The Role of Artificial Intelligence in Smart Classes:
A survey
Eleni Dimitriadou
Visual Media Computing Lab
Dept. of Multimedia and Graphic Arts
Cyprus University of Technology
Limassol,
Cyprus
ela.dimitriadou@edu.cut.ac.cy
Abstract—During the years, the concept of “Smart Classroom”
evolved to reflect technological advances. This survey provides
a review of research work on smart classroom technologies,
with a focus on emerging and Artificial Intelligence(AI)-related
technologies. Smart classroom technologies related to the effective
class management that enhance the convenience of classroom
environments, the use of teaching aids during the educational
process and the use of performance assessment technologies
are presented. Apart from discussing the range of technological
achievements in each of the aforementioned areas, the role of
AI is thoroughly discussed allowing researchers and developers
in AI to realize the existing uses of AI in smart classes and get
informed about future perspectives and challenges in adopting
AI-based techniques in smart classes.
Index Terms—Artificial intelligence, Emerging technologies,
Smart classroom.
I. I NTRODUCTION
The concept of “Smart Classroom” was first proposed by
Rescigno [1] in relation to the classroom use of several tech-
nologies that flourished during the eighties, such as personal
computers, video programs presentation, the use of closed-
circuit television, and the use of networking facilities. Through
the years the meaning of a “Smart Classroom” evolved to
reflect technological advances. Recently, Micrea et al. [2] state
that a smart classroom is based on devices of automated com-
munication and mobile learning, mobile technologies, video
projectors, sensors, cameras, facial recognition algorithms
and other modules controlling different physical environment
parameters. Based on the latest technological developments,
in this study we define a smart classroom as an integrated
learning space that combines Artificial Intelligence (AI) and
emerging technologies to offer an intelligent learning space
either in-class or remotely.
Emerging technologies are defined as the most impactful
and recent technologies of our era [3] while “Artificial Intel-
ligence” (AI) is defined as the ability of computer systems to
do human tasks (like learning and thinking) that frequently
can only be attained with the use of human intelligence [4].
This survey provides a review of research work on smart
classroom technologies, with a focus on emerging and AI-
related technologies. A wide range of smart-class technologies
Andreas Lanitis
Visual Media Computing Lab
Dept. of Multimedia and Graphic Arts
Cyprus University of Technology
& CYENS Centre of Excellence
Limassol, Cyprus
andreas.lanitis@cut.ac.cy
that belong to the three main pillars of “Class Manage-
ment”, “Teaching Aids”, and “Performance Assessment” are
presented, while attention is focused on existing and future
applications of AI in smart classes, enabling the readers to
gain an insight related to the opportunities and challenges
involved in applying AI in smart classes. Previous surveys
related to smart classes include the work of Saini and Goel
[5], who focus on technologies related to smart content
preparation and distribution, smart student engagement, smart
assessment, and smart physical environment. While this survey
has some similarities to our approach, in our case we focus
our attention on the use of AI in conjunction with emerging
technologies in a smart class environment. In a more recent
survey Li and Wong [6] present application domains, research
issues, research participants, learning devices or tools, learning
environments and learning features, which were found in 90
studies related to smart classrooms. Unlike the current survey,
the work of Li and Wong [6] is directed towards educators,
to help them understand their role in smart learning practice.
Spector et. al. [7] point out the significance of technological
advancements into the introduction of innovative learning
approaches, and hence divide smart learning environment
foundations into three main cores, philosophical, phycological
and technological. These fields contribute into the creation
of an effective, adaptive and innovative learning environment
with the aim to develop the mindset of students. In addition,
Tabuenca et al. [8] state that a smart learning environment
includes both the students and the teacher as it gives them the
opportunity to exploit technological tools in order to execute
their tasks.
In the remainder of the paper, we present a literature
review for smart classroom technologies related to classroom
management, teaching aids, and performance assessment. In
Section 3, we elaborate on the role of AI in smart classes,
followed by a discussion and concluding comments.
II. S MART C LASSROOM T ECHNOLOGIES
In this section key smart-class technologies related to
effective class management, teaching aids, and performance
assessment are presented (see Table I). The proposed smart
class technologies taxonomy in Table I, is inspired by the
taxonomy proposed by Saini and Goel [5] who separate smart
class technologies into the categories of smart interaction
and engagement, performance assessment, smart content and
presentation, and smart physical environment. Based on a wide
range of papers and surveys in the fields of pedagogy and
technology, along with recent advances in technological tools
and AI-based methods, the refined version of the taxonomy
shown in Table I is adopted.
TABLE I
TAXONOMY OF S MART C LASSROOM T ECHNOLOGIES .
Classroom
Management
Teaching Aids Performance
Assessment
Smart Environment Robotics Student performance
assessment/prediction
Attendance Management Virtual/Augmented Teacher performance
Mixed Reality assessment
Surveillance/Security E-learning
Platforms
Flipped/Virtual
Remote Classroom
A. Classroom Management
The term classroom management refers to the way or
approach that a teacher uses to manage a classroom as part
of an effort to maintain a comfortable and safe teaching
environment that contributes to the efficient class delivery.
In relation to class management technologies, in this survey
we focus on the issues of Smart Environment, Attendance
Management, and Surveillance/Security.
1) Surveillance/Security: Computer Vision techniques in
smart classroom are often used to help educators to analyse
videos and images of their students as a means of acquiring
important information regarding students. Typically computer
vision is used for attendance management and student action
recognition. Facial recognition can be utilized to implement
innovative attendance management systems in smart class-
rooms that automatically record the presence of a registered
student in class [9]. Human action recognition is a vision-
based technique that can identify actions performed by humans
in video sequences [10]. The ability to recognize human
behavior can be extremely important in a smart classroom [11]
as it can be used for determining student activity through the
analysis of eye, face and body motion.
Several researchers addressed the problem of using AI in
the form of Computer Vision algorithms for automated student
attendance registration and for recognizing students’ actions.
Chowdhury et al [12], proposed an automatic student atten-
dance system based on face recognition using Convolutional
Neural networks (CNN’s) to detect and recognize multiple
student’s face from real-time video stream obtained by a static
camera located in a classroom. Instead of using a static camera,
Mery et al. [13] describe a student attendance system based
on deep learning used in crowded classrooms (70 students),
in which the session images are captured by a smartphone
camera. Instead of using a static or a mobile camera, Gupta
et al. [14], presented a Computer Vision based Unobtru-
sive Classroom Attendance Management System, that uses
a rotating camera to capture images of the students. Student
action recognition can be extended to cover the recognition of
actions performed by students attending online courses [15],
supporting in that way the remote learning activities.
2) Smart Environment: Smart buildings are described as
whole structures that use existing technology resources and
AI to produce a secure, functioning and friendly setting
that utilizes resources wisely and economically [16]. Smart
buildings provide numerous advantages for both users and
the ecosystem, since the utilization of smart technologies
allows power consumption to be reduced, repair expenses to
be decreased, real-time activities to be enabled, problems to be
predicted beforehand, devices to be controlled in real time, and
environmental effects to be improved [17]. Sensor technology,
the Internet of Things (IoT), external telecommunications
and smartphone software technology are commonly used to
power advanced technologies in smart classrooms [18].The
capacity of AI technologies to forecast and identify patterns
is a crucial feature; as a result, they can be flexible and cope
with complicated human habits and meet their unique demands
by processing large amounts of data offered by smart space
devices [19].
B. Teaching Aids
In a modern smart-classroom, the teaching process is as-
sisted by a plethora of technological means, to maximize
the engagement and interaction of students. Towards this
end different types of technology in the form of robotics,
virtual/augmented/mixed reality, e-learning platforms, visu-
alization techniques, and flipped classroom technologies are
being used. In this section we provide an overview of these
technologies.
1) Robotics: Robots used in education can be ‘Real’ de-
vices [20, 21], or they can be software agents in the form
of chatbots [22, 23]. A real robot is device incorporating
hardware and software, that can perform actions usually un-
dertaken by humans. Since the introduction of the first robot
by Papert [24] several educational animal-like or human-like
robots have been presented to suit different levels of education.
Educational robots are usually programmed to demonstrate the
content of a subject topic interactively, and to allow students
to ask questions that a robot answer.
The notion chatbot is a combination of two words: “chat”
demonstrating conversation and “bot” standing for robot [25].
Chatbots involve only a software implementation, they they
can be run through computers or smart mobile devices. Chat-
bots simulate conversation with human users via the use of
instant messaging services and students being facilitated as
chatbots can answer questions regarding the educational ma-
terial. Most studies demonstrated that using chatbots in classes
may offer pupil a more pleasant educational procedure through
close engagement [26], enhance communication and learning
abilities [27], and boost pupil intellectual development [18].
Initially, robots were constructed to perform repetitive tasks,
without any AI. However, the importance of having intelligent
machines led to the use of a series of sensors that provide
information about the environment along with the integration
of AI for processing and making decisions based on the
information received by the sensors [28, 29]. Typical sensors
used in robotics include microphones, Time-of-flight (ToF)
optic sensors, cameras, and motion detectors [30] that when
used in conjunction with AI algorithms can be used for sensing
an environment [31]. AI-based functionality incorporated in
robots include speech recognition, motion control, computer
vision, natural language processing, smart agent technology,
movement control, and control for grasping objects. On the
other hand, the operation of chatbots is a mix of artificial
intelligence and Natural Language Processing (NLP) [32].
2) Virtual/Augmented/Mixed Reality: Smart classrooms of-
ten incorporate virtual, augmented, and mixed reality as a
means of introducing immersive learning experiences[33]. Vir-
tual Reality (VR) concerns the 3D simulation of an imaginary
or real environment, that the user can visualize, explore and
interact with it [34]. Quite often VR is used as an empathy
inducing medium in educational applications [35]. According
to Sobota et al. [36], the two techniques that are widely
used to offer immersive experience regarding virtual reality
in smart classroom environment are CAVE (Cave automatic
virtual environment) and HMDs (Head-mounted displays).
Furthermore, there are different VR accessories which can
combine with HMDs and CAVEs, such as gloves, suits or
controllers which can offer more exciting experience.
Carmigiani and Furh, [37] define Augmented Reality (AR)
“as a real-time direct or indirect view of a physical real-world
environment that has been enhanced/augmented by adding
virtual computer-generated information to it”. There are dif-
ferent types of augmented display devices in a smart class
environment such as tablets, smartphones, smartboards, along
with dedicated AR headsets such as Microsoft HoloLens.
According to Torres et al. [38], AR in smart classrooms can
be used the following forms: Enlarged book, virtual models
of specific complicated structures, educational games, virtual
models which produce sounds, magic eyeglasses, magic mir-
rors, magic doors, navigation support and cooperative space.
According to Chamba-Eras and Aguilar [39], AR is recom-
mended to compensate various deficiencies that might occur
in a smart classroom environment such as difficulties in doing
complicated and dangerous experiments or unavailability of
appropriate facilities.
Mixed Reality (MR) refers to a blending of real-world and
virtual/digital world objects which are visualized together on
only one display in a coherent space [40]. MR results to
the creation of mixed environments and visualizations of co-
existing and interacting virtual and real objects in real-time.
The introduction of AI into virtual, augmented, and mixed
reality settings has propelled this technology to new heights.
Procedural Content Generation is an AI approach for cre-
ating novel personalities and accurate 3D model settings
with no previous information [41]. Furthermore, AI may be
utilized to generate avatars, digital humanoid characters or
complementing users that interact and take decisions imme-
diately according to the gamers’ choices, resulting in more
engaging experiences [42]. Computer vision techniques like
pose estimation, object detection, scene labeling and semantic
segmentation are used to control AR content, project an object
in the scene, trigger a spot or occlude objects from the scene
[43].
3) E-Learning Platforms: E-learning platforms are sys-
tems that use on-line content to support synchronous or
asynchronous learning in platforms such as Moodle and Black-
board [44]. Synchronous learning is teacher-led and occurs
in real time; to this end, students log on at a predetermined
time and communicate directly with the teacher and their
peers. In asynchronous learning, the process is student-led and
occurs at a time, which is most convenient for the student;
thus, students join the platform at a time and place of their
choice and interact with the learning material [45]. E-learning
in the smart classroom aims to develop students’ learning
ability, as it concentrates on linking the digital generation,
enhancing individualized opportunities of learning, sparking
learning innovation, promoting teachers’ digital pedagogy and
acquiring the best ICT investment by schools [46].
Quite often AI is introduced in E-learning platforms in
order to maximize the learning experience of students through
the use of adaptive educational systems.Adaptive educational
systems use the learner profile to diagnose individual charac-
teristics and abilities, supporting dynamic and adaptive teach-
ing course delivery. Apart from supporting adaptive learning
AI is also utilized in other aspects of the learning process.
For example, natural language processing algorithms [12]
are often used to identify plagiarism and avoid transcrib-
ing in assignments submitted by students [47]. Furthermore,
advanced data search capabilities allow the extraction and
indexing of massive amounts of data in colleges and major
academic institutions [48]. In some cases, data related to notes
taking and discussions between peers is analysed to indicate
any misunderstandings or even student interests, and it is
then delivered back to instructors as a summary for every
participant [49].
4) Flipped/Virtual/Remote Classroom: Flipped, virtual and
remote classrooms offer students a unique experience that
renders the learning process a fruitful and interesting proce-
dure for both the students and the teachers. The term ‘flipped
classroom’ was firstly mentioned by Lage et al. [50] as
“Inverting the classroom means that events that have tradition-
ally taken place inside the classroom, now take place outside
the classroom and vice versa”. Flipped classroom focuses
more on the learner and therefore it is characterized as a
valuable complement to an intelligent classroom [51]. Virtual
classroom is defined as a new educational environment that
allows students to attend courses online while also facilitating
interaction and collaboration by using the artificial intelligence
tools and abilities [52]. The smart virtual classroom should
offer all the possibilities offered by a traditional classroom
and can offer more possibilities such as application sharing,
educational games, augmented reality techniques, virtual lab-
oratories, interactive intelligent tutoring systems etc. Remote
classroom refers to a teaching method that is based on distant
learning and gives the ability to students who are not actually
present in class to continue their studies [53]. This method
is proven significant in cases of enforced social isolation, for
students who live in rural areas, and for students who face any
type of disability [54].
AI technologies can support advanced functionalities of
flipped/virtual/remote classroom. Lo, Hew and Chen [55] state
that AI has great potential in the flipped classroom approach,
because it enables the personalization and adaptation of the
learning process to the students needs. Shan and Liu [56]
suggest a model of Hybrid Teaching of Artificial Intelligence
and Flipped Classroom, which combines big data, cloud and
online applications to implement comprehensive and individu-
alized learning. Tangkittipon et al. [57] suggest an alternative
approach, which includes the implementation of a chatbot that
should be integrated to the flipped classroom. Furthermore,
AI technology can be incorporated in virtual classes and
provide assistance to educators as this type of environment
is more challenging, requiring immediate responses and the
control of a remote class. A wide range of AI technologies
are likely to influence student-teacher interaction in remote
classes. For instance, Goel and Polepeddi [58] designed Jill
Watson, an AI teaching assistant, to supplement the teacher’s
interaction with learners by reacting automatically to learners’
presentations, providing regular notifications and addressing
basic, commonly requested inquiries. Perin and Lauterbach
[59] created an AI grading method that helps teachers to
deliver marks more quickly. Luckin [60] demonstrated AI
solutions that assist both learners and educators by generating
continuous feedback regarding the way students learn and their
achievement according to their educational objectives. Ross et.
al. [61] created customizable tests to help students by tailoring
educational material to their specific requirements, resulting in
increased student enthusiasm and participation [62].
C. Performance Assessment
Student performance assessment aims on the one hand to
inform the teacher which students have learnt the content of
the lesson and how well they are expected to perform in
the future, and on the other, to grade students and provide
feedback about their performance during the learning process
[5].The easiest tool to assess students in a smart classroom
is the employment of multiple-choice questions, which allow
automated evaluation and feedback, with the aid of an online
web server that compares students’ answers with the config-
ured correct answer [63]. Apart from student assessment, the
continuous assessment of educators is also highly important
process in a smart class environment [64].
An important application of AI in student assessment is
plagiarism checking, with Turnitin as a frequently used tool
[65]. Moreover, Bhatia and Kaur [66] add an innovative
performance assessment/prediction tool based on quantum
game theoretic (QGT) decision making. This tool incorporates
IoT to gather information and data about students, which are
evaluated over a computing platform aiming to analyze perfor-
mance and determine the academic enhancement of students.
The technologies used for educational performance assessment
are equipped and updated with AI-based techniques in order to
provide accurate and objective results. Srivastava et. al. [67]
proposed an evaluation framework for assessing and improving
teaching methods through the use of IoT systems that collect
data during class hours and process them by utilizing Machine
Learning models and cloud computing. In addition, Jensen et
al. [68, 69] present two frameworks for automated feedback
on teacher discourse that employ machine learning techniques,
like Random Forest classifiers, as well as transfer learning
methods and a natural language processing algorithm.
III. AI IN SMART CLASSES : A SWOT A NALYSIS
Based on the findings of this survey, a SWOT analysis of
the use in AI in smart classes is presented:
STRENGTHS: The strengths of AI in smart classes include
the ability to implement clever environment management
systems that contribute to an improved and safer environment,
through the processing of data captured by sensors. Moreover,
students can benefit through adaptive modes of interaction
tailored for individual needs, allowing each student to get
unique feedback and advice. AI-based teacher-student inter-
action as well as engagement with the learning material can
boost learning, help students retain information more easily
and increase self-efficiency.
WEAKNESSES: The use of AI-based systems in smart-
classes has been criticized for inducing disconnectedness,
which is usually expressed as feelings of separation and
disengagement from learning, the curriculum, the peers, the
teachers and the learning devices. In addition, the installation
of technological tools is almost impossible for some schools
due to the high infrastructure and maintenance cost required.
OPPORTUNITIES: External factors, like the COVID-19
pandemic, can give a boost in the application of smart class
technologies like flipped, virtual and remote classes allowing
students who are not physically present in class or have any
form of disability to attend their lessons. Furthermore, the
widespread use of smart devices by teachers and students
provide an excellent opportunity to capitalize on the use
of AI-based learning technologies that can be deployed on
personal devices. The widespread introduction of AI in smart
classes will also provide to AI-professionals a ’playground’
for introducing novel challenging applications that require the
development of dedicated AI techniques.
THREATS: Machine learning models usually require a vast
amount of data for training, and this raises issues about the
way data is collected and processed. Security and privacy are
therefore issues that could pose a thread for future devel-
opment and deployment of AI-based technologies in smart
classes. In addition, the possibility of introducing bias during
the training process of clever systems, may cause errors that
can have negative impact on the teaching process. Furthermore
the vulnerability of clever systems to hacking attacks and the
overall issue of security is a matter that raises concerns. Last,
but not least technology acceptance by the stakeholders can
pose a serious threat for further development.
 IV. C ONCLUSIONS AND F UTURE W ORK
A range of AI-assisted emerging technologies used in smart
classrooms have been presented and discussed. Through the
discussion it was demonstrated that classroom management
and teaching aids, like smart environments and online modes
of teaching (virtual, online, remote classes) transformed the
educational landscape from a traditional teacher-led learning
to dynamic student-centred learning environment [6]. This
change is evident in the utilization and role of AI technologies,
incorporated in the wide range of smart-class technologies.
The material presented in this survey can be useful for
researchers in educational technology and educators, but most
importantly it is useful for researchers related to emerging
technologies and AI, as information about the existing systems
and prospects for future developments are outlined. Future
plans of our research include the production of a more
detailed survey, that will include comparison between different
technologies, along with the development of novel AI-based
smart class technologies.
ACKNOWLEDGMENT
This project has received funding from the European
Union’s Horizon 2020 Research and Innovation Programme
under Grant Agreement No 739578 and the Government of
the Republic of Cyprus through the Directorate General for
European Programmes, Coordination and Development.
R EFERENCES
[1] R. C. Rescigno, “Practical implementation of educational tech-
nology. the gte/gtel smart-classroom. the hueneme school dis-
trict experience,” 1988.
[2] M. Mircea, M. Stoica, and B. Ghilic-Micu, “Investigating the
impact of the internet of things in higher education environ-
ment,” IEEE Access, vol. 9, pp. 33 396–33 409, 2021.
[3] H. Ten Have and M. Patrǎo Neves, Dictionary of Global
Bioethics, 2021.
[4] M. N. Sadiku, S. M. Musa, and U. C. Chukwu, Artificial
Intelligence in Education, 2022.
[5] M. K. Saini and N. Goel, “How smart are smart classrooms?
a review of smart classroom technologies,” ACM Computing
Surveys (CSUR), pp. 1–28, 2019.
[6] K. C. Li and B. T.-M. Wong, “Review of smart learning:
Patterns and trends in research and practice,” Australasian
Journal of Educational Technology, pp. 189–204, 2021.
[7] J. M. Spector, “Conceptualizing the emerging field of smart
learning environments,” Smart learning environments, pp. 1–10,
2014.
[8] B. Tabuenca, S. Serrano-Iglesias, A. Carruana-Martin, C. Villa-
Torrano, Y. A. Dimitriadis, J. I. Asensio-Perez, C. Alario-Hoyos,
E. Gomez-Sanchez, M. L. Bote-Lorenzo, A. Martinez-Mones
et al., “Affordances and core functions of smart learning en-
vironments: A systematic literature review,” IEEE Transactions
on Learning Technologies, 2021.
[9] Y. Kawaguchi, T. Shoji, W. Lin, K. Kakusho, and M. Minoh,
“Face recognition-based lecture attendance system,” in The 3rd
AEARU workshop on network education, 2005, pp. 70–75.
[10] Y. Kong and Y. Fu, “Human action recognition and prediction:
A survey,” arXiv preprint:1806.11230, 2018.
[11] R. Wang, G. Zhang, F. Zhang, Z. Dong, and M. Qi, “Student
behavior recognition in remote video classrooms,” in Advances
in Intelligent Information Hiding and Multimedia Signal Pro-
cessing, 2021, pp. 496–504.
[12] K. Chowdhary, “Natural language processing,” Fundamentals
of artificial intelligence, pp. 603–649, 2020.
[13] D. Mery, I. Mackenney, and E. Villalobos, “Student attendance
system in crowded classrooms using a smartphone camera,” in
IEEE Winter Conference on Applications of Computer Vision,
2019, pp. 857–866.
[14] S. K. Gupta, T. Ashwin, and R. M. R. Guddeti, “Cvucams:
Computer vision based unobtrusive classroom attendance man-
agement system,” in IEEE 18th International Conference on
Advanced Learning Technologies, 2018, pp. 101–102.
[15] E. Dimitriadou. and A. Lanitis, “Using student action recog-
nition to enhance the efficiency of tele-education,” in 17th
International Joint Conference on Computer Vision, Imaging
and Computer Graphics Theory and Applications, 2022, pp.
543–549.
[16] M. Dryjanski, M. Buczkowski, Y. Ould-Cheikh-Mouhamedou,
and A. Kliks, “Adoption of smart cities with a practical smart
building implementation,” IEEE Internet of Things Magazine,
pp. 58–63, 2020.
[17] A. Yang, M. Han, Q. Zeng, and Y. Sun, “Adopting building
information modeling for the development of smart buildings:
a review of enabling applications and challenges,” Advances in
Civil Engineering, 2021.
[18] E. H.-K. Wu, C.-H. Lin, Y.-Y. Ou, C.-Z. Liu, W.-K. Wang, and
C.-Y. Chao, “Advantages and constraints of a hybrid model k-12
e-learning assistant chatbot,” IEEE Access, pp. 77 788–77 801,
2020.
[19] D. Norman, The design of future things, 2009.
[20] M. Shiomi, T. Kanda, I. Howley, K. Hayashi, and N. Hagita,
“Can a social robot stimulate science curiosity in classrooms?”
International Journal of Social Robotics, pp. 641–652, 2015.
[21] M. Weibel, M. K. F. Nielsen, M. K. Topperzer, N. M. Hammer,
S. W. Møller, K. Schmiegelow, and H. Bækgaard Larsen, “Back
to school with telepresence robot technology: A qualitative pilot
study about how telepresence robots help school-aged children
and adolescents with cancer to remain socially and academically
connected with their school classes during treatment,” Nursing
open, pp. 988–997, 2020.
[22] J. Pereira, “Leveraging chatbots to improve self-guided learning
through conversational quizzes,” in Proceedings of the fourth
international conference on technological ecosystems for en-
hancing multiculturality, 2016, pp. 911–918.
[23] I. Kollia and G. Siolas, “Using the ibm watson cognitive
system in educational contexts,” in IEEE Symposium Series on
Computational Intelligence, 2016, pp. 1–8.
[24] W. Johal, G. Castellano, F. Tanaka, and S. Okita, “Robots for
learning,” pp. 293–294, 2018.
[25] R. Chocarro, M. Cortiñas, and G. Marcos-Matás, “Teachers’
attitudes towards chatbots in education: a technology acceptance
model approach considering the effect of social language, bot
proactiveness, and users’ characteristics,” Educational Studies,
pp. 1–19, 2021.
[26] N.-Y. Kim, Y. Cha, and H.-S. Kim, “Future english learning:
Chatbots and artificial intelligence,” Multimedia-Assisted Lan-
guage Learning, pp. 32–53, 2019.
[27] J. Hill, W. R. Ford, and I. G. Farreras, “Real conversations
with artificial intelligence: A comparison between human–
human online conversations and human–chatbot conversations,”
Computers in human behavior, pp. 245–250, 2015.
[28] M. Brady, L. A. Gerhardt, and H. F. Davidson, Robotics and
artificial intelligence, 2012.
[29] D. M. West, The future of work: Robots, AI, and automation,
2018.
[30] M. Ben-Ari and F. Mondada, “Robots and their applications,”
in Elements of robotics, 2018, pp. 1–20.
[31] B. Poppinga and T. Laue, “Jet-net: Real-time object detection
for mobile robots,” in Robot World Cup, 2019, pp. 227–240.
[32] G. G. Chowdhury, “Natural language processing,” Annual Re-
view of Information Science Technology, 2003.
[33] E. Demitriadou, K.-E. Stavroulia, and A. Lanitis, “Compara-
tive evaluation of virtual and augmented reality for teaching
mathematics in primary education,” Education and Information
Technologies, pp. 381–401, 2020.
[34] F. Górski, P. Buń, R. Wichniarek, P. Zawadzki, and A. Hamrol,
“Effective design of educational virtual reality applications for
medicine using knowledge-engineering techniques,” EURASIA
Journal of Mathematics, Science and Technology Education, pp.
395–416, 2016.
[35] K. E. Stavroulia, E. Baka, A. Lanitis, and N. Magnenat-
Thalmann, “Designing a virtual environment for teacher train-
ing: Enhancing presence and empathy,” in Proceedings of
Computer Graphics International 2018, 2018, pp. 273–282.
[36] B. Sobota, Š. Korečko, L. Jacho, P. Pastornickỳ, M. Hudák,
and M. Sivỳ, “Virtual-reality technologies and smart environ-
ments in the process of disabled people education,” in 15th
International Conference on Emerging eLearning Technologies
and Applications, 2017, pp. 1–6.
[37] J. Carmigniani and B. Furht, “Augmented reality: an overview,”
Handbook of augmented reality, pp. 3–46, 2011.
[38] D. R. Torres et al., “Realidad aumentada, educación y museos,”
Revista ICONO 14. Revista cientı́fica de Comunicación y Tec-
nologı́as emergentes, pp. 212–226, 2011.
[39] L. Chamba-Eras and J. Aguilar, “Augmented reality in a smart
classroom—case study: Saci,” IEEE Revista Iberoamericana de
Tecnologias del Aprendizaje, pp. 165–172, 2017.
[40] V. Kasapakis, D. Gavalas, and E. Dzardanova, “Mixed reality.”
2019.
[41] J. Liu, S. Snodgrass, A. Khalifa, S. Risi, G. N. Yannakakis, and
J. Togelius, “Deep learning for procedural content generation,”
Neural Computing and Applications, pp. 19–37, 2021.
[42] M. El Beheiry, S. Doutreligne, C. Caporal, C. Ostertag, M. Da-
han, and J.-B. Masson, “Virtual reality: beyond visualization,”
Journal of molecular biology, pp. 1315–1321, 2019.
[43] C. K. Sahu, C. Young, and R. Rai, “Artificial intelligence (ai)
in augmented reality (ar)-assisted manufacturing applications:
a review,” International Journal of Production Research, pp.
4903–4959, 2021.
[44] H. Beetham, R. Sharpe et al., Rethinking pedagogy for a digital
age: Designing for 21st century learning, 2013.
[45] A. Potode and P. Manjare, “E-learning using artificial intelli-
gence,” International Journal of Computer Science and Infor-
mation Technology Research, pp. 78–82, 2015.
[46] S. Al-Sharhan, “14 smart classrooms in the context of
technology-enhanced learning (tel) environments,” Transform-
ing Education in the Gulf Region: Emerging Learning Technolo-
gies and Innovative Pedagogy for the 21st Century, pp. 1–10,
2016.
[47] M. Chong, L. Specia, and R. Mitkov, “Using natural language
processing for automatic detection of plagiarism,” in Proceed-
ings of the 4th International Plagiarism Conference (IPC-2010).
[48] W. Hersh, Information Retrieval, 2021, pp. 755–794.
[49] P. Diwanji, K. Hinkelmann, and H. F. Witschel, “Enhance class-
room preparation for flipped classroom using ai and analytics.”
in ICEIS (1), 2018, pp. 477–483.
[50] M. J. Lage, G. J. Platt, and M. Treglia, “Inverting the classroom:
A gateway to creating an inclusive learning environment,” The
journal of economic education, pp. 30–43, 2000.
[51] F. Ozdamli and G. Asiksoy, “Flipped classroom approach,”
World Journal on Educational Technology: Current Issues, pp.
98–105, 2016.
[52] M. Rufai, S. Alebiosu, and O. Adeakin, “A conceptual model
for virtual classroom management,” International Journal of
Computer Science, Engineering and Information Technology,
pp. 27–32, 2015.
[53] S. R. Hiltz and R. Goldman, Learning together online: Research
on asynchronous learning networks, 2004.
[54] C. Francisco, “Effectiveness of an online classroom for flexible
learning,” International Journal of Academic Multidisciplinary
Research (IJAMR), pp. 100–107, 2020.
[55] C. K. Lo, K. F. Hew, and G. Chen, “Toward a set of design
principles for mathematics flipped classrooms: A synthesis
of research in mathematics education,” Educational Research
Review, pp. 50–73, 2017.
[56] S. Shan and Y. Liu, “Blended teaching design of college
students’ mental health education course based on artificial
intelligence flipped class,” Mathematical Problems in Engineer-
ing, 2021.
[57] P. Tangkittipon, A. Sawatdirat, P. Lakkhanawannakun, and
C. Noyunsan, “Facilitating a flipped classroom using chatbot:
A conceptual model,” Engineering Access, pp. 103–107, 2020.
[58] A. K. Goel and L. Polepeddi, “Jill watson: A virtual teaching
assistant for online education,” in Learning Engineering for
Online Education, 2018, pp. 120–143.
[59] D. Perin and M. Lauterbach, “Assessing text-based writing of
low-skilled college students,” International Journal of Artificial
Intelligence in Education, pp. 56–78, 2018.
[60] R. Luckin, “Towards artificial intelligence-based assessment
systems,” Nature Human Behaviour, pp. 1–3, 2017.
[61] B. Ross, A.-M. Chase, D. Robbie, G. Oates, and Y. Absa-
lom, “Adaptive quizzes to increase motivation, engagement and
learning outcomes in a first year accounting unit,” International
Journal of Educational Technology in Higher Education, pp.
1–14, 2018.
[62] G. S. Santos and J. Jorge, “Interoperable intelligent tutoring
systems as open educational resources,” IEEE Transactions on
Learning Technologies, pp. 271–282, 2013.
[63] S. P. Balfour, “Assessing writing in moocs: Automated essay
scoring and calibrated peer review™.” Research & Practice in
Assessment, pp. 40–48, 2013.
[64] S. H. Jackson, “Student questions: A path to engagement and
social presence in the online classroom.” Journal of Educators
Online, 2019.
[65] R. Ahmed, “Overview of different plagiarism detection tools,”
International Journal of Futuristic Trends in Engineering and
Technology, pp. 1–3, 2015.
[66] M. Bhatia and A. Kaur, “Quantum computing inspired frame-
work of student performance assessment in smart classroom,”
Transactions on Emerging Telecommunications Technologies,
2021.
[67] M. Srivastava, P. Saurabh, and B. Verma, “Iot for capturing
information and providing assessment framework for higher
educational institutions—a framework for future learning,” in
Soft Computing for Problem Solving, 2020, pp. 249–261.
[68] E. Jensen, M. Dale, P. J. Donnelly, C. Stone, S. Kelly, A. Godley,
and S. K. D’Mello, “Toward automated feedback on teacher
discourse to enhance teacher learning,” in Proceedings of the
2020 CHI Conference on Human Factors in Computing Systems,
2020, pp. 1–13.
[69] E. Jensen, S. L. Pugh, and S. K. D’Mello, “A deep transfer
learning approach to modeling teacher discourse in the class-
room,” in LAK21: 11th International Learning Analytics and
Knowledge Conference, 2021, pp. 302–312.