided by the expert in the field. With the help of
user interface, necessary response will be collected from the user. These response are mapped
with the rules from expert system.
Figure 3. Screenshot of the First Interface
4.1 PROVIDING THE REQUIRED INFORMATION TO THE USER
In this module the respondent will be provided with the information regarding his/her
temperament which he can get based on his responses. We will have the knowledge-base details
and the rule production system. After cross verifying the user response with the system the
temperament for the user will be suggested in the output screen. The output will comprise of both
the temperament and counseling advice.
Figure 4. Screenshot of the Question Interface

91
Figure 4. Screenshot of the Final Interface
5. CONCLUSION
This work presented the design and development of a rule based expert system for detecting
human Temperament.The system was developed to provide support for an expert psychologist in
properly predicting the temperament of an individual as well as given advice to the user. The
system does this by following designed rules. Of this, we have deduced some features that
characterizes known temperament types from which the system can accurately classify the user‘s
temperament based on the person‘s characters. Also, our work is solely limited to temperament
and mood detection, any expert advice sought from and given by the system is limited to this
scope.
ACKNOWLEDGEMENTS
The authors appreciate the reviewers for their careful reading of this paper, for their helpful
comments, this has made the work better. The author also send their appreciation to colleagues
who assisted in this work.
REFERENCES
[1] Kolodner, J. (1983): Maintaining organization in a dynamic long-term memory. Cognitive Science,
Vol.7, pgs.243-280.
[2] Schank, R. (1982): Dynamic memory; a theory of reminding and learning in computers and people.
Cambridge University Press.
[3] Schank, R. and Leake, D. (1989): Creativity and learning in a case-based explainer. Artificial
Intelligence, Vol. 40, no 1-3. pp 353-385.

92
[4] Aamodt, A., (1989) Towards robust expert systems that learn from experience - an architectural
framework. In John Boose, Brian Gaines, Jean-Gabriel Ganascia (eds.): EKAW-89; Third European
Knowledge Acquisition for Knowledge-Based Systems Workshop , Paris, July 1989. pp 311-326.
[5] Aamodt, A. (1991). A knowledge-intensive approach to problem solving and sustained learning,
Ph.D. dissertation, University of Trondheim, Norwegian Institute of Technology, May 1991.
(University Microfilms PUB 92-08460)
[6] Massie S. And Susan Craw And Nirmaliewiratunga (2006), Complexity-Guided Case Discovery for
Case Based Reasoning. The Robert Gordon University Aberdeen, AB25 1HG, Scotland, UK
[7] PanticMaja And Rothkrantz Leon, (2004), Case-Based Reasoning For User-Profiled Recognition Of
Emotions From Face Images Delft University of Technology EEMCS / Mediamatics Dept. Delft, the
Netherlands
[8] Dr. D. W. Ekstrand - Amazon”, located at:
http://corecanvas.s3.amazonaws.com/thetransformedsoul-
[9] Wos, Larry; Owerbeek, Ross; Ewing, Lusk; Boyle, Jim (1984). Automated Reasoning: Introductions
and Applications. Prentice Hall. p. 4. ISBN 0-13-054453-1.
[10] Grosof, Benjamin N. (30 December 1997). "Courteous Logic Programs: Prioritized Conflict Handling
For Rules" (Postscript). IBM Research Report. RC 20836 (92273).
[11] Moses, Yoram; Vardi, Moshe Y; Fagin, Ronald; Halpern, Joseph Y (2003).Reasoning About
Knowledge. MIT Press. ISBN 978-0-262-56200-3
Authors Profile
ShomoyeAbiodun R is final year student of Department of Computer Science,
Oduduwa University, Ipetumodu, Nigeria. His areas of interest are Artificial
Intelligence, object oriented programming, Software Complexity, Numerical
computation.
ShomoyeAdekunle I is a senior lecturer of Statistic, Department of Math and Stat,
Federal Polytechnic, Ilaro, Nigeria. His areas of interest are Artificial Intelligence,
Econometrics, Applied Statistic, Software Complexity, Numerical computation.

A rule based approach towards detecting human temperament

More Related Content

Viewers also liked (10)

Similar to A rule based approach towards detecting human temperament (20)

Recently uploaded (20)

A rule based approach towards detecting human temperament