=Paper=
{{Paper
|id=Vol-2627/short14
|storemode=property
|title=Malang Tourism Recommendation Using Mobile Based Group Decision Support System
|pdfUrl=https://ceur-ws.org/Vol-2627/short13.pdf
|volume=Vol-2627
|authors=Ratih Kartika Dewi,Muhammad Aminul Akbar,Mustika Mentari,I Made Wira Satya Dharma,Felinda Gracia Lubis,Ade Armawi Paypas
|dblpUrl=https://dblp.org/rec/conf/iicst/DewiAMDLP20
}}
==Malang Tourism Recommendation Using Mobile Based Group Decision Support System==
https://ceur-ws.org/Vol-2627/short13.pdf
MALANG TOURISM RECOMMENDATION USING MOBILE BASED GROUP
DECISION SUPPORT SYSTEM
Ratih Kartika Dewi1, Muhammad Aminul Akbar1, Mustika Mentari2 , I Made Wira Satya Dharma1, Felinda
Gracia Lubis1, Ade Armawi Paypas1
1
Faculty of Computer Science, Brawijaya University, Indonesia, ratihkartikad@ub.ac.id
2
Department of Information Technology, State Polytechnic of Malang, Indonesia
ABSTRACT
Malang has many tourist attraction so the decision support system can help user to choose the best place to be
visited. The Decision Support System used for tourist attractions in Malang was built with TOPSIS method.
TOPSIS was chosen as the primary algorithm due to its relatively low complexity of the algorithm so that it is
precisely used on mobile devices. However, DSS using TOPSIS method can accommodate recommendation for
single user only, it cannot be used for a group of users, whilst people usually go to a tourist attraction in a group.
Therefore, this research contributes to make a group decision support system based recommendation of Malang
tourism. In this research, usability test is conducted to understand user’s perception about the application. The
comparison between personal decision support system and group decision support system is conducted to
understand the impact of group decision support system in user perception. The comparison between decision
support system and group decision support system shows that SUS score of group decision support system (79.5)
is better than personal decision support system (72.5).
Key words: Malang tourism, Group Decision Support System, SUS score.
1. INTRODUCTION
These days, traveling is a need for some people. Malang, as one of the travel destinations in Indonesia, is showing
a rapid progress on its developments. Malang has appeal as the most visited spot for the tourists in East Java. It is
proved by the amount of the tourists coming to Malang. Not only going to the tourist attractions, but souvenirs
shopping is also one of the interesting things to do in Malang. This huge excitement is not balanced with the
information about the tourist attractions in Malang for the tourists, while the use of mobile devices is widely
increasing (Tolle et al., 2017). Therefore, it is necessary to develop Malang tourism recommendation application
based on mobile devices.
Research about mobile recommendation system has been conducted in (Ricci et al., 2010) it states that mobile
devices are primary tools for information access and when combined with recommender system technologies, they
can used for leisure and business applications. Tourism or travel recommendation system suggest product or tourist
destination and provide the user with information to support their process of decision making (Ricci et al., 2002).
Research about recommendation system in tourism are (Kabassi et al., 2010) that contributes in personalizing
recommendations for tourist and (Meehan et al., 2013) about context aware recommendation system for tourism.
Malang tourism recommendation by using mobile application has been done in the research (Dewi et al., 2019).
The research (Dewi et al., 2019) used TOPSIS as the decision support system algorithm of the Malang tourism
recommendation. TOPSIS was chosen as the algorithm used in the research due to its relatively low complexity
of the algorithm, so that it is precisely used on mobile devices. However, DSS using TOPSIS method cannot be
used for a group of users, whilst people usually go to a tourist attraction in a group (Dewi et al., 2018). Therefore,
this research contributes to make a group decision support system based recommendation of Malang tourism.
Previous research concentrates in the algorithm & the proof of its effectiveness, but there is no usability testing of
the application from the user perspective. In this research, usability test is conducted to understand user’s
perception about the application. The comparison between personal decision support system and group decision
support system is conducted to understand the impact of group decision support system in user perception.
2. LITERATURE REVIEW
The literature review of this research are including group decision support system, group decision support system
algorithm and usability testing.
Copyright © 2020 for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).
IICST2020: 5th International Workshop on Innovations in Information and Communication Science and Technology, Malang, Indonesia
Malang Tourism Recommendation Using Mobile Based Group Decision Support System
2.1 Group Decision Support System (GDSS)
GDSS is used to accommodate preferences of the decision makers, so it creates group decision. In the
recommendation system scenario, users tend to make decisions in a group rather than personal. Group preferences
are more complex and relatively different than personal preferences. Group decision support system method
calculates the preferences of all members of the group and gives a set of recommendation based on it (Dewi et al.,
2018). Decision support system (DSS) has 3 interconnected core component. DSS components consist of data
management, model management and communication management (Turban, 2005) as explained in Figure 1.
Internet
Data
Data Management Model Management
User Communication Management
Fig. 1. Decision Support System Architecture
2.2 Group Decision Support System (GDSS) Algorithm
In this research, group decision support system developed with TOPSIS algorithm that combined with voting rule
algorithm. Figure 2 explains the flow of the group recommendation.
Group
User 1 User 2 User 3 User n
TOPSIS: TOPSIS: TOPSIS: TOPSIS:
User 1 User 2 User 3 User n
Voting Rule
Algorithm
Malang tourism recommendation
Fig. 2. Flow Diagram of GDDS Algorithm
91
Copyright © 2020 for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).
Dewi R.K., Akbar M.A., Mentari M., Dharma I.M.W., Lubis F.G., Paypas A.A
TOPSIS is used to give personal recommendation of Malang tourism (Dewi et al., 2019). Recommendation
method using TOPSIS (Technique for Order of Preference by Similarity to Ideal Solution) is done the same way
as (Hwang, 2012). While voting rule algorithm is used to rank group voting. The first alternative in the ranking is
given a value greater than the other alternative with the rank position below it as in a pairwise comparison. Based
on final calculation of the alternatives, alternative with the highest value is the most recommended or preferred by
the decision makers.
2.3 Usability Testing with System Usability Scale
The System Usability Scale (SUS) was found by John Brooke in 1986. It is a usability test to evaluate variety of
system types in practical. SUS is cheaper than any usability test, because it only requires some prospective users,
and also quicker, because the template of statements is ready to be used and adjusted to the needs. Usability test is
conducted to understand user’s perception about the application (Gutiérrez-Carreón et al., 2015). SUS (System
Usability Scale) is done the same way as (Brooke, 2013) with 10 usability questions:
a) I think that I would like to use this system frequently
b) I found the system unnecessarily complex
c) I thought the system was easy to use
d) I think that I would need the support of a technical person to be able to use this system
e) I found the various functions in this system were well integrated
f) I thought there was too much inconsistency in this system
g) I would imagine that most people would learn to use this system very quickly
h) I found the system very cumbersome to use
i) I felt very confident using the system
j) I needed to learn a lot of things before I could get going with this system
3. RESEARCH METHOD
Group decision support system in this research is developed under the same architecture of general decision
support system architecture in Figure 1. Decision support system (DSS) has 3 interconnected core component.
DSS components consist of data management, model management and communication management as in Figure
3.
Usability
Develop
Develop data Develop model testing with
communication
management management SUS (Personal
management
vs Group DSS)
Fig. 3. Block Diagram of Research Methodology
Data management is related with the data used in group decision support system. In decision support system,
there are 2 important terms, criteria and alternative. The Malang tourism data used as the recommendation option
is referred as the alternative, while the variable that affects the decision maker to make a decision of some
alternatives is referred as the criteria.
Model management used in this research is TOPSIS (Technique for Order of Preference by Similarity to Ideal
Solution) combined with voting rule algorithm. The detail steps of Malang tourism recommendation using group
decision support system are explained in section 2.2.
Communication management is the user interface, it accommodates the user to interact with the group decision
support system that has been built. Communication management in this research is developed in Android platform.
4. RESULT AND DISCUSSION
The final result of this research consists of the core components of the group decision support system. Those
components are data management and communication management. Overall, data management in this research is
explained in Table 1.
92
Copyright © 2020 for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).
Malang Tourism Recommendation Using Mobile Based Group Decision Support System
Table 1. Data Management.
No. Type of Malang Tourism Criteria Alternative
Recommendation
1 Tourists destination in Malang & Price, distance, rating, number List of recommendations for
Batu of reviewers Tourists destination in Malang &
Batu
2 Beach around Malang Price, distance, rating, List of recommendations for
transportation access, facility Beach around Malang
3 Shopping destination in Malang Rating, facility, operational List of recommendations for
hours, distance Shopping destination in Malang
4 Place to buy souvenirs in Malang Distance, price, store’s List of recommendations for
existence Place to buy souvenirs in Malang
5 Place to buy Korean cuisine Price, rating, operational hour, List of recommendations for
distance, facility Place to buy Korean cuisine
6 Café in Malang Price, situation, distance, List of recommendations for
facility, rating Café in Malang
7 Martial arts in Malang Distance, price, training List of recommendations for
duration martial arts training center
Model management used in this research is TOPSIS (Technique for Order of Preference by Similarity to Ideal
Solution) combined with voting rule algorithm as in Section 2.2. Communication management (user interface) in
this research is developed under Android platform. The user interface of the application is shown in Figure 4-6. It
is the group decision support system recommendation application for one of the Malang tourism applications,
places to buy souvenirs in Malang.
Fig. 4. User interface to choose the number of user
In Figure 5, user can choose the number of the user that will be included in GDSS. Figure 6 shows the user
interface where user can choose DSS button (for personal recommendation system) or Group DSS button (for
group recommendation system).
93
Copyright © 2020 for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).
Dewi R.K., Akbar M.A., Mentari M., Dharma I.M.W., Lubis F.G., Paypas A.A
Fig. 5. User interface to get the recommendation
Figure 7 is the list of recommendation. These communication management are adapted from our previous study
(Dharma et al., 2020).
Fig. 6. User interface to get the list of recommendation
94
Copyright © 2020 for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).
Malang Tourism Recommendation Using Mobile Based Group Decision Support System
In this research, usability test is conducted to understand user’s perception about the application. The
comparison between personal decision support system and group decision support system is conducted to
understand the impact of group decision support system in user perception as in Table 2.
There are 5 users that familiar with mobile application and ever have a holiday vacation in Malang that will be
respondents for usability testing with system usability scale (SUS). SUS statement was given to them and each
statement has a scale of 1 to 5, which means 1 for strongly disagree and 5 very agree to the statement in the SUS
instrument. The final step is to analyze the test results that are calculated according to SUS calculations. The
comparison between decision support system and group decision support system shows that SUS score of group
decision support system (79.5) is better than personal decision support system (72.5).
Table 2. Usability testing.
Personal DSS Group DSS
User 1 28 *2.5 = 70 31 *2.5 = 77.5
User 2 30 *2.5 = 75 35 *2.5 = 87.5
User 3 28 *2.5 = 70 25 *2.5 = 62.5
User 4 30 *2.5 = 75 35 *2.5 = 87.5
User 5 29 *2.5 = 72.5 32 *2.5 = 80
SUS Score 72.5 79.5
5. CONCLUSION AND FUTURE WORK
The implementation of group decision support system is successfully implemented in Android platform. In this
research, usability test is conducted to understand user’s perception about the application. The comparison between
decision support system and group decision support system shows that SUS score of group decision support system
(79.5) is better than personal decision support system (72.5). It is also stated that the application can be accepted
by the users. For further research, it is recommended to choose specific voting rule algorithm, for example BORDA
algorithm and test the results with rank consistency testing. Rank consistency testing is recommended to test the
GDSS algorithm.
ACKNOWLEDGEMENT
Authors (Ratih Kartika Dewi, M. Aminul Akbar, I Made Wira Satya Dharma, Felinda Gracia Lubis, Ade Armawi
Paypas, Mustika Mentari) want to thanks lecturers and under graduate students from the Laboratory of media
technology, games, and mobile devices, Faculty of Computer Science, Brawijaya University. Authors also want
to thank colleagues from State Polytechnic of Malang for the participation in this research.
REFERENCES
Brooke, J. (1996). SUS-A quick and dirty usability scale. Usability evaluation in industry, 189(194), 4-7.
Dewi, R.K. (2019). Group Decision Support System based on AHP-TOPSIS for Culinary Recommendation
System. Jurnal Ilmu Komputer dan Informasi, 12(2), 85-90.
Dewi, R.K., Ananta, M.T., Fanani, L., Brata, K.C., and Priandani, N.D. (2018). The Development of Mobile
Culinary Recommendation System Based on Group Decision Support System. International Journal of
Interactive Mobile Technologies (iJIM), 12(3), 209-216.
Dewi, R.K, Mentari, M., Saputro, W., Nugroho, U.A., and Hibatullah M.H. (2019). Usability Analysis of TOPSIS
based Mobile Recommender System of Malang Tourism, In: The 4th International Conference on
Sustainable Information Engineering and Technology, 285-288. IEEE: New York NY.
Dharma, I.M.W.S, Dewi, R.K., and Akbar, M.A. (2020). Pengembangan Aplikasi Android Sistem Rekomendasi
Kelompok Tempat Pembelian Kerajinan Tangan Khas Malang dengan Metode TOPSIS-BORDA.
Undergraduate thesis of Brawijaya University, 2020.
95
Copyright © 2020 for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).
Dewi R.K., Akbar M.A., Mentari M., Dharma I.M.W., Lubis F.G., Paypas A.A
Gutiérrez-Carreón, G., Daradoumis, T., and Jorba, J. (2015). Integrating learning services in the cloud: An
approach that benefits both systems and learning. Journal of Educational Technology & Society, 18(1), 145-
157.
Hwang, C.-L., and Yoon, K. (1981). Methods for multiple attribute decision making, In: Multiple attribute decision
making, 58-191. Lecture Notes in Economics and Mathematical Systems, 186. Springer: Berlin, Heidelberg.
Kabassi, K. (2010). Personalizing recommendations for tourists. Telematics and Informatics, 27(1), 51-66.
Meehan, K., Lunney, T., Curran, K., and McCaughey, A. (2013). Context-aware intelligent recommendation
system for tourism, In: 2013 IEEE Annual Conference on Pervasive Computing and Communications
Workshops (PerCom), 328-331. IEEE: New York NY.
Ricci, F. (2010). Mobile recommender systems. Information Technology & Tourism, 12(3), 205-231.
Ricci, F. (2002). Travel recommender systems. IEEE Intelligent Systems, 17(6), 55-57.
Saputra, I.M.A.B., and Wardoyo, R. (2017). Sistem Pendukung Keputusan Kelompok Penentuan Karyawan
Terbaik Menggunakan Metode Topsis dan Borda. IJCCS (Indonesian Journal of Computing and Cybernetics
Systems), 11(2), 165-176.
Tolle, H., Pinandito, A., Kharisma, A.P., and Dewi, R.K. (2017). Pengembangan Aplikasi Perangkat Bergerak.
Universitas Brawijaya Press.
Turban, E., Liang, T.P., and Aronson, J.E. (2005). Decision Support Systems and Intelligent Systems (International
Edition). Pearson Prentice Hall: Upper Saddle River NJ.
96
Copyright © 2020 for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).