Article Search
닫기

Original Article

Split Viewer

International Journal of Fuzzy Logic and Intelligent Systems 2022; 22(4): 373-381

Published online December 25, 2022

https://doi.org/10.5391/IJFIS.2022.22.4.373

© The Korean Institute of Intelligent Systems

IdVar4CL: Causal Loop Variable Identification Method for Systems Thinking Based on Text Mining Approach

Yudi Priyadi1 , Krishna Kusumahadi2, and Pramoedya Syachrizalhaq Lyanda1

1Department of Software Engineering, Telkom University, Bandung, Indonesia
2Department of Informatics Business, Telkom University, Bandung, Indonesia

Correspondence to :
Yudi Priyadi (whyphi@telkomuniversity.ac.id)

Received: July 10, 2021; Revised: May 1, 2022; Accepted: September 23, 2022

This is an Open Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License (http://creativecommons.org/licenses/by-nc/3.0/) which permits unrestricted noncommercial use, distribution, and reproduction in any medium, provided the original work is properly cited.

Systems thinking is a discipline for understanding wholeness and frameworks based on the changing patterns of the interconnectedness of the whole system. The storytelling of a system is a description of the mental model of an individual in describing the state of the environment. There are differences in the interpretation of the system description. This difference occurs because each individual has a different level of systems thinking in terms of experience, learning process, insight, intuition, and assumption in understanding system interactions. This study aims to extract data in the description of the storytelling of a systems thinking case by performing text mining and similarity to identify and find a variable to form causal loop diagrams. Based on the results of this study, there are results in the data extraction from the description of storytelling for the systems thinking case. The conclusions of this study are as follows: First, processing the five documents has successfully identified two documents with the highest similarity value, such as d1 and d3. Second, based on the cosine similarity calculation results and the results of the similarity value, there is a value closest to 1, such as 0.0913166. This value is at the d1 and d3 positions. Third, it produces a variable approach in the form of a group of words used in modeling thinking systems based on a connectedness value greater than 0.50.

Keywords: Systems thinking, Storytelling, Text mining, Similarity, Causal loop diagrams

This work was supported by the Directorate of Research and Community Service (PPM Tel-U), Department of Software Engineering (RPL), and Department of Informatics Business at Telkom University, Bandung 40257.

No potential conflict of interest relevant to this article was reported.

Yudi Priyadi currently actives as a researcher and lecturer at the Department of Software Engineering, Telkom University. He has the competence of teaching and practitioners in Text Mining, Data Management, Web Development, Information System Modeling, Multimedia Action Script, and Information Technology Risk Management.

E-mail: whyphi@telkomuniversity.ac.id

KrishnaKusumahadi currently actives as a researcher and lecturer in the Department of Informatics Business, Telkom University. He has the competence of teaching and practitioners in Systems Thinking, Data Modelling, and Big Data.

E-mail: kusumahadi@telkomuniversity.ac.id

Pramoedya Syachrizalhaq Lyanda currently actives as a researcher and student in the Department of Software Engineering, Telkom University. He is competent in the field of Software Requirement Specification.

Article

Original Article

International Journal of Fuzzy Logic and Intelligent Systems 2022; 22(4): 373-381

Published online December 25, 2022 https://doi.org/10.5391/IJFIS.2022.22.4.373

Copyright © The Korean Institute of Intelligent Systems.

IdVar4CL: Causal Loop Variable Identification Method for Systems Thinking Based on Text Mining Approach

Yudi Priyadi1 , Krishna Kusumahadi2, and Pramoedya Syachrizalhaq Lyanda1

1Department of Software Engineering, Telkom University, Bandung, Indonesia
2Department of Informatics Business, Telkom University, Bandung, Indonesia

Correspondence to:Yudi Priyadi (whyphi@telkomuniversity.ac.id)

Received: July 10, 2021; Revised: May 1, 2022; Accepted: September 23, 2022

This is an Open Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License (http://creativecommons.org/licenses/by-nc/3.0/) which permits unrestricted noncommercial use, distribution, and reproduction in any medium, provided the original work is properly cited.

Abstract

Systems thinking is a discipline for understanding wholeness and frameworks based on the changing patterns of the interconnectedness of the whole system. The storytelling of a system is a description of the mental model of an individual in describing the state of the environment. There are differences in the interpretation of the system description. This difference occurs because each individual has a different level of systems thinking in terms of experience, learning process, insight, intuition, and assumption in understanding system interactions. This study aims to extract data in the description of the storytelling of a systems thinking case by performing text mining and similarity to identify and find a variable to form causal loop diagrams. Based on the results of this study, there are results in the data extraction from the description of storytelling for the systems thinking case. The conclusions of this study are as follows: First, processing the five documents has successfully identified two documents with the highest similarity value, such as d1 and d3. Second, based on the cosine similarity calculation results and the results of the similarity value, there is a value closest to 1, such as 0.0913166. This value is at the d1 and d3 positions. Third, it produces a variable approach in the form of a group of words used in modeling thinking systems based on a connectedness value greater than 0.50.

Keywords: Systems thinking, Storytelling, Text mining, Similarity, Causal loop diagrams

Fig 1.

Figure 1.

Fundamental ideas for the IdVar4CL method.

The International Journal of Fuzzy Logic and Intelligent Systems 2022; 22: 373-381https://doi.org/10.5391/IJFIS.2022.22.4.373

Fig 2.

Figure 2.

Paragraphs as dataset. Source: https://time.com/5761097/jakarta-indonesia-floods

The International Journal of Fuzzy Logic and Intelligent Systems 2022; 22: 373-381https://doi.org/10.5391/IJFIS.2022.22.4.373

Fig 3.

Figure 3.

Illustration of causal loop variable identification.

The International Journal of Fuzzy Logic and Intelligent Systems 2022; 22: 373-381https://doi.org/10.5391/IJFIS.2022.22.4.373

Fig 4.

Figure 4.

Case folding.

The International Journal of Fuzzy Logic and Intelligent Systems 2022; 22: 373-381https://doi.org/10.5391/IJFIS.2022.22.4.373

Fig 5.

Figure 5.

Dataset documents.

The International Journal of Fuzzy Logic and Intelligent Systems 2022; 22: 373-381https://doi.org/10.5391/IJFIS.2022.22.4.373

Fig 6.

Figure 6.

Normalization and index.

The International Journal of Fuzzy Logic and Intelligent Systems 2022; 22: 373-381https://doi.org/10.5391/IJFIS.2022.22.4.373

Fig 7.

Figure 7.

Term frequency (TF) matrix.

The International Journal of Fuzzy Logic and Intelligent Systems 2022; 22: 373-381https://doi.org/10.5391/IJFIS.2022.22.4.373

Fig 8.

Figure 8.

Inverse document frequency (IDF).

The International Journal of Fuzzy Logic and Intelligent Systems 2022; 22: 373-381https://doi.org/10.5391/IJFIS.2022.22.4.373

Fig 9.

Figure 9.

Preview of TF-IDF matrix results.

The International Journal of Fuzzy Logic and Intelligent Systems 2022; 22: 373-381https://doi.org/10.5391/IJFIS.2022.22.4.373

Fig 10.

Figure 10.

Cosine similarity.

The International Journal of Fuzzy Logic and Intelligent Systems 2022; 22: 373-381https://doi.org/10.5391/IJFIS.2022.22.4.373

Fig 11.

Figure 11.

Stopword removal process.

The International Journal of Fuzzy Logic and Intelligent Systems 2022; 22: 373-381https://doi.org/10.5391/IJFIS.2022.22.4.373

Fig 12.

Figure 12.

Measures semantic similarity/relatedness between words.

The International Journal of Fuzzy Logic and Intelligent Systems 2022; 22: 373-381https://doi.org/10.5391/IJFIS.2022.22.4.373

Table 1 . Documents.

Document labelingDocument identification
d1The death toll from severe flooding in and around the Indonesian capital of Jakarta has risen to 66 as parts of the country continue to reel from heavy rain that began on New Year’s Eve.
d2Landslides and flash floods have displaced more than 36,000 in Jakarta and the nearby provinces of West Java and Banten, according to the ASEAN Coordinating Center for Humanitarian Assistance (AHA).
d3These are the worst floods Indonesia has seen since 2013, when at least 29 people edited in the aftermath of torrential rains.
d4The disaster, experts say, underscores the impacts of climate change in a country with a capital city that is sinking so quickly that officials are working to move it to another island.
d5The floods are also threatening to exacerbate the already severe wealth inequality that plagues the Southeast Asian nation.

Table 2 . Document similarity value..

d1d2d3d4d5
d110.036202630.09131660.079170810.04962767
d20.0362026310.0330806200.03595653
d30.09131660.03308062100.04534792
d40.079170810010
d50.049627670.035956530.0453479201

Table 3 . Identification of variables for causal loops.

Variable identification resultsValue of connectedness
DeathFloods0.7500
DeathPeople0.5455
DeathAftermath0.7059
DeathRains0.6316
TollFloods0.7059
TollAftermath0.7059
CapitalFloods0.5217
CapitalPeople0.5333
RisenSeen0.5714
RisenDied0.6667
PartsFloods0.6000
PartsPeople0.6000
CountryPeople0.9091
ContinueSeen0.5714
RainFloods0.6316
BeganSeen0.6667
YearFloods0.5333
YearPeople0.6667
EveFloods0.5333

Share this article on :

Related articles in IJFIS