Article
Enhancing Personalised Learning with a Context-Aware
Intelligent Question-Answering System and Automated
Frequently Asked Question Generation
Eleonora Bernasconi 1, *,† , Domenico Redavid 2,† and Stefano Ferilli 1,†
1 Department of Computer Science, University of Bari Aldo Moro, 70125 Bari, Italy;
2 Department of Economic and Finance, University of Bari Aldo Moro, 70124 Bari, Italy;
* Correspondence:
† These authors contributed equally to this work.
Abstract: The increasing integration of Artificial Intelligence (AI) in education has led to
the development of innovative tools like Intelligent Question-Answering Systems (IQASs),
aiming to revolutionize traditional learning paradigms. However, many existing IQAS
struggle with the nuances of natural language and the complexities of student questions.
This research focuses on developing a context-aware IQAS that leverages advanced Natural
Language Processing (NLP) techniques and contextual information, including student
learning history and educational content, to provide personalised support. This study
also introduces a software tool that utilizes NLP techniques to automatically generate
FAQs from educational materials. Employing a hybrid approach combining rule-based and
machine learning techniques, the IQAS demonstrated high accuracy in interpreting and
responding to a wide range of student queries. The software tool effectively automated the
generation of FAQs, creating a valuable resource for personalised learning. The findings
suggest that these tools can significantly improve student engagement, motivation, and
learning outcomes, highlighting the potential of AI to transform education and pave the
way for more personalised, adaptive, and effective learning environments.
Academic Editor: Vytautas Rudžionis
Keywords: intelligent question answering; educational technology; student learning
Received: 3 March 2025
enhancement; adaptive learning systems; knowledge graphs; natural language processing;
Revised: 31 March 2025
Accepted: 4 April 2025
transformers in education; AI-driven personalisation; educational data mining
Published: 7 April 2025
Citation: Bernasconi, E.; Redavid, D.;
Ferilli, S. Enhancing Personalised
Learning with a Context-Aware 1. Introduction
Intelligent Question-Answering The landscape of education is undergoing a dramatic transformation, propelled by the
System and Automated Frequently
rapid integration of Artificial Intelligence (AI) [1]. As traditional learning paradigms are
Asked Question Generation.
challenged, AI-powered tools are emerging as catalysts for personalised, engaging, and
Electronics 2025, 14, 1481.
https://doi.org/10.3390/
effective learning experiences. Among these advancements, Intelligent Tutoring Systems
electronics14071481 (ITSs) and Intelligent Question-Answering Systems (IQASs) stand out as particularly
promising innovations [2]. ITSs provide adaptive feedback and personalised learning
Copyright: © 2025 by the authors.
Licensee MDPI, Basel, Switzerland.
paths, while IQASs offer on-demand support, addressing students’ queries in real time.
This article is an open access article This confluence of technologies has the potential to revolutionize education, tailoring the
distributed under the terms and learning journey to individual student needs and fostering a deeper understanding of
conditions of the Creative Commons complex concepts [3].
Attribution (CC BY) license
However, despite the promise of these tools, current iterations of IQASs often fall short
(https://creativecommons.org/
of their potential. Many existing systems struggle to effectively decipher the nuances of
licenses/by/4.0/).
Electronics 2025, 14, 1481 https://doi.org/10.3390/electronics14071481
,Electronics 2025, 14, 1481 2 of 26
natural language, particularly within the complex and dynamic context of student–teacher
interactions [4]. Student queries, often imbued with colloquialisms, incomplete information,
or implicit assumptions, pose a significant challenge to these systems. Consequently,
responses may be inaccurate, irrelevant, or fail to address the underlying learning gap,
leading to frustration and hindering the learning process. This limitation underscores the
critical need for a more sophisticated IQAS that can accurately interpret and respond to a
wide range of questions, taking into account the context of the query, the student’s learning
history, and the specific educational content being addressed.
This research endeavors to address this gap by developing a novel, context-aware
IQAS designed to enhance learning outcomes and foster a more engaging and effective
learning environment. By leveraging cutting-edge Natural Language Processing (NLP)
techniques and incorporating contextual information, the proposed IQAS aims to deliver
tailored and informative answers to student queries, promoting a deeper understanding of
the subject matter [5]. Moreover, recognizing the importance of readily available knowledge
resources, this research introduces a complementary software tool that automatically
generates frequently asked questions (FAQs) from educational materials using advanced
NLP techniques [6].
This tool will not only provide students with quick answers to common questions but
will also aid instructors in developing more effective and comprehensive learning resources,
further supporting personalised learning and efficient knowledge dissemination.
1.1. Significance
This research holds significant implications for the future of education, spanning
theoretical, practical, and societal domains.
1.1.1. Theoretical Implications
This research pushes the boundaries of AI in education by exploring the synergis-
tic integration of contextual understanding, personalised learning, and advanced NLP
techniques in Question-Answering Systems [7]. It investigates how AI can be harnessed
to provide tailored support to students based on their individual needs, learning history,
and the specific context of their queries, contributing to a more nuanced understanding
of personalised learning in AI-driven educational environments [8]. Furthermore, this
study will contribute to the refinement of NLP algorithms for educational applications,
specifically addressing the challenges of ambiguity, context dependency, and the evolving
language patterns of students.
1.1.2. Practical Implications
The developed context-aware IQAS and the accompanying FAQ generation tool have
the potential to be seamlessly integrated into existing educational platforms and Learning
Management Systems (LMSs) [9]. This integration can provide students with immediate,
personalised support, potentially improving learning outcomes, increasing engagement,
and fostering a more interactive learning experience. The ability to cater to individual
learning styles and paces makes this technology particularly beneficial for diverse learners,
promoting inclusivity and accessibility in education. In addition, these tools can help
educators quickly create responsive learning materials, significantly reducing the time and
effort traditionally required to develop FAQs.
1.1.3. Societal Implications
At a broader level, this research contributes to the development of more effective,
accessible, and equitable educational tools. By democratizing access to personalised learn-
ing support and facilitating the dissemination of knowledge, these AI-powered tools can
, Electronics 2025, 14, 1481 3 of 26
empower students from all backgrounds to achieve their full academic potential. This,
in turn, can contribute to a more educated and informed populace, fostering intellectual
growth and social progress. The potential to bridge educational gaps and promote lifelong
learning underscores the transformative impact of this research on society [10].
1.2. Objectives
This research aims to design and implement a context-aware IQAS capable of ac-
curately interpreting and responding to a diverse range of student queries. The system
leverages contextual information such as each student’s learning history, prior interac-
tions, and course-specific materials to provide tailored and informative answers. Further-
more, the study seeks to enhance the system’s capacity to manage complex, nuanced, and
multifaceted questions by incorporating advanced reasoning, inference, domain-specific
knowledge, and strategies designed to address ambiguities or implicit assumptions often
present in student language. In addition to these efforts, the research involves developing
an automated software tool that generates comprehensive and relevant FAQs from educa-
tional materials, including textbooks, lecture notes, and online resources, by employing
advanced NLP techniques to identify frequently asked questions and produce accurate,
concise answers. Moreover, the project explores the seamless integration of both the IQAS
and the FAQ generation tool into existing Learning Management Systems (LMSs) to ensure
accessibility, user-friendliness, and broad adoption within familiar learning environments.
Finally, a comprehensive evaluation will be conducted to assess the performance of both
systems by comparing their effectiveness against traditional Question-Answering Systems,
existing AI-powered learning tools, and human tutors, using metrics such as accuracy,
relevance, response time, and user satisfaction.
1.3. Research Questions
This research seeks to address the following key questions:
1. RQ1: Optimizing NLP for educational context. How can Natural Language Processing
techniques be optimized to enhance the accuracy and relevance of responses generated
by the IQAS, specifically addressing the unique challenges posed by educational
content, student language, and the dynamic nature of classroom interactions?
2. RQ2: Handling complex and nuanced queries. What strategies can be implemented
to enhance the system’s ability to understand and respond to complex and nuanced
queries that require reasoning, inference, the integration of domain-specific knowl-
edge, and the resolution of ambiguities inherent in natural languages? [11]
3. RQ3: Seamless integration into learning environments. How can the IQAS and the
FAQ generation tool be seamlessly integrated into existing Learning Management Sys-
tems to provide effective, accessible, and user-friendly support to students, ensuring
compatibility across different platforms and learning environments?
4. RQ4: Effectiveness of automatic FAQ generation. How effective is the software
tool in automatically generating relevant, informative, and comprehensive FAQs
from diverse educational materials, and how can this tool be leveraged to sup-
port personalised learning, knowledge dissemination, and the creation of dynamic
learning resources?
5. RQ5: Impact on learning outcomes. What is the measurable impact of the context-
aware IQAS and FAQ generation tool on student learning outcomes, engagement, and
satisfaction compared to traditional learning methods and existing AI-powered tools?
Enhancing Personalised Learning with a Context-Aware
Intelligent Question-Answering System and Automated
Frequently Asked Question Generation
Eleonora Bernasconi 1, *,† , Domenico Redavid 2,† and Stefano Ferilli 1,†
1 Department of Computer Science, University of Bari Aldo Moro, 70125 Bari, Italy;
2 Department of Economic and Finance, University of Bari Aldo Moro, 70124 Bari, Italy;
* Correspondence:
† These authors contributed equally to this work.
Abstract: The increasing integration of Artificial Intelligence (AI) in education has led to
the development of innovative tools like Intelligent Question-Answering Systems (IQASs),
aiming to revolutionize traditional learning paradigms. However, many existing IQAS
struggle with the nuances of natural language and the complexities of student questions.
This research focuses on developing a context-aware IQAS that leverages advanced Natural
Language Processing (NLP) techniques and contextual information, including student
learning history and educational content, to provide personalised support. This study
also introduces a software tool that utilizes NLP techniques to automatically generate
FAQs from educational materials. Employing a hybrid approach combining rule-based and
machine learning techniques, the IQAS demonstrated high accuracy in interpreting and
responding to a wide range of student queries. The software tool effectively automated the
generation of FAQs, creating a valuable resource for personalised learning. The findings
suggest that these tools can significantly improve student engagement, motivation, and
learning outcomes, highlighting the potential of AI to transform education and pave the
way for more personalised, adaptive, and effective learning environments.
Academic Editor: Vytautas Rudžionis
Keywords: intelligent question answering; educational technology; student learning
Received: 3 March 2025
enhancement; adaptive learning systems; knowledge graphs; natural language processing;
Revised: 31 March 2025
Accepted: 4 April 2025
transformers in education; AI-driven personalisation; educational data mining
Published: 7 April 2025
Citation: Bernasconi, E.; Redavid, D.;
Ferilli, S. Enhancing Personalised
Learning with a Context-Aware 1. Introduction
Intelligent Question-Answering The landscape of education is undergoing a dramatic transformation, propelled by the
System and Automated Frequently
rapid integration of Artificial Intelligence (AI) [1]. As traditional learning paradigms are
Asked Question Generation.
challenged, AI-powered tools are emerging as catalysts for personalised, engaging, and
Electronics 2025, 14, 1481.
https://doi.org/10.3390/
effective learning experiences. Among these advancements, Intelligent Tutoring Systems
electronics14071481 (ITSs) and Intelligent Question-Answering Systems (IQASs) stand out as particularly
promising innovations [2]. ITSs provide adaptive feedback and personalised learning
Copyright: © 2025 by the authors.
Licensee MDPI, Basel, Switzerland.
paths, while IQASs offer on-demand support, addressing students’ queries in real time.
This article is an open access article This confluence of technologies has the potential to revolutionize education, tailoring the
distributed under the terms and learning journey to individual student needs and fostering a deeper understanding of
conditions of the Creative Commons complex concepts [3].
Attribution (CC BY) license
However, despite the promise of these tools, current iterations of IQASs often fall short
(https://creativecommons.org/
of their potential. Many existing systems struggle to effectively decipher the nuances of
licenses/by/4.0/).
Electronics 2025, 14, 1481 https://doi.org/10.3390/electronics14071481
,Electronics 2025, 14, 1481 2 of 26
natural language, particularly within the complex and dynamic context of student–teacher
interactions [4]. Student queries, often imbued with colloquialisms, incomplete information,
or implicit assumptions, pose a significant challenge to these systems. Consequently,
responses may be inaccurate, irrelevant, or fail to address the underlying learning gap,
leading to frustration and hindering the learning process. This limitation underscores the
critical need for a more sophisticated IQAS that can accurately interpret and respond to a
wide range of questions, taking into account the context of the query, the student’s learning
history, and the specific educational content being addressed.
This research endeavors to address this gap by developing a novel, context-aware
IQAS designed to enhance learning outcomes and foster a more engaging and effective
learning environment. By leveraging cutting-edge Natural Language Processing (NLP)
techniques and incorporating contextual information, the proposed IQAS aims to deliver
tailored and informative answers to student queries, promoting a deeper understanding of
the subject matter [5]. Moreover, recognizing the importance of readily available knowledge
resources, this research introduces a complementary software tool that automatically
generates frequently asked questions (FAQs) from educational materials using advanced
NLP techniques [6].
This tool will not only provide students with quick answers to common questions but
will also aid instructors in developing more effective and comprehensive learning resources,
further supporting personalised learning and efficient knowledge dissemination.
1.1. Significance
This research holds significant implications for the future of education, spanning
theoretical, practical, and societal domains.
1.1.1. Theoretical Implications
This research pushes the boundaries of AI in education by exploring the synergis-
tic integration of contextual understanding, personalised learning, and advanced NLP
techniques in Question-Answering Systems [7]. It investigates how AI can be harnessed
to provide tailored support to students based on their individual needs, learning history,
and the specific context of their queries, contributing to a more nuanced understanding
of personalised learning in AI-driven educational environments [8]. Furthermore, this
study will contribute to the refinement of NLP algorithms for educational applications,
specifically addressing the challenges of ambiguity, context dependency, and the evolving
language patterns of students.
1.1.2. Practical Implications
The developed context-aware IQAS and the accompanying FAQ generation tool have
the potential to be seamlessly integrated into existing educational platforms and Learning
Management Systems (LMSs) [9]. This integration can provide students with immediate,
personalised support, potentially improving learning outcomes, increasing engagement,
and fostering a more interactive learning experience. The ability to cater to individual
learning styles and paces makes this technology particularly beneficial for diverse learners,
promoting inclusivity and accessibility in education. In addition, these tools can help
educators quickly create responsive learning materials, significantly reducing the time and
effort traditionally required to develop FAQs.
1.1.3. Societal Implications
At a broader level, this research contributes to the development of more effective,
accessible, and equitable educational tools. By democratizing access to personalised learn-
ing support and facilitating the dissemination of knowledge, these AI-powered tools can
, Electronics 2025, 14, 1481 3 of 26
empower students from all backgrounds to achieve their full academic potential. This,
in turn, can contribute to a more educated and informed populace, fostering intellectual
growth and social progress. The potential to bridge educational gaps and promote lifelong
learning underscores the transformative impact of this research on society [10].
1.2. Objectives
This research aims to design and implement a context-aware IQAS capable of ac-
curately interpreting and responding to a diverse range of student queries. The system
leverages contextual information such as each student’s learning history, prior interac-
tions, and course-specific materials to provide tailored and informative answers. Further-
more, the study seeks to enhance the system’s capacity to manage complex, nuanced, and
multifaceted questions by incorporating advanced reasoning, inference, domain-specific
knowledge, and strategies designed to address ambiguities or implicit assumptions often
present in student language. In addition to these efforts, the research involves developing
an automated software tool that generates comprehensive and relevant FAQs from educa-
tional materials, including textbooks, lecture notes, and online resources, by employing
advanced NLP techniques to identify frequently asked questions and produce accurate,
concise answers. Moreover, the project explores the seamless integration of both the IQAS
and the FAQ generation tool into existing Learning Management Systems (LMSs) to ensure
accessibility, user-friendliness, and broad adoption within familiar learning environments.
Finally, a comprehensive evaluation will be conducted to assess the performance of both
systems by comparing their effectiveness against traditional Question-Answering Systems,
existing AI-powered learning tools, and human tutors, using metrics such as accuracy,
relevance, response time, and user satisfaction.
1.3. Research Questions
This research seeks to address the following key questions:
1. RQ1: Optimizing NLP for educational context. How can Natural Language Processing
techniques be optimized to enhance the accuracy and relevance of responses generated
by the IQAS, specifically addressing the unique challenges posed by educational
content, student language, and the dynamic nature of classroom interactions?
2. RQ2: Handling complex and nuanced queries. What strategies can be implemented
to enhance the system’s ability to understand and respond to complex and nuanced
queries that require reasoning, inference, the integration of domain-specific knowl-
edge, and the resolution of ambiguities inherent in natural languages? [11]
3. RQ3: Seamless integration into learning environments. How can the IQAS and the
FAQ generation tool be seamlessly integrated into existing Learning Management Sys-
tems to provide effective, accessible, and user-friendly support to students, ensuring
compatibility across different platforms and learning environments?
4. RQ4: Effectiveness of automatic FAQ generation. How effective is the software
tool in automatically generating relevant, informative, and comprehensive FAQs
from diverse educational materials, and how can this tool be leveraged to sup-
port personalised learning, knowledge dissemination, and the creation of dynamic
learning resources?
5. RQ5: Impact on learning outcomes. What is the measurable impact of the context-
aware IQAS and FAQ generation tool on student learning outcomes, engagement, and
satisfaction compared to traditional learning methods and existing AI-powered tools?
