Citation: Agrawal, G.; Deng, Y.; Park,
J.; Liu, H.; Chen, Y.-C. Building
Knowledge Graphs from
Unstructured Texts: Applications and
Impact Analyses in Cybersecurity
Education. Information 2022, 13, 526.
https://doi.org/10.3390/
info13110526
Academic Editor: Ryutaro Ichise
Received: 27 September 2022
Accepted: 2 November 2022
Published: 4 November 2022
Publisher’s Note: MDPI stays neutral
with regard to jurisdictional claims in
published maps and institutional affil-
iations.
Copyright: © 2022 by the authors.
Licensee MDPI, Basel, Switzerland.
This article is an open access article
distributed under the terms and
conditions of the Creative Commons
Attribution (CC BY) license (https://
creativecommons.org/licenses/by/
4.0/).
information
Article
Building Knowledge Graphs from Unstructured Texts:
Applications and Impact Analyses in Cybersecurity Education
Garima Agrawal
1,
* , Yuli Deng
1
, Jongchan Park
2
, Huan Liu
1
and Ying-Chih Chen
2
1
School of Computing and Augmented Intelligence, Arizona State University, Tempe, AZ 85281, USA
2
Mary Lou Fulton Teachers College, Arizona State University, Tempe, AZ 85281, USA
* Correspondence: garima.agrawal@asu.edu
Abstract: Knowledge graphs gained popularity in recent years and have been useful for concept
visualization and contextual information retrieval in various applications. However, constructing a
knowledge graph by scraping long and complex unstructured texts for a new domain in the absence
of a well-defined ontology or an existing labeled entity-relation dataset is difficult. Domains such as
cybersecurity education can harness knowledge graphs to create a student-focused interactive and
learning environment to teach cybersecurity. Learning cybersecurity involves gaining the knowledge
of different attack and defense techniques, system setup and solving multi-facet complex real-world
challenges that demand adaptive learning strategies and cognitive engagement. However, there are
no standard datasets for the cybersecurity education domain. In this research work, we present a
bottom-up approach to curate entity-relation pairs and construct knowledge graphs and question-
answering models for cybersecurity education. To evaluate the impact of our new learning paradigm,
we conducted surveys and interviews with students after each project to find the usefulness of bot
and the knowledge graphs. Our results show that students found these tools informative for learning
the core concepts and they used knowledge graphs as a visual reference to cross check the progress
that helped them complete the project tasks.
Keywords: knowledge graph; knowledge graph question answering systems (KGQA); natural
language processing (NLP); ontology; cybersecurity
1. Introduction
The ability to represent knowledge, visualize, manage and retrieve useful information
has made knowledge graphs more popular than other traditional knowledge-oriented
information management and mining systems. After Google coined the term ‘Knowledge
Graph’ (KG) in 2012 [1], mainly for the purpose of web-based semantic search, knowledge
graphs have undergone many technical advancements and broader applications both in
industry and academia. Knowledge graphs are basically an extension of semantic nets [2],
which represent knowledge in the form of interconnected nodes and arcs, where nodes
represent ‘objects’ or ‘concepts’ and the arcs or edges represent the interaction or relations
between them. The semantic nets lacked formal syntax and semantics, whereas knowledge
graphs overcame the limitations of these methods by defining a structured schema and
a formal way of interpreting the graphs. Knowledge graphs have an entity-centric view;
they not only focus on the structured representation of semantic knowledge but also on
how the entities are linked, interpreted and disambiguated. This helps in checking the
correctness, connectedness and consistency of information. Knowledge graphs provide
flexibility for the user in adding meaningful information or ‘explicit knowledge’ in the
form of entity attributes and relational labels. The convention to define the scope and
semantic conditions of entities and relations in a given domain is called an ontology. It is
crucial to have a well-defined ontology for the construction of a domain-specific knowledge
graph as the ontology enables domain entailment and drives the behavior of entities and
Information 2022, 13, 526. https://doi.org/10.3390/info13110526 https://www.mdpi.com/journal/information