Gift Recommendations Based On Personality Using Fu
Gift Recommendations Based On Personality Using Fu
Decree of the Director General of Higher Education, Research, and Technology, No. 158/E/KPT/2021
Validity period from Volume 5 Number 2 of 2021 to Volume 10 Number 1 of 2026
JURNAL RESTI
(Rekayasa Sistem dan Teknologi Informasi)
Vol. 6 No. 6 (2022) 987 - 992 ISSN Media Electronic: 2580-0760
Abstract
Gifts are usually given to someone to strengthen a relationship or to motivate someone. However, givers often need help
determining the appropriate gift for the potential recipient. On the other hand, many recipients are disappointed with the gifts
received. This event can result in the relationship between the giver and recipient being disrupted or the motivational goal not
being achieved. This research aims to develop a system to recommend gifts based on the recipient's personality. Gift
recommendation is determined based on the recipient's personality because the recipient highly values gifts that match the
recipient's personality. The system is built using the Fuzzy method, and the personality measurement tool used is the Big Five
Personality Test. Fifteen pairs of respondents validated the system. The validation results show that 80% of respondents as
gift-givers strongly agree that the system helps determine the appropriate gift for someone. In addition, 73.33% of respondents
as gift recipients strongly agree that the gifts recommended by the system do not disappoint them.
Keywords: gift recommendation, personality, big five personality, Fuzzy
recommendations from friends that do not match the are determined based on personality assessed using the
thoughts of the gift giver. Big Five Personality Test. The five personality
indicators used are extraversion, agreeableness,
The survey results show that around 40% of
conscientiousness, neuroticism, and openness. The
respondents were disappointed with the gift they
variables used to assess each personality indicator are
received. Some of the reasons put forward were because
taken from research conducted by Ramdhani. There are
the gifts given were not following needs, were not
43 variables used, namely: nine variables for indicators
useful, were not following what the recipient liked, and
of extraversion, nine variables for indicators of
was of poor quality. As a result, the gifts received
agreeableness, nine variables for indicators of
become trash.
conscientiousness, seven variables for indicators of
Several studies related to reward recommendation neuroticism, and nine for indicators of openness [16].
systems, the relationship between rewards and To find out the performance of the system being built,
personality, and recommendation systems using the Mar'i, et al. (2018) measured the accuracy of the system
Fuzzy method have been carried out before. Research using 22 test data. Accuracy is measured by comparing
conducted by Pereira et al. (2017) proposed a gift the results of professional recommendations from the
recommendation algorithm for mobile devices using the system with those based on the rules used in the Top
iOS operating system. The algorithm was developed Ranked Personality-Based Work Styles for 22 Job
based on adjustments to the COREL framework. Families. The test results show that the system built has
Recommendations are given based on products that an accuracy of 63%; 14 of 22 test data have the same
users and user preferences have rated in the Gifter recommendation results [16]. The researcher stated that
application [13]. The weakness of this recommendation the resulting accuracy value can still be improved by
system is that a product with a good rating or following optimizing the determination of the membership
the gift giver's preference may not necessarily meet the function.
expectations or needs of the potential gift recipient.
In this study, an application was built to help
Unlike the research conducted by Pereira et al. (2017), recommend gifts according to the personality of the
Shruti et al. (2018) designed a gift recommendation potential recipient. So the research conducted combines
system using a hybrid approach that combines the Science and Psychology by utilizing technology. The
Content-Based Recommendation method with personality of the potential gift recipients will be
Collaborative Filtering [14]. The researcher's purpose evaluated based on a psychological test, namely the Big
in building a gift recommendation system is to increase Five Personality (BFP). The variables used to measure
sales of an e-commerce website. Adiman and Guntara each indicator in the BFP, the inference rules, and the
[15] conducted the same research. The workings of the gift categories for each inference rule were developed
gift recommendation system begin with looking for with the help of two Psychologists. This is different
similarities in profiles of users who request from previous research conducted by Mar'i et al. (2018),
recommendations from other users using the which only used reference data from previous
Collaborative Filtering method. Furthermore, from researchers [16]. In addition, our research continues
users with the same profile as the user requesting beyond recommending gift categories. However, it is
recommendations, a common interest in existing developed further by determining specific gifts
products is sought using the Content-Based according to the limitations of the potential gift giver
Recommendation method. Products that have the (gender, age, moments, and hobbies of the potential gift
highest demand are recommended products. However, recipient, as well as the budget provided by the gift
profile similarities, especially general profiles (e.g., giver) and suggestions of web addresses where to buy
gender and age) between users, do not necessarily gifts.
indicate the similarity of interests and personalities
between users. 2. Research Methods
The relationship between reward and psychological The research was conducted in two stages. In the first
aspects was investigated by Pizetti [12]. Pizetti stated stage, data collection is carried out to form reference
that the potential recipient of the gift would highly data that will be used in the second stage. Meanwhile,
appreciate a gift that matches the personality of the in the second phase, a gift recommendation system will
potential recipient. On the other hand, gifts that do not be developed based on the personality of the potential
follow the personality of the potential recipient but gift recipients. The steps taken in the first stage can be
follow the giver's personality can be considered seen in Figure 1, while the steps taken in the second
coercion by the potential recipient. stage can be seen in Figure 2.
Mar'i et al. (2018) developed a system for determining
the proper professional recommendations for someone
using the Fuzzy Tsukamoto method. Recommendations
DOI: [Link]
Creative Commons Attribution 4.0 International License (CC BY 4.0)
988
Susana Limanto, Vincentius Riandaru Prasetyo, Ni Wayan Gitaputri
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol. 6 No. 6 (2022)
Start Start
Fuzzification
Store in database
DOI: [Link]
Creative Commons Attribution 4.0 International License (CC BY 4.0)
989
Susana Limanto, Vincentius Riandaru Prasetyo, Ni Wayan Gitaputri
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol. 6 No. 6 (2022)
0.8
a * z i i
z= i =1
n
(2)
0.6
ai
i =1
0.4
Where z is the result of defuzzification, n is the number
0.2
of rules obtained from the inference process, ai is the
0 4 8 12 16 20 24 28 32 36 40 minimum degree of membership of the i-th rule, and zi
is the implication value of the i-th rule.
Value
The rule with the smallest difference between the
implication value and the result of the defuzzification is
Figure 3. Input Membership Function used to determine the appropriate gift category. A
Furthermore, the inference process is carried out, recommended gift search was conducted based on these
namely looking for appropriate inference rules based on gift categories, the characteristics of potential gift
the results of the fuzzification process. Based on the recipients (gender, age, and hobbies), the moment of
rules obtained, the minimum value of the membership gift giving, and the available budget. The list of gifts
degree and each rule's output are calculated. according to the characteristics of recipients and the
moment was prepared with two Psychologists. The
After the inference process is complete, the implication results were stored in a database.
value is calculated using the minimum value resulting
from the inference process and the output membership A gift recommendation system according to personality
function. The Fuzzy output membership function used is made in a mobile application. Validation is carried
for the low and high categories is linear. Meanwhile, the out to evaluate the performance of the system created.
Fuzzy output membership function used for the medium Validation was carried out on 15 respondents who were
category is in the form of a triangular function (Figure selected using the simple random sampling method.
4) [16] [Mar'i, F., Mahmudy, W. F., & Yusainy]. The Each respondent was asked to find a partner who knew
formula for calculating the implication value can be the respondent well. For each pair of respondents, each
seen in Equation 1. respondent was asked to run the application to get the
right gift recommendation for their partner. After that,
z = zmax − a( zmax − z min ) (1) all respondents were asked to fill out two satisfaction
questionnaires, one as a gift giver and one as a gift
Where z is the crisp value of the output of the inference recipient. Respondent satisfaction is measured using a
process, Zmax is the highest value of the membership value between zero to five. A zero value indicates that
function of the Fuzzy output, Zmin is the lowest value the respondent strongly disagrees with the statement.
of the membership function of the Fuzzy output, and a While the value of five states that the respondent
is the minimum value of the degree of membership strongly agrees with the statement.
obtained from the inference process.
DOI: [Link]
Creative Commons Attribution 4.0 International License (CC BY 4.0)
990
Susana Limanto, Vincentius Riandaru Prasetyo, Ni Wayan Gitaputri
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol. 6 No. 6 (2022)
DOI: [Link]
Creative Commons Attribution 4.0 International License (CC BY 4.0)
991
Susana Limanto, Vincentius Riandaru Prasetyo, Ni Wayan Gitaputri
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol. 6 No. 6 (2022)
DOI: [Link]
Creative Commons Attribution 4.0 International License (CC BY 4.0)
992