=Paper=
{{Paper
|id=Vol-3234/paper3
|storemode=property
|title=Application of Knowledge Graphs for Creating a Library of Reusable Knowledge in the Smart City Domain
|pdfUrl=https://ceur-ws.org/Vol-3234/paper3.pdf
|volume=Vol-3234
|authors=Dmitry Kudryavtsev,Natalia Chichkova
|dblpUrl=https://dblp.org/rec/conf/qurator/KudryavtsevC22
}}
==Application of Knowledge Graphs for Creating a Library of Reusable Knowledge in the Smart City Domain==
https://ceur-ws.org/Vol-3234/paper3.pdf
Application of knowledge graphs for creating a library of
reusable knowledge in the smart city domain
Dmitry Kudryavtsev 1, Natalia Chichkova 1
1
Digital City Planner Oy, Lapinlahdenkatu 16, Helsinki, 00180, Finland
Abstract
Knowledge reuse can increase the quality and efficiency of different activities, as well as
reduce risks. The digital transformation of a city is a complex task that requires new approaches
and management technologies. Knowledge reuse can reinforce city digital transformation
initiatives, e.g. data integration and modeling activities can be improved via ontology reuse,
design and development of digital solutions can be enhanced via reference architectures and
reuse of existing methods and systems. Such reuse can speed up the work of city development
managers, digital architects, and other ICT specialists, as well as decrease costs and risks.
Although there are platforms for knowledge sharing and reuse within the smart city domain,
they apply a traditional document-oriented approach to knowledge representation. This limits
knowledge integration and the creation of intelligent services. So, knowledge graph technology
was selected for collecting and curating digital city planning reusable content. The Open
Research Knowledge Graph (ORKG) provided an opportunity for piloting this approach. The
current paper will overview the digital city planning observatory within the ORKG, including
main knowledge representation mechanisms and representative content examples, and provide
the link between content and application scenarios.
Keywords 1
Knowledge reuse, knowledge graph, smart city, city modeling
1. Introduction
People and organizations can reuse previous knowledge when encountering new tasks and challenges.
They can either take and apply documented knowledge or ask for advice from someone with relevant
prior experience. Knowledge reuse situations vary: reuse by shared knowledge producers, reuse by
shared work practitioners, reuse by expertise-seeking novices, and reuse by secondary knowledge
miners [1]. There are also different methods and techniques for “packaging” knowledge to stimulate
reuse: patterns (task patterns, ontology patterns, workflow patterns, etc.), reference models, best
practice cases, and lessons learned [2; 3]. Sometimes reusable knowledge is named knowledge building
blocks; for example, architecture and solutions building blocks are used within the enterprise
architecture management domain [4].
City digital transformation (or digitalization) is a complex task that requires new approaches and
management technologies:
• Number of tasks, stakeholders, problem-solving ways, and approaches is growing,
• Life speed is increasing: people need the newest innovative technologies and applications,
• New digital services for citizens and businesses are required.
Knowledge reuse can improve many activities (areas) within a city’s digital transformation:
1. Data integration and modeling activities can be improved via the reuse of data models and
ontologies,
Qurator 2022: 3rd Conference on Digital Curation Technologies, September 19-23, 2022, Berlin, Germany
EMAIL: dmitry.kudryavtsev@digicityplanner.com (A. 1); natalia.chichkova@digicityplanner.com (A. 2)
ORCID: 0000-0002-1798-5809 (A. 1); 0000-0002-6382-5259 (A. 2)
©️ 2020 Copyright for this paper by its authors.
Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).
CEUR Workshop Proceedings (CEUR-WS.org)
2. Design and development of city digital solutions and systems can be improved via reference
architectures and reuse of existing solutions/systems/methods,
3. (Re-)Design of public services and processes can be improved via the reuse of patterns and
reference process models,
4. Smart city management and development can be improved by reusing proven key performance
indicators from existing reference models and standards or by reusing existing cutting-edge
solutions for city analysis, monitoring, and control (including city digital twins).
Some initiatives and platforms support knowledge transfer and reuse in the smart city domain (see
section 2). But these initiatives and platforms use traditional document-oriented formats for knowledge
representations, so knowledge integration, access, and reuse are limited. It is also hard to develop
intelligent services using such knowledge representation. So there is a need for semantic representation
of reusable knowledge in the smart city domain.
2. Related work
There are several existing solutions and platforms for knowledge sharing and reuse in the smart city
domain including platforms with a broad scope, domain-specific platforms, and platforms for the
specific type of content.
1. Broad scope platforms with smart city solutions:
• Bee smart city platform (https://www.beesmart.city/) is a database of smart city cases
and solutions that is extended with elements of a social network of smart city experts.
This platform also collects information about tenders and is supported by matchmaking
and consulting services.
• Bable (https://www.bable-smartcities.eu/) offers information on how to implement smart
city solutions and includes a library of use cases, solutions, and products. It also provides
the opportunity for communication between companies and the city’s administration.
2. Domain-specific platforms:
• Eltis – The Urban Mobility Observatory (https://www.eltis.org/) is an EU-funded platform
that consists of tools, information, communication channels, and best practices to help
transport planners to create sustainable mobility.
3. Platforms for the specific type of content:
• Smartcity.linkeddata.es – a repository of ontologies about smart cities, energy, and other
related fields. The repository has a list of ontologies with their attributes: availability,
format, type of licenses, syntaxis, using language, domain, and link. Even though it is a
unique example of this type of ontology library, the biggest problem is it has not been
updated since 2015.
Although these platforms include well-structured libraries of materials, they use the "traditional"
approach for knowledge representation: text documents with metadata. Such an approach has
limitations in terms of knowledge access, reuse, and applicability for creating intelligent services. Smart
city best practices and cases can be accumulated via knowledge graphs in order to make them more
findable and reusable.
Also attempts to create a city knowledge graph were made several times all over the world. An example,
a Zaragoza’s Knowledge Graph [5]. The graph presents a mix of open-data and data management
system. The graph was built over 15 years. As a result, there is access to city data through a catalog or
open platform. The project was admitted as successful and is developing. But the existing city
knowledge graph initiatives are mostly related to the collection and integration of smart city data, while
we are interested in smart city knowledge reuse.
3. Information requirements within city digital transformation activities
Some examples of information/knowledge requirements within city digital transformation activities,
which can be supported by knowledge reuse, are presented in table 1.
Table 1
Examples of city digital transformation information/knowledge requirements
City digital Questions
transformation activities
Data integration and What concepts, domains, layers, dimensions, and relationships can be used for
modeling describing a city?
Design and development of What are the examples of digital solutions/systems for improving a specific
city digital solutions and domain or solving a particular problem? Are there any reusable ones?
systems What are the results and outcomes of a solution/system application in smart
cities?
What methods and approaches are used within the particular solution?
(Re-)Design of public What digital services can be offered to a specific category of citizens or
services and processes businesses within a particular context (event)?
How can services be delivered and implemented?
How specific processes can be organized and/or transformed using available
technologies?
Smart city management and What indicators can we use for measuring domain X?
development What city ranking systems exist, and what are the differences between them?
What indicators can we use for measuring outcomes, outputs, processes, and
inputs in domain X?
How to integrate and present city-related data for decision-making?
How city digital twins can be used for city management and development?
These information/knowledge requirements arise among city development managers, their digital
transformation teams, and/or solution providers.
4. The ORKG application for creating a library of reusable knowledge in the
digital city planning domain
4.1. Overview of the project and ORKG
Digital City Planner company aims to support city digital transformation via knowledge reuse and
application of knowledge graphs and semantic technologies. This initiative may help city development
managers do the following things:
1. Have easy access to the world’s best practices and experience in the smart city area,
2. Minimize hiring top/external consultants,
3. Have a holistic and evidence-based smart city development system,
4. Collect, prepare and pack knowledge for reuse and worldwide replication.
There are a lot of reference and reusable content in smart city domain, such as reference models,
ontologies, data models, classifications/taxonomies (e.g. of processes or services), patterns, good
practice cases, reusable methods, and systems. This content can be integrated and prepared for reuse
both by practitioners and researchers. From an industry point of view, such an effort can be considered
as a step toward the digital transformation of IT consulting services [6].
We decided to make a pilot project using publicly available research papers as a source of reusable
knowledge for city digital transformation. So despite the existence of different platforms for managing
knowledge graphs, we selected the Open Research Knowledge Graph (ORKG) platform provided by
the TIB Leibniz Information Centre for Science and Technology [7, 8]. The ORKG “aims to describe
research papers in a structured manner. With the ORKG, papers are easier to find and compare” [9].
The ORKG represents the next-generation digital library for semantic scientific knowledge. The ORKG
envisions “the transformation of the dominant document-centered knowledge exchange to knowledge-
based information flows by representing and expressing knowledge through semantically rich,
interlinked knowledge graphs” [8]. Originally, the ORKG is focused on researchers and aims to help
them “find relevant contributions to their field and create state-of-the-art comparisons and reviews”
[10]. But we also consider opportunities for ORKG usage by practitioners, more specifically by city
transformation and development teams.
So our pilot project for creating a library of reusable knowledge resulted in the curation of the digital
city planning observatory within the ORKG [11] (for more information about observatories see [12]).
4.2. Representation of smart city reusable knowledge in the ORKG
We took examples of city digital transformation information/knowledge requirements as input,
searched information via Google Scholar and Scopus, collected relevant research papers (primarily
reviews and comparisons), and transformed them into the ORKG format. This format includes a
structured description of the paper’s contributions, comparisons, and reviews (for more details about
the representation format see the ORKG documentation [13]). The key elements of the ORKG
representation format are described in Fig. 1.
Fig. 1. Overview of the ORKG representation format [created by authors]
Structured Descriptions of Research papers via Contributions
In the ORKG, knowledge that is traditionally described in scholarly articles is described semantically,
i.e. machine-readable. Research papers are added to the ORKG, and their contributions are described
in a structured way. Typically, a research contribution describes the addressed problem, the utilized
materials and methods, and the obtained result.
Our digital city planning observatory within the ORKG describes 296 research papers (for 30.07.2022).
Figure 1 demonstrates two examples of structured descriptions of research papers.
Part A of Figure 2 describes the KM4City ontology (a contribution of the paper [14]). This description
mostly covers classes that correspond to certain smart city modeling levels.
Every paper has a mandatory property: research problem. In addition, this property helps to categorize
papers inside of the ORKG system. All other properties were chosen based on the aim of our final
research. We have added properties “ontology name” and “type” to describe ontology and categorize it
for feature comparison. It was important to highlight which of the existing ontologies have been reused
to create current ontologies and link them with their articles (if there is one in the ORKG system).
Part B of Figure 2 describes a building permit recommender system for smart cities (a contribution of
the paper [15]).
As it was mentioned before, this article has a mandatory property research problem. Other properties
mainly classify the suggested recommender systems: by the smart city dimension, smart city action,
and smart city goal. Because the article includes use cases, we have added properties such as country,
city, and application scope to identify use case characteristics.
https://orkg.org/paper/R138642/R138645 https://orkg.org/paper/R138187/R138189
A) provides a structured description of a paper, B) provides a structured description of a paper,
which suggests smart city ontology [14] which suggests a recommender system for smart
cities [15]
Fig. 2. Structured description of research contributions within the DCP observatory
Comparisons
Comparisons are the main element of the ORKG platform, which integrates the contributions of
individual papers and gives an overview of any topic. The ORKG documentation says that
“comparisons are the core type of ORKG content and give a condensed overview on the state-of-the-
art for a particular research question. Contributions towards the problem are organized in a tabular view
and can be compared and filtered along different properties.” [13].
The Digital city planning observatory within the ORKG includes 32 comparisons (for 30.07.2022).
Figure 3 demonstrates a fragment of comparison “Ontologies for smart city: levels and key classes”,
which compares the content of 6 smart city ontologies described in the corresponding research papers
[16]. It shows and compares classes of the ontologies along 18 levels (e.g. physical level, service level,
safety, and risk management level).
Reviews
Reviews is the most integrative element of the ORKG. They can integrate one or more comparisons, a
description of the properties used in the comparison, visualizations and text blocks including an
introduction, conclusions, and links between the embedded elements. So, they give an opportunity to
create a holistic overview of a specific domain. “Reviews are a novel ORKG-based method to create
review or survey articles for giving an overview on research addressing a particular research question.”
[13].
Fig. 3. A fragment of the smart city ontology comparison
The Digital city planning observatory within the ORKG includes three reviews (for 30.07.2022).
Reviews can be provided with metadata (title, authors, etc.) and formally published with a DOI, they
can be updated, and new versions can be published, while the archive records prior versions and can
compare changes between revisions – for more details, see the documentation [13].
Figure 4 gives an overview of the Smart city's ontologies review, which integrates three comparisons
(1. Ontologies for smart city: levels and key classes, 2. Domain coverage in smart city ontologies, 3.
Ontology reuse in smart city ontologies). These comparisons in turn compare 18 papers described via
approximately 40 contributions.
Fig. 4. Smart city’s ontologies review as an integration of contributions and comparisons
4.3. Overview of the digital city planning observatory content
Totally the Digital City Planning (DCP) observatory within the Open Research Knowledge Graph
(ORKG) includes 296 papers, 32 comparisons and 3 reviews.
Table 2 gives an overview of reviews and comparisons within the DCP observatory and shows how
they can support various city digital transformation activities and corresponding
information/knowledge requirements from Table 1.
Table 2
Overview of the Digital City Planning observatory content (fragment)
City digital Questions The DCP observatory content at the
transformation ORKG
activities
Data integration What business / data objects exist Review: Smart city's ontologies review
and modeling in the domain? [17]
What are the relationships Comparisons: Ontologies for smart city:
between business / data objects levels and key classes [14]
in the domain? Domain coverage in smart city ontologies
[18]
Design and What are the examples of digital Comparison: Recommender systems for
development of solutions/systems for improving smart cities, Smart governance dimension
city digital a specific domain or solving a [19]
solutions and particular problem?
systems
Smart city What indicators can we use for Review: Smart and sustainable city's
management and measuring domain X? indicators [20]
development What indicators can we use for Comparisons: Standardized indicators for
measuring outcomes, outputs, Smart sustainable cities, by type of
process and inputs in domain X? indicators [21]
Analysis of natural environment indicators
How to integrate and present
in Smart Cities' standards [22]
city-related data for decision
making? Review: Towards a city digital twin [23]
How city digital twins can be
Comparisons: Thematic Identification of
used for city management and
the City Digital Twin Potentials [24]
development?
Application areas of Digital Twin solutions
in the smart city domain [25]
4.4. Knowledge curation methods and techniques
The following ORKG tools were actively used during the curation work:
Templates – they provide structure to comparisons and help to simplify entering contributions (for more
details see [13]).
Classes and resources (instances) – they helped us minimize duplicates in descriptions of papers
(contributions) and comparisons.
4.5. Existing application scenarios
Our pilot project and the resultant observatory within the ORKG can support city digital transformation
activities via two additional knowledge services: search and visual analytics.
Faceted search for relevant contributions within the ORKG
Figure 5 demonstrates the application of property-based filters for searching relevant AI systems
(recommender systems) within the comparison Recommender systems for smart cities, Smart
governance dimension [19]. Properties for the current comparison were chosen based on the original
research made by Lara Quijano-Sánchez et al [26].
The following filters are applied:
• Addresses smart city action = Citizen participation and inclusion AND
• Recommended items = Political candidates AND
• Application domain = Smart governance (restricted by the scope of the comparison).
This filtering results in the following two contributions:
1. A Recommender System with Uncertainty on the Example of Political Elections
2. A Fuzzy Recommender System for eElections
And what is especially important is that these two contributions are presented in a structured way, which
enables one to get answers to many questions without reading the papers. For example, we see the
recommendation approach and methods which were used within the suggested contributions. We also
see that one paper suggested a prototype and another one – an algorithm.
Although similar attributive or faceted search is provided by existing smart city knowledge sharing
platforms, their filtering properties are very limited and associated with a predefined document e.g. case
description.
Fig. 5. Faceted search of relevant items within the DCP observatory of the ORKG
Visual analytics
The content of the comparisons within the ORKG can be also represented in the visual format.
Figure 6 demonstrates the visualization of comparison results – several standardised sets of reference
indicators for Smart Sustainable cities are compared in terms of the types of indicators they have,
whether they mostly measure Input, Process, Output, Outcome or Impact aspects of the city
development and transformation activities [21].
The standardised sets of reference indicators for Smart Sustainable cities are mostly reflected in
international standards, which can be considered as the next step of maturity of research results.
The suggested visualization helps to identify standards which include, for example, a lot of Impact
indicators – ISO 37120, ITU 4902, UN SDG 11+.
Then another comparison can be used to get access to all these impact indicators – see figure 7 [22].
Fig. 6. Visualization of the comparison content
Fig. 7. Examples of city indicators for reuse
5. Future steps
The suggested Digital City Planning observatory within the ORKG can be considered as a MVP for
the knowledge-based product for city digital transformation.
Next steps can be associated with two sides: knowledge consumers and knowledge producers.
We envision consumption of reusable knowledge by city development managers and their teams
within different city digital transformation activities, such as design and development of city digital
solutions and systems, data integration and modeling, (re-)design of public services and processes.
Semantic knowledge representation enables the infrastructure for creating knowledge services for users,
for example, recommendations and/or reasoning. Also, reusable smart city knowledge in the form of
knowledge graph fragments can be used as building blocks for ontology-based city modeling and
creating city digital twins. The ideas of knowledge graph application for these purposes are already
elaborated for organizations in general [27, 28]. In order to establish effective consumption of reusable
knowledge, additional marketing research and customer development should be done: clarify jobs to be
done and pains of potential users, specify information requirements and possible use cases. Such market
understanding will enable the creation of demanded value proposition.
The production of reusable knowledge – the development of reference city knowledge graph should
also be modified. Nickel et al. [29] divided knowledge graph (KG) construction methods into four
groups: (1) curated approaches, i.e., KG created manually by a closed group of experts, (2) collaborative
approaches, i.e., KG created manually by an open group of volunteers, (3) automated semi-structured
approaches, i.e., KG extracted automatically from semi-structured text via handcrafted rules, and (4)
automated unstructured approaches, i.e., KG are extracted automatically from unstructured text. So it
is necessary to move from the current curated approach (1) to a collaborative one (2) with some
elements of automation (3 and/or 4). We envision the involvement of knowledge providers in this
collaborative effort since reusable knowledge for city digital transformation is created by research
institutes, providers of city digital solutions, universities, lighthouse cities, and associations; all these
parties can participate in the knowledge graph creation. So there is a need to establish the ecosystem
around the reference knowledge graph, which integrates reusable knowledge.
This approach is represented in figure 8.
Fig. 8. Platform for creating and reusing city digital transformation knowledge
6. Conclusions
City digital transformation can be enhanced via knowledge reuse. The city development managers and their
teams may do their work faster, cheaper and with low risks by reusing best practice cases, reference models,
patterns (task patterns, ontology patterns, workflow patterns, etc.), and other “knowledge building blocks”.
Although there are several platforms for smart city knowledge sharing and reuse, they apply a traditional
document-oriented approach to knowledge representation. Such an approach has limitations in terms of
knowledge access, reuse, and applicability for creating intelligent services. So, knowledge graphs
technology was selected for collecting and curating digital city planning reusable content. We decided to
make a pilot project using publicly available research papers as a source of reusable knowledge for city
digital transformation. So despite the existence of different platforms for managing knowledge graphs, we
selected the Open Research Knowledge Graph (ORKG) platform. So our pilot project for creating a library
of reusable knowledge resulted in the curation of the digital city planning observatory within the ORKG.
The paper described a representation of smart city reusable knowledge in the ORKG, gave an overview of
the digital city planning observatory content, highlighted knowledge curation methods and techniques, and
provided current and future application scenarios.
7. Acknowledgements
We would like to thank Sören Auer, Lars Vogt, and their colleagues from the ORKG team for their support,
advice, and direction. Knowledge curation work within the smart city planning observatory was also partially
supported by the ORKG Curation Grant from TIB.
8. References
[1] L.M. Markus, 2001. Toward a theory of knowledge reuse: Types of knowledge reuse situations
and factors in reuse success. Journal of management information systems, 18(1), (2001): 57-93.
[2] K. Sandkuhl Knowledge Reuse: Survey of Existing Techniques and Classification Approach. In:
Zimányi E., Kutsche RD. (eds) Business Intelligence. eBISS 2014. Lecture Notes in Business
Information Processing, vol 205. Springer, Cham. 2015. pp. 126–148.
[3] R. Weber, D.W. Aha, I. Becerra-Fernandez, Intelligent lessons learned systems. Expert systems
with applications, 20(1), (2001). pp.17-34.
[4] Section 5. Building Blocks in Architecture Content, The TOGAF Standard, 2022. URL:
https://pubs.opengroup.org/togaf-standard/architecture-content/chap05.html
[5] P. Espinoza-Arias, M. Fernández-Ruiz, V. Morlán-Plo, R. Notivol-Bezares, Oscar Corcho (2020).
The Zaragoza’s Knowledge Graph: Open Data to Harness the City Knowledge. Information. 11(3),
129.
[6] M. Bode, M. Daneva, M. J. van Sinderen, Characterising the digital transformation of IT consulting
services–Results from a systematic mapping study. IET software. (2022): 1-23.
[7] S. Auer, A. Oelen, M. Haris, M. Stocker, J. D’Souza, K.E. Farfar, L. Vogt, M. Prinz, V. Wiens,
M.Y. Jaradeh, Improving access to scientific literature with knowledge graphs. Bibliothek
Forschung und Praxis, 44(3), (2020). pp.516-529.
[8] A. Brack, A. Hoppe, M. Stocker, S. Auer, R. Ewerth, Analysing the requirements for an Open
Research Knowledge Graph: use cases, quality requirements, and construction strategies.
International Journal on Digital Libraries, 23(1), (2022). pp.33-55.
[9] The Open Research Knowledge Graph (ORKG), Main page, 2022. URL: https://orkg.org/
[10] Overview of the Open Research Knowledge Graph (ORKG), 2022. URL:
https://orkg.org/about/1/Overview
[11] Smart city planning observatory within the Open Research Knowledge Graph (ORKG), 2022.
URL: https://orkg.org/observatory/Smart_city_planning
[12] Observatories in the Open Research Knowledge Graph (ORKG), 2022. URL:
https://orkg.org/about/27/Observatories
[13] ORKG features. 2022. URL: https://orkg.org/about/14/Get_started
[14] Bellini, P., Benigni, M., Billero, R., Nesi, P., & Rauch, N. (2014). Km4City ontology building vs
data harvesting and cleaning for smart-city services. Journal of Visual Languages & Computing,
25(6), 827-839.
[15] Eirinaki, M., Dhar, S., Mathur, S., Kaley, A., Patel, A., Joshi, A., & Shah, D. (2018). A building
permit system for smart cities: A cloud-based framework. Computers, Environment and Urban
Systems, 70, 175-188.
[16] A. Begler, Ontologies for smart city: levels and key classes ver. 2 [Data set]. Open Research
Knowledge Graph, 2022. https://doi.org/10.48366/R215443
[17] D Chichkova, N., Kudryavtsev, D. Smart city's ontologies review. Review. Open Research
Knowledge Graph. 2021. URL: https://orkg.org/review/R159176
[18] N. Chichkova, D. Kudryavtsev, Domain coverage in smart city ontologies [Data set]. Open
Research Knowledge Graph. 2022. https://doi.org/10.48366/R145951
[19] D. Kudryavtsev, Recommender systems for smart cities, Smart governance dimension [Data set].
Open Research Knowledge Graph, 2022. https://doi.org/10.48366/R139567
[20] N. Chichkova, D. Kudryavtsev, Smart and sustainable city's indicators. Review. Open Research
Knowledge Graph. 2021. URL: https://orkg.org/review/R157397
[21] D. Kudryavtsev, Standardized indicators for Smart sustainable cities, by type of indicators [Data
set]. Open Research Knowledge Graph. 2021. https://doi.org/10.48366/R139568
[22] N. Chichkova, Analysis of natural environment indicators in Smart Cities' standards. [Data set].
Open Research Knowledge Graph. 2022. https://doi.org/10.48366/R152727
[23] N. Chichkova, D. Kudryavtsev, Towards a city digital twin, [Data set]. Open Research Knowledge
Graph. 2022. URL: https://orkg.org/review/R161914.
[24] N. Chichkova, D. Kudryavtsev, Thematic Identification of the City Digital Twin Potentials, [Data
set]. Open Research Knowledge Graph. 2022. URL: https://orkg.org/comparison/R161729/
[25] N. Chichkova, D. Kudryavtsev, Application areas of Digital Twin solutions in the smart city
domain, [Data set]. Open Research Knowledge Graph. 2022. URL:
https://orkg.org/comparison/R161728/
[26] L. Quijano-Sánchez, I. Cantador, M. E. Cortés-Cediel, O. Gil, Recommender systems for smart
cities. Information Systems, Volume 92, (2020). 101545.
[27] M. Kubelskiy, Application of Semantic Networks and Enterprise Architecture Approaches for
Creation of Digital Twins of Organizations, in Networks in the Global World V (A. Antonyuk and
N. Basov, eds.), (Cham), Springer International Publishing, 2021, pp. 144–161.
[28] G. Poels, H. A. Proper, D. Bork, DT4GITM-A Vision for a Framework for Digital Twin enabled
IT Governance. In HICSS, 2022. pp. 1-10.
[29] M. Nickel, K. Murphy, V. Tresp, E. Gabrilovich, A review of relational machine learning for
knowledge graphs. Proc. IEEE 104(1), 11–33 (2016).
https://doi.org/10.1109/JPROC.2015.2483592