Quiz-Ifying Education: Exploring the Power of Virtual Assistants

Todericiu Ioana Alexandra

, Pop Mihai Daniel

, S¸erban Camelia

and Dios¸an Laura

Faculty of Mathematics and Computer Science, Babes¸-Bolyai University

1, M. Kogalniceanu Street, 400084, Cluj-Napoca, Romania

Keywords:

Virtual Assistant, Cloud, Education, Amazon Alexa, Amazon Web Services.

Abstract:

Technology offers transformative potential for educational innovation. This paper introduces a novel approach

by harnessing virtual assistants, speciﬁcally through an Alexa quiz skill tailored for university students, to

enhance learning experiences. Supported by a preliminary evaluation, our solution demonstrates signiﬁcant

user satisfaction, indicating its effectiveness and areas for further reﬁnement. Our tailored skill dynamically

generates custom quizzes aligned with students’ preferences and topics, providing a personalized and learning

alternative to the one-size-ﬁts-all content. Utilizing Amazon Web Services (AWS) for its cloud infrastructure,

our methodology ensures scalability and a seamless user experience. We detail the theoretical foundations and

technical implementations of our approach, showcasing its capability to tackle current educational . This work

contributes to the ongoing discourse about modernizing education techniques by providing a comprehensive

framework for an innovative, interactive learning tool that capitalizes on the power of virtual assistants.

1 INTRODUCTION

Virtual Assistants (VAs) like Amazon’s Alexa present

an opportunity to change educational experience.

While VAs have become a trend, their potential in

education extends beyond mere popularity(Agarwal

et al., 2022). The motivation for this research

comes from the necessity to address key educational

challenges such as student engagement, personalized

learning, and the effective integration of technology

in educational settings. Our approach leverages the

capabilities of VAs to create a more interactive, en-

gaging, and tailored educational experience. Our fo-

cus is to illustrate skill development for educational

VA applications, aiming to contribute to the ﬁeld of

educational technology.

If we are looking at the use of VAs in education

for the past few years, it shows that they are here to

stay. A study by Kuhail et al. (2022) (Kuhail et al.,

2022) analyzed 36 papers and concluded that VAs and

chatbots hold the promise of revolutionizing educa-

tion by personalizing learning activities, supporting

educators, and developing deep insights into learn-

ers’ behavior. Studies also show that the most ef-

https://orcid.org/0000-0002-2469-134X

https://orcid.org/0009-0000-1391-9292

https://orcid.org/0000-0002-5741-2597

https://orcid.org/0000-0002-6339-1622

fective way of providing high-quality learning con-

tent is by leveraging a personalized learning environ-

ment (Shemshack and Spector, 2020). The content is

adapted to the needs of students, to cover the gaps that

they might have.

In the current technological landscape, Virtual As-

sistants (VAs) are increasingly being integrated with

generative AI technologies, which are known for their

ability to produce content autonomously. This in-

tegration is often seen in applications that require

creative content generation, such as in writing, art,

or music. However, our research takes a different

path. While acknowledging the potential of genera-

tive AI, we focus our VA implementation on enhanc-

ing interactive learning experiences rather than con-

tent creation. This decision is driven by our goal to

improve student engagement and learning outcomes

through tailored interactions and adaptive quizzes.

We believe this approach better suits the educational

objectives of our study, providing a more direct and

controlled impact on the learning process, as opposed

to the broader and often less predictable outcomes as-

sociated with generative AI.

To achieve a personalized learning experience, we

have developed a quiz skill that is customized for

Alexa and based on a university subject. The skill

is adaptable to students’ requirements, as it allows the

quiz-formation to be based on the topics speciﬁed by

Todericiu, I., Pop, M., ¸Serban, C. and Dio¸san, L.

Quiz-Ifying Education: Exploring the Power of Virtual Assistants.

DOI: 10.5220/0012722400003693

Paper published under CC license (CC BY-NC-ND 4.0)

In Proceedings of the 16th International Conference on Computer Supported Education (CSEDU 2024) - Volume 2, pages 589-596

ISBN: 978-989-758-697-2; ISSN: 2184-5026

589

the students, provided as verbal input. It generates

quizzes from a diverse set of questions, covering vari-

ous topics and levels of difﬁculty, to ensure a balanced

and challenging experience for students. The idea of

developing a quiz skill came from the desire to help

the students who are using it, in particular, taking a

quiz for a university course in an engaging manner

(Serban and Lungu, 2020).

In comparison to the built-in quiz capability on

Alexa, our ”Quiz for Uni” skill offers several advan-

tages. While Alexa does come with a built-in quiz

skill, it has certain limitations that may not meet the

requirements of a personalized learning experience.

The built-in skill typically offers generic quizzes and

lacks the adaptability to cater to individual student

needs. It may not allow students to specify their de-

sired quiz topics or offer a wide range of questions

covering various subjects and difﬁculty levels. More-

over, one of the limitations of our ”Quiz for Uni” skill

is its language constraint. Currently, the skill is devel-

oped in English, which may restrict its usage for non-

English speaking students. Additionally, Alexa itself

is available in a predeﬁned set of languages, which

limits the usability of the skill to students in those

speciﬁc language regions. The skill we explored ad-

vances personalized learning by offering an engaging

quiz-taking process with verbal input.(Kosslyn, 2017)

Adding Practice Testing, where students test them-

selves, enhances retention and comprehension. This

combination ensures both engagement and a deeper

understanding of the material.

This paper aims to address the following research

questions:

RQ1. In what ways does the proposed Alexa quiz

skill, tailored for university students, innovate upon

current methods of active learning?

RQ2. What are the technical aspects and theoretical

foundations of implementing an Alexa quiz skill for

personalized learning?

2 SETTING THE CONTEXT

2.1 Quiz-Based Learning

Quizzes have long been recognized as a potent tool

for enhancing learning outcomes. They are a form of

active learning that stimulate students’ engagement,

promoting deeper understanding and long-term reten-

tion of knowledge. They create an interactive envi-

ronment where students can assess their understand-

ing and knowledge gaps, encouraging subsequent tar-

geted learning (Freeman et al., 2014).

In the context of the ongoing digitization in ed-

ucation, the incorporation of technology, particularly

virtual assistants, into teaching methods has the po-

tential to signiﬁcantly enhance these active learning

strategies. However, any novel technological solu-

tion, such as a new Alexa skill, needs to be grounded

in scientiﬁcally validated learning theories.

The proposed Alexa quiz skill in this paper stands

on the foundation of active learning and retrieval prac-

tice theories. These theories emphasize that learners

can reinforce their memory and understanding by ac-

tively recalling information during quizzes.

This paper thus provides a comprehensive

overview of the technical framework for this novel

learning tool, demonstrating its potential to revolu-

tionize education by making learning more engaging,

stimulating, and efﬁcient.

2.2 Virtual Assistants

A software agent that can carry out tasks or provide

services on behalf of a human based on orders or

inquiries is known as an intelligent virtual assistant

(IVA) or intelligent personal assistant (IPA) (Lopa-

tovska, 2019). The term ”chatbots” is often used to re-

fer to VAs that can be interacted with via online chat.

This applies both to generic VAs as well as those that

are tailored for specialized tasks. Certain VAs pos-

sess the ability to comprehend verbal language and

respond using artiﬁcially created vocalizations. By

utilizing voice commands, human individuals can per-

form routine tasks such as managing emails, creating

to-do lists, and organizing schedules. Additionally,

they can make queries to personal assistants, operate

home automation devices, and playback media con-

tent. (Bohouta and K

epuska, 2018).

VAs use natural language processing (NLP) to

match user text or voice input to executable com-

mands. Many VAs continually learn using Artiﬁcial

Intelligence techniques including machine learning

and ambient intelligence (Polyakov et al., 2018).

In the continuous evolution of the world and new

technologies, different types of VAs are already de-

veloped (Silva et al., 2020), (Schmidt et al., 2021).

Some of the most remarkable ones are from: Ap-

ple (Siri), Google (Google Assistant), Microsoft (Cor-

tana), Amazon (Alexa).

Virtual Assistants have become a vital part of our

daily routines (Tavares et al., 2022). They are fre-

quently used to manage and execute tasks in a more

effective manner, thus enhancing our productivity and

organization. In the context of VAs, these ’tasks’ refer

to speciﬁc actions or commands that they can execute

in response to user input. Such tasks can include set-

CSEDU 2024 - 16th International Conference on Computer Supported Education

590

ting an alarm, playing music, checking the weather,

or even conducting interactive quizzes.

In this article, we will focus on a speciﬁc VA -

Amazon’s Alexa. Alexa has carved out a notable

reputation as the ﬁrst VA to have a dedicated device

(Amazon Echo) speciﬁcally designed to manage and

perform these types of tasks, including the interactive

quiz feature.

2.3 Virtual Assistants in Education

Education serves several important functions. One

of them is helping individuals acquire the knowl-

edge and skills they need to pursue their interests and

achieve their goals. This includes both academic and

practical skills. With the help of a VA, all of that

could lead to an environment where learning is more

efﬁcient than ever (Davie and Hilber, 2018) (C

ondor-

Herrera et al., 2021). VAs create an interactive envi-

ronment where students can assess their understand-

ing and knowledge gaps, encouraging subsequent tar-

geted learning (Freeman et al., 2014).

Despite the progress in educational technology,

several challenges remain that prevent the optimiza-

tion of student learning. One fundamental issue is

the lack of personalization in traditional education

systems, which fails to cater to the diverse learn-

ing styles, paces, and abilities of students (Kulik and

Fletcher, 2016) (Guskey, 2007). Personalization in

education refers to the tailoring of teaching meth-

ods, instructional content, and learning experiences to

meet the individual needs, skills, and interests of each

student. This approach recognizes that students have

unique learning styles, paces, and abilities, and aims

to provide a more relevant and effective educational

experience by accommodating these differences. Per-

sonalized learning often involves using technology to

assess and address individual learner needs, thereby

enhancing student engagement and improving learn-

ing outcomes. (Makhambetova et al., 2021)

Feedback is another key aspect where current ed-

ucational systems often fall short. Regular and timely

feedback is crucial for learning, but it’s challenging

for teachers to provide immediate, personalized feed-

back consistently, especially in larger classes (Hattie

and Timperley, 2007). The heavy reliance on high-

stakes testing for assessment is another area of con-

cern. These tests often lead to increased stress among

students and may not accurately reﬂect a student’s

comprehensive understanding and mastery of a sub-

ject (Stobart, 2008). Lastly, maintaining regular and

active engagement with each student is often difﬁcult

due to the constraints on teachers’ time and resources

(Fredricks et al., 2004).

VAs like Alexa can play a crucial role in address-

ing these challenges. They can provide instant feed-

back, helping reinforce learning concepts and cor-

rect misconceptions promptly. Moreover, Alexa can

supplement traditional high-stakes testing with low-

pressure quizzes for continuous assessment and re-

duce student stress.

3 PROPOSED APPROACH

The proposed approach, ”Quiz for Uni”, is a skill

developed for Alexa, designed to augment personal-

ized learning through interactive quizzes. The pri-

mary goal of the skill is to provide students with a

stimulating learning tool that adapts to their individ-

ual needs and preferences. We will outline the key

stages involved in the development process, includ-

ing the selection of technologies, the modeling of the

conversational ﬂow, and the implementation details.

We selected Alexa as our interface due to its wide

user base and the Alexa Developer Console, which

streamlines skill development. This console offers

comprehensive tools for creating, testing, and deploy-

ing interactive voice applications, making it ideal for

our quiz system. Additionally, the integration be-

tween Alexa and AWS is seamless as both are Ama-

zon products. This synergy allows for efﬁcient and

coherent development, with AWS providing robust

backend services like Lambda and DynamoDB, en-

suring scalability, reliability, and ease of management

for ’Quiz for Uni’.

3.1 Alexa-Based Interactive Quizzes in

Software Engineering Education

This solution is for now developed for second-year

students in Software Engineering (SE), with a fo-

cus on enhancing their understanding of the Java

programming language and object-oriented program-

ming (OOP) concepts. At this stage of their educa-

tion, students are transitioning from basic program-

ming skills to more complex concepts and practices

in SE. The Alexa-based interactive quiz system is tai-

lored to meet the educational needs of this learning

phase.

The implementation of this solution in SE educa-

tion involves:

1. Java Programming: The quizzes are designed to

test and reinforce students’ knowledge in Java, cover-

ing fundamental aspects like syntax, data types, con-

trol structures, and error handling, and extend to more

advanced topics such as exception handling and ﬁle

I/O operations.

Quiz-Ifying Education: Exploring the Power of Virtual Assistants

591

2. Object-Oriented Programming Concepts:

Quizzes will challenge students on key OOP prin-

ciples such as encapsulation, inheritance, polymor-

phism, and abstraction. Multiple-answer questions

will be used to deepen their understanding of how

these concepts are applied in Java.

3. Continuous Learning and Assessment: This

system serves as a continuous learning and assess-

ment tool, that in the future could enable educators

to track student progress in understanding Java and

OOP concepts, and to provide targeted feedback for

improvement.

By integrating our Alexa-based interactive quiz

system into the routine for second-year SE students,

we aim to provide a more engaging, personalized, and

effective learning experience in Java and OOP. This

approach can aid in the comprehension of theoretical

concepts but also could prepare students for the prac-

tical challenges.

3.2 Technical Overview

The technical architecture of the prototype involves

several components that work together to provide a

quiz skill for Alexa devices (see ﬁgure 1). To develop

Alexa skills, Amazon provides developers with vari-

ous tools and services, including the Alexa Developer

Console and AWS services (Amazon Alexa, 2023).

The technical architecture of the quiz skill presented

in this work utilizes various AWS services, such as

AWS Lambda, Amazon S3, Amazon DynamoDB,

and Amazon CloudWatch. This architecture allows

for the creation of a scalable and reliable quiz skill for

Alexa devices, while also providing monitoring and

logging capabilities to ensure the skill’s performance

(Amazon Web Services, 2023).

Alexa Devices. Alexa devices are the hardware de-

vices that allow users to interact with the Alexa Voice

Service. These devices include physical components,

such as: Amazon Echo, Echo Dot, Echo Show, and

many others. The devices are equipped with micro-

phones and speakers, which enable users to talk to

Alexa and receive responses. Some of them also have

an integrated display, which can be helpful to main-

tain the user’s attention to the device.

Alexa Developer Console. The Alexa Developer

Console is a web-based interface provided by Ama-

zon that developers can use to create, test, and publish

Alexa skills (Pilling and Coulton, 2020). The con-

sole includes tools for deﬁning the skill’s interaction

model, conﬁguring the skill’s endpoints, and testing

the skill’s functionality.

Quiz Skill. A basic quiz skill exists within the Alexa

Developer Console, although it’s static and not cus-

tomizable. Our custom quiz skill, however, offers its

users the ability to choose from various topics, and

different difﬁculty levels, and provides feedback after

the questions are answered. This quiz skill directly in-

terfaces with and uses various other tools and services

mentioned above.

AWS Services. The proposed quiz skill is devel-

oped using various AWS services, including AWS

Lambda, Amazon S3, Amazon DynamoDB, and

Amazon CloudWatch. These services provide the

necessary infrastructure and resources for the skill to

function correctly.

Lambda Function. The Lambda function is the pri-

mary component of the quiz skill. It is a serverless

function that is executed in response to requests from

Alexa devices. The function generates quiz questions,

retrieves content from S3, and manipulates the ques-

tion pool database stored in DynamoDB. The Lambda

function also logs its activities in CloudWatch, which

provides monitoring and logging capabilities.

Amazon S3. Amazon S3 is a cloud-based storage

service that provides developers with secure, durable,

and scalable object storage. The quiz skill uses S3 to

store and retrieve media ﬁles such as images.

Amazon DynamoDB. Amazon DynamoDB is a fully

managed NoSQL database service provided by AWS.

The quiz skill uses DynamoDB to store the question

pool database, which contains the questions and an-

swers used in the quiz, as well as characteristics for

each question such as difﬁculty level, and topics.

Amazon CloudWatch. Amazon CloudWatch is a

monitoring and logging service provided by AWS.

The quiz skill logs its activities in CloudWatch, which

allows developers to monitor and troubleshoot the

skill’s performance and behavior. The logs can also

serve as historical data to see how the skill serves the

users.

As this initiative is currently in the prototype

phase, we are actively exploring data privacy and se-

curity measures to ensure the protection of user infor-

mation as we further develop the solution.

Overall, the technical architecture of the quiz skill

leverages several AWS services to provide a scalable

and ﬂexible platform for developing Alexa skills. The

architecture allows developers to easily create and de-

ploy quiz skills for Alexa devices, while also provid-

ing monitoring and logging capabilities to ensure the

skill’s reliability and performance (Todericiu et al.,

2021).

3.3 Conversational Flow

The conversational ﬂow of the university quiz skill is

broken down into four main components: invocation,

CSEDU 2024 - 16th International Conference on Computer Supported Education

592

Figure 1: Technical architecture of the proposed quiz skill.

intent, slot type, and prompt. We will deﬁne these

concepts and describe their implementation and ex-

ploitation in the university quiz skill.

An invocation is the trigger phrase that the

user says to initiate the university skill. The in-

vocation phrase for our skill is ”Alexa, start the

university quiz.”. An intent represents a user’s

goal when interacting with the quiz skill. Intents

are primarily focused on answering user’s requests.

We divide our intents into two categories: built-in

intents, which are provided by Amazon Alexa,

and custom intents, which we created to facili-

tate the quiz process. Built-in Intents: Amazon

Alexa provides several built-in intents to handle

common user requests. These intents include: AMA-

ZON.CancelIntent, AMAZON.HelpIntent, AMA-

ZON.StopIntent, AMAZON.NavigateHomeIntent,

AMAZON.FallbackIntent. Custom Intents: We have

deﬁned three custom intents to facilitate the quiz

process: Setup Intent, Response Intent, and Question

Prompt.

Setup Intent. It is activated after the invocation of the

skill. The user is asked to select from a list of avail-

able topics for the quiz. The user’s selection initiates

the quiz.

Response Intent. The Response Intent follows each

question and is activated when the user chooses one

or more options from the multiple-choice responses.

Question Prompt. The Question Prompt presents the

user with the questions for the quiz. The questions

are displayed one at a time, along with their possible

responses.

Slot Type. A slot type extracts speciﬁc pieces of in-

formation from the user’s input. Each of our custom

intents uses a speciﬁc slot type to process the user’s

input.

Prompt. A prompt is the university skill’s response

to the user’s input. The prompt depends on the user’s

intent and any associated slot types.

Conversational Flow Instance. To illustrate the ﬂow

of conversation, we present a practical example, fol-

lowing the ﬂow described in the following ﬁgure:

User: ”Alexa, start the university quiz.”

Invocation: The user’s input triggers the Quiz Skill, im-

plemented as a Lambda function in AWS.

Prompt: The Quiz Skill returns a prompt, ”Welcome

to the university quiz! What topic would you like to learn

about?”

User: ”I want a quiz about inheritance and access mod-

iﬁers in Java.”

Intent and Slot Type: The university skill recognizes

the user’s intent to start a quiz and extracts the slot types

”inheritance” and ”access modiﬁers in Java”.

Prompt: The university skill responds with a prompt

that provides a quiz on the selected topics.

3.4 Technical Implementation Details

The brain of this skill is the lambda function, a server-

less computing service from Amazon Web Services,

which processes the requests from the Alexa Devel-

oper Console. Moreover, this is considered to be the

”backend” part of the skill, where all intents have their

handlers. All the communication with other Amazon

Services is performed inside the Lambda Function,

and it makes the process a lot easier to go through

developing the skill.

Lambda Function has 3 important roles:

• Generate a quiz based on the input received from

the user

• Send back a response with one question at a time/

quiz score for the ﬁnal interaction of the quiz skill

Quiz-Ifying Education: Exploring the Power of Virtual Assistants

593

• Handle the response of the user (the correct an-

swer to each of the quiz questions)

In order to generate a quiz based on the user input,

our function utilizes a question pool with predeﬁned

more than 300 questions and answers, stored in the

DynamoDB database. Each question is deﬁned by:

topics (covered by the question) and difﬁculty level

(easy, medium, hard). The quiz consists of 20 ques-

tions, which are equally divided among topics and dif-

ﬁculty levels. Some questions contain code snippets,

which aren’t meant to be read out loud by the voice

assistant. In order to have the questions, together

with their corresponding code, we used an external

service that transforms plain text to images, that will

be displayed next to the question on the Alexa device

screen, as can be observed in the following ﬁgure.

After successfully generating the quiz, each ques-

tion is sent to the user, one at a time. The quiz skill

moves to another question only after it receives an an-

swer for the current question. Once it does, it checks

if the answer that it receives is a valid one (one or

multiple letters from the ones available as answers).

If not, it returns a prompt that lets the user know

that the answer does not comply with the answer ex-

pected, and awaits for another reply. The user’s score

is tracked after each question, and once they reach the

end of the quiz, it is provided as an output along with

relevant information, such as the questions that they

answered incorrectly.

To adhere to the separation of concerns principle,

each of these tasks is handled separately by differ-

ent functions grouped in different modules. The con-

nection between the Quiz skill and the lambda func-

tion is done via lambda’s Amazon Resource Name

(ARN). As both Alexa Developer Console and the

Lambda Function are Amazon products, the integra-

tion is seamless and quick. There is no noticeable

latency throughout the course of the interaction be-

tween the skill and the user.

4 PRELIMINARY EVALUATION

In this study, we conducted a preliminary evaluation

of our prototype with a diverse group of 6 partic-

ipants, comprising 3 undergraduate students and 3

graduate-level individuals who possessed substantial

experience in the relevant ﬁeld. The evaluation pro-

cess involved the administration of a comprehensive

questionnaire containing both closed and open-ended

questions, totaling 13 in number. Our analysis of the

results revealed signiﬁcant insights into the user ex-

perience and usability of the prototype. Notably, we

observed that both undergraduate and graduate par-

ticipants expressed a high degree of satisfaction with

the system’s interface and functionality. Furthermore,

the open-ended responses provided valuable qualita-

tive data, highlighting speciﬁc areas of improvement

and potential enhancements for future iterations of the

prototype. These ﬁndings constitute a critical founda-

tion for reﬁning our system and advancing its effec-

tiveness.

5 RELATED WORK

In this part of our paper, we look at other studies that

focus on using Virtual Assistants (VAs) and advanced

interactive systems in teaching software engineering.

We chose research that talks about how interactive

technology is used in education, especially studies

that use VAs like Alexa. These studies are particu-

larly relevant to teaching software engineering. In the

research we found, there’s a strong interest in using

smart technology in education. This is a key trend

that’s changing how we teach and learn.

oksel and Bozkurt (G

oksel and Bozkurt, 2019),

who look at the present in order to gather relevant data

to forecast the future of AI in education, believe that

the future of education will go hand in hand with AI-

applied solutions. One such applicability they men-

tion is NLP tools, such as Alexa, which have the po-

tential to serve one of the themes listed in their work

as a ”personalization and learning system”. Our con-

tribution demonstrates a practical example, showcas-

ing an Alexa quiz skill that enhances personalized

learning, embodying the concept they introduced.

Another study that enhances the importance of in-

telligent solutions in education is the work of Dasic

et al. (Da

c et al., 2016) Their work offers a com-

prehensive review of 15 intelligent tutoring systems

in education, that aim to simplify the learning journey

for students. Although their work provides a broad

overview, it doesn’t explore in-depth how such tech-

nologies can adapt to different learning styles or con-

tents. By designing a versatile Alexa quiz skill that

can handle various topics and difﬁculty levels, our

approach addresses these areas, providing a more nu-

anced and adaptable tool for educational purposes.

Alexa and other similar voice VAs turned out

to be a powerful tool when it comes to educa-

tion. Terzopoulos and Satratzemi (Terzopoulos and

Satratzemi, 2020) present different real-case scenar-

ios where education embraced smart speakers and

VAs, from Alexa skills created for teachers that help

them generate practice quizzes using voice com-

mands, to custom actions for Google Assistant that

help students learn Java. While this use case is beneﬁ-

CSEDU 2024 - 16th International Conference on Computer Supported Education

594

cial, it predominantly serves educators. Our quiz skill

expands on this, serving the students directly, engag-

ing them in an interactive learning experience that is

challenging and educational.

There are numerous ways in which custom skills

for Alexa serve educational purposes. Another study

(Ochoa-Orihuel et al., 2020) discusses the implemen-

tation of an Alexa skill that connects to Moodle, a

popular open-source learning platform, for getting in-

formation related to courses and events from a Moo-

dle instance and present it to students through voice

interaction. A similar approach (Serban and Toderi-

ciu, 2020) follows the details of a skill that offers or-

ganizational information to students (eg.: class sched-

ules, exam dates) and integrates with Microsoft prod-

ucts such as Outlook and Teams, for facilitating con-

versation on channels and emails with professors and

colleagues, by using voice commands.

Overall, the existing literature highlights the im-

portance of leveraging smart technologies in educa-

tion, with emphasis on the potential of VAs and NLP

tools like Alexa. The studies discussed in this sec-

tion demonstrate the variety of ways in which Alexa

and other VAs can serve educational purposes, from

assisting the learning process to providing organi-

zational information and facilitating communication

with professors and colleagues. With the develop-

ment of a custom skill for interactive quizzes, this pa-

per contributes to the growing body of work exploring

the potential of these technologies in education and

provides a valuable addition to the literature.

6 DISCUSSION

The results of the research aim to shed light on the

potential roles of virtual assistants in education. How-

ever, it’s important to note that the conclusions drawn

here are primarily theoretical and based on a concep-

tual understanding of the technology. To strengthen

these answers, future work should include empirical

data and a more systematic research methodology.

The current discussion addresses the research ques-

tions as follows:

RQ1. In what ways does the proposed Alexa quiz

skill, tailored for university students, innovate upon

current methods of active learning?

A1. The proposed Alexa quiz skill enhances active

learning in several unique ways. It allows for person-

alized quiz creation based on students’ chosen topics

and preferences, thus catering to individual learning

needs and styles. This tailoring of content increases

student engagement, a key aspect of effective active

learning. Moreover, the Alexa quiz skill incorporates

a variety of question difﬁ culty levels, promoting cog-

nitive growth by challenging students’ understanding

at different levels. It also offers immediate feedback,

which aids in the reinforcement of learned concepts

and quick identiﬁcation of knowledge gaps, leading

to a more effective study plan. The Alexa quiz skill

inherently incorporates Practice Testing principles.

By emphasizing regular self-assessments through the

skill’s immediate feedback and varied questions, it

boosts retention and supports active learning.

RQ2. What are the technical aspects and theoretical

foundations of implementing an Alexa quiz skill for

personalized learning?

A2. The technical framework for implementing the

Alexa quiz skill involves using Amazon Web Ser-

vices (AWS) as the cloud provider. This ensures a

scalable, secure, and reliable infrastructure, which is

fundamental for creating a seamless user experience.

The use of AWS allows the system to handle a large

number of requests, ensuring its availability to a vast

number of users at any given time. On the theoret-

ical side, the design of the Alexa quiz skill draws

from scientiﬁcally validated learning theories like ac-

tive learning. These theories emphasize the impor-

tance of student engagement, recall practice, and per-

sonalized learning experiences in enhancing learning

outcomes. Overall, the Alexa quiz skill promises to

offer a potent tool for effective education.

7 CONCLUSION

Through the course of this paper, virtual assistants

have found their way into the educational sphere. We

presented how VAs can be customized in order to be

ﬁtted for students on account of personalized skills,

more speciﬁcally, a quiz skill that can make testing

knowledge enjoyable, engaging, and efﬁcient. Future

recommendations include expanding language sup-

port, conducting larger-scale user studies, and explor-

ing additional features. While the current research

has its limitations, such as language constraints and

the need for further evaluation, our skill stands as a

valuable contribution to personalized learning envi-

ronments powered by VAs.

In the future, we hope to roll out the prototype to

a larger group of students and see what are the out-

comes of the tool applied to our university. We would

also like to enhance the question pool with a larger set

of data and extend the skill to various courses.

In conclusion, virtual assistants have the potential

to revolutionize the way students learn and engage

with educational content. By tailoring these assistants

to the individual needs of students, we can provide a

Quiz-Ifying Education: Exploring the Power of Virtual Assistants

595

more personalized and effective learning experience.

With the development of our quiz skill, we have taken

a step towards making this a reality. As we continue

to reﬁne and expand our tool, we are excited to see

the positive impact it can have on the education land-

scape. After all, the future of learning is not just about

technology, but about how we can use it to better our-

selves and the world around us.

8 DATA AVAILABILITY

The data supporting the preliminary questionnaire

used to assess the skill of this study are available in

the following repository, ensuring transparency.

REFERENCES

Agarwal, S., Agarwal, B., and Gupta, R. (2022). Chatbots

and virtual assistants: a bibliometric analysis. Library

Hi Tech, 40.

Amazon Alexa (2023). Alexa Developer Console.

Amazon Web Services (2023). AWS Services.

Bohouta, G. and K

epuska, V. (2018). Next-generation of

virtual personal assistants (microsoft cortana, apple

siri, amazon alexa and google home).

ondor-Herrera, O., Jadan-Guerrero, J., and Ramos, C.

(2021). Virtual Assistants and Its Implementation in

the Teaching-Learning Process, pages 203–208.

Davie, N. and Hilber, T. (2018). Opportunities and

challenges of using amazon echo in education.

c, P., Da

c, J., Crvenkovi

c, B., and Seriﬁ, V. (2016).

A review of intelligent tutoring systems in e-learning.

Annals of the Oradea University – Fascicle of Man-

agement and Technological Engineering, 15:85–90.

Fredricks, J. A., Blumenfeld, P. C., and Paris, A. H. (2004).

School engagement: Potential of the concept, state of

the evidence. Review of Educational Research, 74:60–

80.

Freeman, S., Eddy, S. L., McDonough, M., Smith, M. K.,

Okoroafor, N., Jordt, H., and Wenderoth, M. P. (2014).

Active learning increases student performance in sci-

ence, engineering, and mathematics. Proceedings

of the National Academy of Sciences, 111(23):8410–

8415.

Guskey, T. R. (2007). Closing achievement gaps: Revisiting

benjamin s. bloom’s “learning for mastery”. Journal

of Advanced Academics, 65:73.

oksel, N. and Bozkurt, A. (2019). Artiﬁcial Intelligence in

Education: Current Insights and Future Perspectives,

pages 224–236.

Hattie, J. and Timperley, H. (2007). The power of feedback.

Review of Educational Research, 77:81–112.

Kosslyn, S. (2017). The Science of Learning: Mechanisms

and Principles.

Kuhail, M. A., Alturki, N., Alramlawi, S., and Alhejori, K.

(2022). Interacting with educational chatbots: A sys-

tematic review. Education and Information Technolo-

gies, 28:1–46.

Kulik, J. A. and Fletcher, J. D. (2016). Effectiveness of

intelligent tutoring systems: a meta-analytic review.

Review of Educational Research, 38.

Lopatovska, I. (2019). Overview of the intelligent personal

assistants. Ukrainian Journal on Library and Infor-

mation Science, pages 72–79.

Makhambetova, A., Zhiyenbayeva, N., and Ergesheva, E.

(2021). Personalized learning strategy as a tool to im-

prove academic performance and motivation of stu-

dents. International Journal of Web-Based Learning

and Teaching Technologies, 16:1–17.

Ochoa-Orihuel, J., Marticorena-S

anchez, R., and S

aiz-

Manzanares, M. C. (2020). Moodle lms integration

with amazon alexa: A practical experience. Applied

Sciences, 10(19).

Pilling, F. and Coulton, P. (2020). What’s it like to be alexa?

an exploration of artiﬁcial intelligence as a material

for design.

Polyakov, E. V., Mazhanov, M. S., Rolich, A. Y., Voskov,

L. S., Kachalova, M. V., and Polyakov, S. V. (2018).

Investigation and development of the intelligent voice

assistant for the internet of things using machine

learning. In 2018 Moscow Workshop on Electronic

and Networking Technologies (MWENT), pages 1–5.

Schmidt, R., Alt, R., and Zimmermann, A. (2021). A con-

ceptual model for assistant platforms.

Serban, C. and Lungu, I. (2020). Qlearn: Towards a frame-

work for smart learning environments. Procedia Com-

puter Science, 176:2812–2821.

Serban, C. and Todericiu, I.-A. (2020). Alexa, what classes

do i have today? the use of artiﬁcial intelligence via

smart speakers in education. Procedia Computer Sci-

ence, 176:2849–2857.

Shemshack, A. and Spector, J. (2020). A systematic lit-

erature review of personalized learning terms. Smart

Learning Environments, 7.

Silva, A., Gomes, M., Andr

e da Costa, C., Righi, R., Bar-

bosa, J., Pessin, G., Doncker, G., and Federizzi, G.

(2020). Intelligent personal assistants: A systematic

literature review. Expert Systems with Applications,

147:113193.

Stobart, G. (2008). Testing Times: The uses and abuses of

assessment. Routledge.

Tavares, R., Sousa, H., and Ribeiro, J. (2022). Smart

Speakers and Functional Diversity: A Scoping Re-

view, pages 48–64.

Terzopoulos, G. and Satratzemi, M. (2020). Voice assistants

and smart speakers in everyday life and in education.

Informatics in Education, 19:473–490.

Todericiu, I.-A., Serban, C., and Laura, D. (2021). Towards

accessibility in education through smart speakers. an

ontology based approach. Procedia Computer Sci-

ence, 192:883–892.

CSEDU 2024 - 16th International Conference on Computer Supported Education

596