ASSIGNMENT FINAL REPORT

Qualification Pearson BTEC Level 5 Higher National Diploma in Computing

Unit number and title Unit 19: Computing Research Project (Pearson Set)

Submission date 12/12/2024 Date Received 1st Submission 12/12/2024

Re-submission Date Date Received 2nd Submission

Student Name Tran Kim Thanh Student ID BS00461

Class SE06101 Assessor name Nguyen Van Quang

Plagiarism
Plagiarism is a particular form of cheating. Plagiarism must be avoided at all costs and students who break the rules, however innocently,
may be penalised. It is your responsibility to ensure that you understand correct referencing practices. As a university level student, you
are expected to use appropriate references throughout and keep carefully detailed notes of all your sources of materials for material you
have used in your work, including any material downloaded from the Internet. Please consult the relevant unit lecturer or your course tutor
if you need any further advice.

Student Declaration
I certify that the assignment submission is entirely my own work and I fully understand the consequences of plagiarism. I declare that the
work submitted for assessment has been carried out without assistance other than that which is acceptable according to the rules of the
specification. I certify I have clearly referenced any sources and any artificial intelligence (AI) tools used in the work. I understand that
making a false declaration is a form of malpractice.
 Student’s signature Thanh

Grading grid

P1 P2 P3 P4 P5 P6 P7 M1 M2 M3 M4 D1 D2 D3
 ASSIGNMENT GROUP WORK
Qualification Pearson BTEC Level 5 Higher National Diploma in Computing

Unit number and title Unit 19: Computing Research Project (Pearson Set)

Submission date 12/12/2024 Date Received 1st submission 12/12/2024

Re-submission Date Date Received 2nd

submission

Group number: Student names & codes Final scores Signatures

Truong Pham Anh Tuan BS00563 Tuan

Tran Kim Thanh BS00461 Thanh

Class SE06101 Assessor name Nguyen Van Quang

Plagiarism
Plagiarism is a particular form of cheating. Plagiarism must be avoided at all costs and students who break the rules, however innocently, may be
penalised.
It is your responsibility to ensure that you understand correct referencing practices. As a university level student, you are expected to use appropriate

references throughout and keep carefully detailed notes of all your sources of materials for material you have used in your work, including any material
downloaded from the Internet. Please consult the relevant unit lecturer or your course tutor if you need any further advice.

Student Declaration
I certify that the assignment submission is entirely my own work and I fully understand the consequences of plagiarism. I declare that the work submitted
for assessment has been carried out without assistance other than that which is acceptable according to the rules of the specification. I certify I have clearly
referenced any sources and any artificial intelligence (AI) tools used in the work. I understand that making a false declaration is a form of malpractice.
OBSERVATION RECORD
Student Tran Kim Thanh

Description of activity undertaken

Database design (product data).

Chatbot design and integration.

Set up backend.

Assessment & grading criteria

Project contribution percentage: 50%

How the activity meets the requirements of the criteria

Student Thanh Date: 12/12/2024

signature:

Assessor Date:
signature:

Assessor Nguyen Van Quang

name:
 Summative Feedback:  Resubmission Feedback:

Grade: Assessor Signature: Date:

Internal Verifier’s Comments:

Signature & Date:

Table of Contents
Introduction ............................................................................................................................................................. 9
A. Assignment Part 1 ................................................................................................................................................ 9
P2. Examine appropriate research methods and approaches to primary and secondary research ............................. 9
P3. Conduct primary and secondary research using appropriate methods for a computing research project that
consider costs, access and ethical issues................................................................................................................. 15
P4. Apply appropriate analytical tools, analyse research findings and data ............................................................. 31
P5 Communicate research outcomes in an appropriate manner for the intended audience .................................... 46
P6 Reflect on the effectiveness of research methods applied for meeting objectives of the computing research
project ................................................................................................................................................................... 51
P7. Consider alternative research methodologies and lessons learnt in view of the outcomes ................................ 53
Conclusion ............................................................................................................................................................. 68
References ................................................................................................................... Error! Bookmark not defined.
Introduction
Artificial Intelligence (AI) has transformed the landscape of personalized systems by tailoring experiences,
services, and products to individual users. By analysing vast amounts of data and utilizing advanced
algorithms, AI enables systems to learn from user interactions and adapt over time, enhancing user
satisfaction.

AI-driven personalized systems can be found in applications like recommendation engines for streaming
services, targeted marketing in e-commerce, and adaptive learning platforms. These systems analyse user
behaviour and preferences to deliver tailored content, improving customer engagement and retention.

The integration of AI also includes techniques like predictive analytics and natural language processing,
which allow for more intuitive and seamless interactions. Ultimately, AI in personalized systems offers a
path toward creating meaningful user experiences that are optimized for individual needs, paving the way
for future advancements in user engagement.

A. Assignment Part 1

P2. Examine appropriate research methods and approaches to primary and secondary research.
1. Research

a) Primary research

Definition: Primary research is a technique of gathering original data straight from sources in order to
answer particular research questions or goals is known as primary research. Instead of depending on
preexisting data or secondary sources, this kind of study collects fresh information through a variety of
techniques, including surveys, interviews, experiments, and observations. Primary research is useful because
it offers personal perspectives that are customized for the particular study setting, allowing researchers to
get precise and pertinent data that is directly related to their area of interest. (Smith, 2020)
Advantages and Disadvantages of Primary research.
Advantages of Primary Research Disadvantages of Primary Research

Specificity: Primary research is tailored to Cost: Conducting primary research can be

the specific needs of the researcher, expensive, requiring resources for tools,
allowing for focused data collection that materials, participant recruitment, and data
addresses particular questions or analysis.
hypotheses.
Time-Consuming: The process of designing,
Original Data: Since the data is collected conducting, and analysing primary research
firsthand, it is original and unique, often can take considerable time, delaying the
providing more accurate and relevant research outcomes.
insights than secondary data.
Limited Sample Size: Depending on
Control Over Data Collection: resources and access, researchers may have a
Researchers can control the smaller sample size, which can limit the
generalizability of the findings.
methodology, sample size, and conditions
under which data is collected, ensuring that Skill Requirement: Primary research often
the research design aligns with their requires specialized skills in research design,
objectives. data collection methods, and statistical
analysis, which may necessitate training or
hiring experts.

b) Secondary research

Definition: Secondary research is the process of gathering and examining data that has previously been
obtained by research others. Reviewing and combining data from a variety of sources, including books,
scholarly journals, articles, reports, and databases, is part of this kind of study. Secondary research employs
data that has already been published to make inferences, spot trends, or obtain understanding of a certain
subject, in contrast to primary research, which concentrates on producing new data through firsthand
examination.

secondary research can be exploratory or explanatory, it is primarily focused on explaining the cause-and
effect relationships of well-defined problems. (Smith, 2020)
 Advantages of Secondary Research Disadvantages of Secondary Research

Cost-Effective: Secondary research is Lack of Specificity: The data collected may

generally less expensive than primary not be tailored to the specific needs of the
research since it relies on data that has research project, which can limit its relevance.
already been collected and published.
Time-Saving: Researchers can access Potential Outdated Information: Secondary
existing information quickly, allowing data may not reflect the current situation or
them to gather insights without the trends, especially if it has not been updated
lengthy process of data collection. Wide recently.
Range of Data: Secondary research Quality and Reliability Issues: The accuracy
provides access to a broad spectrum of of secondary research depends on the
information from various sources, reliability of the original sources. If the original
enabling a more data is flawed, the conclusions drawn can also
comprehensive understanding of the be misleading.
topic. Limited Control: Researchers have no control
over how the data was collected, which may
Established Data: The data used in
introduce biases or inconsistencies.
secondary research has often been peer
reviewed or validated, which can lend
credibility to the findings.

2. Methods

a) Qualitative Research method: Qualitative research focuses on exploring phenomena in-

depth to understand experiences, meanings, and perspectives. This type of research often deals
with non-numerical data, such as interviews, focus groups, ethnographic studies, and
observations. It emphasizes understanding the complexity of human behaviour and the context
in which it occurs.
 Advantages and Disadvantages of Qualitative research

Advantages of Qualitative Research Disadvantages of Qualitative Research

Rich, Detailed Data: Qualitative research Subjectivity and Bias: The researcher's
provides in-depth insights into participants' own biases, interpretations, or
thoughts, feelings, and behaviours, capturing preconceptions can influence data collection
the complexity of human experiences. and analysis, potentially affecting the
validity of the findings.
Contextual Understanding: This method
allows researchers to explore phenomena in

their natural context, making findings more Limited Generalizability: Because qualitative
relevant and realistic. research often involves small, non-random
samples, the findings may not be generalizable
Flexibility: The flexible and open-ended nature
to the larger population.
of qualitative research allows researchers to
adjust their methods as new themes or insights Time-Consuming: Qualitative research
emerge during the study. methods, such as interviews and observations,
can be time-intensive to conduct and analyse,
requiring significant effort to process large
volumes of data.

c) Quantitative Research method Quantitative Research Methods

• Surveys and Questionnaires: Collect numerical data through structured questions that can be
analysed statistically.
• Experiments: Involve manipulating variables to observe their effect on other variables under
controlled conditions.
• Longitudinal Studies: Track the same group of participants over an extended period to observe
changes or trends.
• Correlational Studies: Examine the relationship between two or more variables without
manipulating them.
• Statistical Analysis: Use tools like regression analysis, hypothesis testing, and descriptive statistics
to analyse the data. (Johnson, 2023)
 Advantages and Disadvantages of Quantitative research

Advantages of Quantitative Research Disadvantages of Quantitative Research

Objectivity: Quantitative research is based Lack of Depth: Quantitative research

on numerical data and statistical analysis, may not provide a deep understanding of
which minimizes researcher bias and the underlying reasons or motivations
subjectivity. behind behaviour or attitudes.

Generalizability: Large, random samples Limited Flexibility: Pre-structured tools

allow the findings to be generalized to a like surveys or questionnaires may not
broader population. capture all the nuances of the research
topic.
Replicability: Quantitative studies can be
replicated with different samples or in Context Ignorance: Quantitative
different contexts, enhancing the reliability methods often focus on variables in
of the results.

Precision and Accuracy: Quantitative methods isolation, neglecting the broader context in
can provide precise, reliable measurements which they occur.
that can lead to highly specific conclusions.
Over-Simplification: Reducing complex
phenomena to numerical data may
oversimplify the complexities of human
behaviour.

d) Scientific method

The scientific method is a systematic approach to research that involves observing phenomena,
formulating hypotheses, conducting experiments, and analysing data to draw conclusions. It is
designed to minimize bias and ensure objective, reliable results. The process typically follows
these steps:

1. Observation: Identifying a phenomenon or problem.

2. Hypothesis: Formulating a testable explanation or prediction.

3. Experimentation: Testing the hypothesis through controlled experiments or data collection.

4. Analysis: Analysing the data to determine whether it supports or refutes the hypothesis.

5. Conclusion: Drawing conclusions based on the results of the analysis and determining whether the
hypothesis is valid.
 6. Replication: Repeating experiments to verify the results. (Johnson, 2023)

Advantages and Disadvantages of Scientific Method

Advantages of Scientific Method Disadvantages of Scientific Method

Objectivity: The scientific method minimizes bias Limited by Current Knowledge: The
by relying on empirical evidence and systematic scientific method is based on existing
testing. knowledge and frameworks, which may
limit the scope of inquiry or the
Replicability: Experiments and procedures can be interpretation of results.
repeated and verified by other researchers, which
helps validate the results. Ethical Constraints: In some cases,
experiments may involve ethical dilemmas
Consistency: By following a structured approach, (e.g., medical trials), limiting the range of
the scientific method ensures consistent and
experiments that can be conducted.
reproducible results.
Reductionism: The scientific method often
breaks complex phenomena into

Accuracy and Precision: The method allows for smaller, more manageable components,
precise measurement and rigorous analysis, leading which may overlook the
to reliable conclusions. interconnectedness or complexity of real-
world systems.

3. Choosing the right research methods.

After reviewing the aforementioned research methods, I must now select the best one for my own
research paper. Based on my own evaluations, I have determined the following research methodologies:
Method of Quantitative Research: When precise and highly generalizable research is needed, quantitative
approaches are the best option. This approach aids in objectively measuring variables and testing
particular hypotheses by gathering and evaluating numerical data. When researchers need to compare
groups of subjects, examine causal linkages, or search for common patterns in a big sample, they
frequently employ quantitative research.

Qualitative Research Method: Qualitative research is the best option for complicated subjects that call for
a thorough examination of people's opinions, feelings, and experiences. In order to comprehend the
nature of social phenomena, this approach relies on gathering non-numerical data, such as text, photos,
or audio. It gives researchers greater freedom to modify their inquiries and methodologies, leading to the
discovery of fresh viewpoints that quantitative methods might overlook.

Secondary Research: When time and resources are scarce or primary data is already available, secondary
research is the best option. This approach depends on recycling data that has already been gathered, such
as surveys, statistics, or historical reports. Although it saves time and money, researchers must be careful
to assess the trustworthiness and appropriateness of the data to verify that the study still fits the original
objectives.

P3. Conduct primary and secondary research using appropriate methods for a computing research
project that consider costs, access and ethical issues
1. Primary Research Methods

Primary research involves gathering original data directly from sources through various methods. These
methods are tailored to your specific research needs, particularly user preferences and system functionality
in the context of a personalized learning system.

a. Surveys and Questionnaires

• Purpose: Gather quantitative and qualitative data from potential users (students, teachers, or
administrators) about their needs, preferences, and attitudes toward personalized learning.

• Method: Create an online survey using tools like Google Forms or SurveyMonkey. Focus on
questions that address:

o Current challenges in personalized learning (e.g., lack of customization, engagement issues).

o Preferred features in a personalized learning system (e.g., adaptive content, real-time

feedback).

o Opinions on data privacy and how they would like their data to be used.

• Considerations:

o Costs: Low (free tools available).

o Access: Ensure the survey is accessible to your target users (students, teachers, etc.) via
email or social media.

o Ethical Issues: Informed consent, anonymization of responses, and clear data privacy
policies.

b. Interviews
• Purpose: Conduct semi-structured interviews with users, educators, or experts in personalized
learning.

• Method: Prepare a list of open-ended questions and use video conferencing tools (Zoom, Google
Meet) or in-person interviews. Focus on understanding user experiences, expectations, and
challenges with personalized learning systems.

• Considerations:

o Costs: Low to moderate (if interviews are done online, costs are minimal).
 o Access: Ensure you have access to educators, students, or other relevant stakeholders for
interviews. o Ethical Issues: Informed consent, confidentiality of responses, and permission
to record interviews.

c. Usability Testing

• Purpose: Test a prototype or early version of your personalized learning system to gather feedback
on usability, effectiveness, and user engagement.

• Method: Create a prototype and ask users to perform specific tasks (e.g., navigating the system,
completing assignments). Observe their interactions and ask follow-up questions.

• Considerations:

o Costs: Moderate to high (if developing a working prototype requires resources). o

Access: Ensure access to a group of users who represent your target demographic.

o Ethical Issues: Informed consent, minimizing harm by ensuring users' data is protected
during testing.

d. Focus Groups

• Purpose: Discuss user needs and preferences in-depth through group discussions. This method
allows you to observe group dynamics and obtain diverse viewpoints.

• Method: Organize a group of 4-8 participants (students, educators, etc.) to discuss their experiences
and expectations of personalized learning systems.

• Considerations:

o Costs: Low to moderate (cost of organizing and compensating participants). o

Access: Ensure you have access to a diverse group of people to avoid bias in feedback.

o Ethical Issues: Informed consent and confidentiality.

2. Secondary Research (Documents Review)

Secondary research involves gathering data from existing sources like academic papers, industry reports,
and market research. This type of research helps you build a foundation of existing knowledge and find
proven strategies for designing your system.

1. Lucking, R., Holmes, W., Griffiths, M., & Forcier, L. B. (2016). "Intelligence Unleashed: An Argument for
AI in Education."
Goal and Objectives of Research:
  To explore the potential of artificial intelligence (AI) in transforming education systems.
 To advocate for integrating AI technologies to enhance personalized learning and support educators.
Methods Used:
 A review of existing AI applications in education, focusing on practical examples and their impacts.
 Analysis of potential benefits, challenges, and ethical considerations in implementing AI in learning
systems.
Key Results of the Research:
 AI can provide personalized learning paths tailored to individual needs, improving engagement and
outcomes.
 It highlights the importance of collaboration between AI systems and human educators.
 Challenges such as data privacy and ethical concerns must be addressed.

2. Li, F. W. B., Lau, R. W. H., & Dharmendran, P. (2009). "A Three-Tier Profiling Framework for Adaptive E-
Learning."
Goal and Objectives of Research:
 To develop a framework for adaptive e-learning systems that adjusts content based on learner
profiles.
 To enhance learning experiences by creating personalized education environments.
Methods Used:
 Proposal of a three-tier profiling framework, including learner profiles, domain knowledge models,
and pedagogical strategies.
 Testing the framework using a prototype system and evaluating its adaptability.
Key Results of the Research:
 The framework effectively adapts content to learners' needs, improving knowledge retention and
satisfaction.
 The integration of domain-specific knowledge with learner profiles enhances personalization.
 Recommendations for implementing similar systems in broader educational contexts.
3. Khalil, M., & Ebner, M. (2016). "Using Electronic Learning Systems in Higher Education: Learning
Analytics and Personalized Learning."
Goal and Objectives of Research:
 To investigate the role of learning analytics in improving personalized learning experiences in higher
education.
 To evaluate how data-driven insights can support students and instructors.
Methods Used:
 Case studies of e-learning systems incorporating learning analytics.
 Data analysis to identify patterns in student behaviour and learning outcomes.
Key Results of the Research:
 Learning analytics provide actionable insights into student performance, enabling timely
interventions.
 Personalized feedback and adaptive recommendations enhance student engagement and
outcomes.
 Institutional support and training are critical for successful implementation.

4. Brusilovsky, P., & Millán, E. (2007). "User Models for Adaptive Hypermedia and Adaptive Educational
Systems."
Goal and Objectives of Research:
 To explore the development and use of user models in adaptive educational systems.
 To understand how these models can support personalized learning experiences.
Methods Used:
 Review of existing adaptive hypermedia systems and their user modelling techniques.
 Development of taxonomy for user models in adaptive educational contexts.
Key Results of the Research:
 User models enable systems to tailor content, navigation, and interaction to individual learners.
 The combination of explicit and implicit data collection methods enhances model accuracy.
 The study highlights the need for ongoing refinement of models to ensure effectiveness.
5. Pope Nici, S. A. D., & Kerr, S. (2017). "Exploring the Impact of Artificial Intelligence on Teaching and
Learning in Higher Education."
Goal and Objectives of Research:
 To examine the transformative potential of AI in teaching and learning within higher education.
 To identify challenges and opportunities associated with AI integration.
Methods Used:
 Literature review of existing studies and case examples of AI applications in education.
 Discussion of pedagogical implications and future research directions.
Key Results of the Research:
  AI enhances learning experiences through personalization and automation of routine tasks.
 Ethical and pedagogical challenges, such as data privacy and dependency on AI, need careful
consideration.
 AI fosters a shift toward student-cantered learning but requires complementary human oversight.

3. Considerations: Costs, Access, and Ethical Issues

a. Costs

• Primary Research: Surveys and questionnaires are cost-effective, but prototyping and usability
testing may require significant resources. If you're developing a working prototype, the
development cost can be high.

• Secondary Research: Literature reviews and online forums are generally free, but accessing industry
reports or specialized academic articles may require a subscription or institutional access. b. Access

• Primary Research: Ensure you have access to a diverse user group. Online tools like Google Forms
and video conferencing tools (Zoom) make access easier. However, ensure your sample represents
the broader target demographic.

• Secondary Research: Access to academic papers and industry reports may require subscriptions or
institutional access. Some reports may be behind paywalls, but you can often find open-access
papers or summaries on academic platforms.

c. Ethical Issues

• Informed Consent: Always seek permission from participants, whether for surveys, interviews, or
usability testing. Make sure they understand how their data will be used.

• Privacy: Protect personal data, especially when handling sensitive information about students or
educators. Follow GDPR or other relevant data protection laws.

• Bias and Representation: Ensure your research methods and sample populations are representative
of the broader user base to avoid bias in findings.
1. Survey form

Figure 1
Figure 2
Figure 3
Figure 4
Figure 5
 Figure 6

2. Interview form
Figure 7
Figure 8
Figure 9
Figure 10
 Figure 11

Figure 12

P4. Apply appropriate analytical tools, analyse research findings and data
Analysing data from interview
Figure 13

Figure 14
Figure 15

Figure 16
 Figure 17

Figure 18

 The majority of respondents prefer visual and auditory learning styles, emphasizing the importance of
interactive and media-rich content. A significant portion also Favors text-based learning, while kinaesthetic
learning is the least popular. These preferences suggest that educational tools or AI systems should focus
on providing visual aids, audio resources, and written materials to meet diverse learning needs.
 Figure 19

Results:

1. Less than 5 hours (36.7%):

o A significant portion of respondents spend minimal time on self-study, indicating potential barriers
like a lack of time or motivation.

2. 5–10 hours (30%):

o Close to a third dedicate moderate effort to self-study each week.

3. 10–15 hours (20%):

o A smaller group invests more substantial time in learning outside of structured settings.

4. More than 15 hours (13.3%):

o The fewest respondents are highly committed to extensive self-study, showcasing dedication to
learning.

 The majority of respondents dedicate 5–10 hours or less per week to self-study, while a smaller group
invests more time. This suggests that learning solutions should be efficient and tailored to fit into limited
schedules. AI tools could support this by providing personalized, time-efficient resources that maximize
learning in shorter periods.
 Figure 20

 All respondents either support or are open to trying adaptive learning content that adjusts based on
progress. This highlights a positive reception toward personalized learning systems. However, for those
unsure, demonstrating the tangible benefits of adaptivity could help increase acceptance and engagement
with such tools.

Figure 21

 While a large portion of respondents either agree or are neutral about AI's ability to improve
education, there is room for further exploration and education on AI's benefits. Demonstrating
successful applications of AI in educational settings could help convert neutral or sceptical
respondents into supporters.
 Figure 22

 While most respondents see AI as moderately to highly effective in addressing individual learning needs, a
notable portion remains sceptical. This highlights the need to improve AI systems' capabilities in
personalizing learning experiences and demonstrating their impact to win over more users.

Figure 23

 Most respondents are either comfortable or neutral about using AI-based study suggestions, with a
minority expressing discomfort. This shows that while many trust AI's potential in resource curation,
 addressing concerns about recommendation reliability and demonstrating clear benefits could increase
confidence among neutral and hesitant users.

Figure 24

• The results indicate that many people consider quick access to relevant resources as the greatest benefit of
using AI in study.
• Personalized learning experiences are also highly valued, accounting for more than one-third of the votes.
• However, real-time feedback and efficient study planning are seen as less significant benefits.

Figure 25
• The survey reflects that participants are primarily worried about the increasing reliance on technology in
education.
• Privacy issues and the potential loss of human interaction are also key areas of concern.
• Bias in AI-generated content is a notable concern but not as prominent as the others.

Figure 26

• There is a generally positive attitude toward AI-based study assistants, with most participants leaning
towards likely or very likely (4 or 5).

• However, a small proportion of respondents remain hesitant or unlikely to adopt these tools.
 Figure 27

• General Preference for Collaboration: The majority of respondents (60%) see AI as a supporting role in
education, emphasizing the importance of maintaining human interaction and traditional teaching methods
alongside technological advancements.
• Openness to AI Leadership: Over one-third (33.3%) are open to AI playing a leading role, which reflects a
growing interest in the transformative potential of AI in modernizing educational practices.
• Low Neutrality: Only a small percentage (6.7%) are neutral, suggesting that most individuals have clear
opinions on this issue, indicating its relevance and importance in educational discourse.
• Balanced Viewpoint: The results highlight a balanced approach where the integration of AI in education
should be gradual and carefully aligned with human-driven methods to address concerns about
overreliance on technology.

Analysing responses from interview:

Figure 28

Figure 29
Figure 30

Figure 31

Figure 32
 Figure 33

 The most popular AI applications: Duolingo, Grammarly, Socratic, Khan Academy, and ChatGPT.
Preferred AI features: Personalization of learning paths and instant support are highly valued factors.
Limitations to address: Some tools focus only on specific areas and lack versatility or integration.

Figure 34

 Respondents are largely optimistic about AI's role in education, focusing on personalization, engagement,
and accessibility. However, they underline the importance of maintaining human involvement in teaching
to ensure a holistic learning experience.

Figure 35

 While respondents recognize AI's potential, they express serious concerns about data privacy, equitable
access, over-reliance, and the high cost of implementation. Ensuring transparency, fairness, and human
oversight are key to mitigating these issues.
 Figure 36

 Respondents believe AI can make learning more engaging by personalizing experiences, providing instant
feedback, and incorporating gamification. Automation of repetitive tasks further enhances productivity,
freeing up time for deeper learning activities. These features make studying less monotonous and more
tailored to individual needs.

 Respondents overwhelmingly support adaptive learning systems for their ability to personalize learning
experiences, improve efficiency, and keep students motivated. They value the focus on individual strengths,
weaknesses, and progress, which leads to more engaging and effective education.

Figure 37

 Respondents see significant potential in AI for study management by creating personalized, adaptive
schedules and breaking down tasks into manageable steps. The ability to adjust plans in real-time and track
progress is particularly valued for maintaining efficiency and balance in workloads.
 Figure 38

 Respondents strongly believe that integrating gamification and personalization into AI-based learning apps
would significantly increase their motivation to study. Features that make learning engaging, relatable, and
enjoyable are viewed as key to fostering a positive learning experience.

Figure 39

 Respondents are generally open to AI tools collecting data on learning habits, provided there is
transparency, privacy protection, and user control. They recognize the value of data-driven personalization
but stress the need for secure and ethical data handling practices.

Figure 40

 Respondents see AI as a valuable tool to support and enhance teacher interactions, particularly by
providing tailored resources and handling administrative tasks. However, they stress that AI should not
replace the human connection in teaching, emphasizing its role as a complementary asset rather than a
substitute.
 Figure 41

 Respondents find AI highly effective in enhancing learning through personalized lessons, immediate
feedback, and engaging content. While AI tools are particularly helpful in practice-based subjects, they
work best as a complement to traditional teaching methods, ensuring a balanced approach to education.

P5 Communicate research outcomes in an appropriate manner for the intended audience

Figure 42
Figure 43

Figure
 44

Figure 45

Figure
 46

Figure
Figure 47

48

Figure
P6 Reflect on the effectiveness of research methods applied for meeting objectives of the computing
research project.
The research project aimed to explore the integration of artificial intelligence (AI) into personalized systems
and its impact on enhancing user experience. The research process followed a structured sequence of
steps to ensure thorough and systematic investigation.

The first step was identifying the research problem, which involved defining how AI contributes to
improving user engagement in personalized systems. Following this, a literature review was conducted to
gather secondary data from credible sources such as academic articles and case studies, providing a solid
foundation for the study. Primary research was then carried out through surveys and interviews to collect
firsthand data directly from users and professionals in the AI field, offering valuable insights into real-world
applications and perspectives.

The data collected was analyses using a combination of qualitative and quantitative methods to ensure a
comprehensive interpretation of the findings. Finally, the research results were presented in a manner
tailored to both academic and professional audiences, emphasizing clarity and relevance. This structured
approach facilitated effective data collection, analysis, and reporting, ultimately enhancing the coherence
and reliability of the study.

1.Describe in detail the methods used

 Qualitative research:

Qualitative research played a crucial role in the study by offering in-depth insights into user perceptions
and enabling the exploration of subjective aspects of AI-driven systems. However, it had certain limitations,
including the significant time required for data collection and analysis. Additionally, the smaller sample
sizes often associated with qualitative methods made it challenging to generalize the findings to a broader
population.

 Secondary research

Secondary research complemented this approach by being highly cost-effective and providing access to a
wide range of existing data. It allowed the study to draw from established sources, offering a broader
context. Nonetheless, secondary research had its own limitations, such as the potential for outdated or
overly generalized information that might not fully align with the study's specific focus.

The relationship between these two methods proved to be highly synergistic. Secondary research provided
a solid foundation and a broader understanding of the topic, while qualitative research added depth and
context by capturing nuanced and specific insights. Together, they enabled a comprehensive analysis of AI's
role in personalized systems, leveraging the strengths of each method to offset their individual limitations.

 Role of Literature Review

The literature review served as a cornerstone for the project by:

 • Establishing a theoretical framework.
• Identifying existing gaps in research.
• Supporting the methodology and justifying the use of AI in personalized systems with evidence from
past studies.

2. Evaluate the effectiveness of the methods

a) Strengths of the Methods

The research project effectively utilized a combination of primary and secondary research methods.
Secondary research provided a cost-effective way to establish a strong foundational understanding by
leveraging existing academic articles and case studies. This was complemented by primary research
methods, including surveys and interviews, which gathered tailored and specific data directly relevant to
the research questions. Together, these approaches created a balanced and comprehensive framework for
the study.

The qualitative research method added significant depth to the project by capturing detailed insights into
user perceptions and exploring the subjective aspects of AI-driven systems. This approach was particularly
effective in examining personal experiences and nuanced opinions, which are essential for understanding
the dynamics of personalized systems. Furthermore, the research process followed a logical sequence, from
identifying the problem to presenting the findings, ensuring clarity and coherence throughout. The
inclusion of ethical considerations also enhanced the credibility and integrity of the study.

b) Limitations and Challenges Encountered

Despite its strengths, the research faced several limitations and challenges in scaling. Qualitative methods,
while offering in-depth insights, were constrained by small sample sizes, making it difficult to generalize
findings to a broader population. Additionally, the time-intensive nature of qualitative research demanded
significant effort for data collection and analysis. Secondary research, though valuable, faced issues with
potentially outdated or overly generalized data, which might have limited its relevance. The lack of detailed
evaluation of secondary sources for quality and reliability further affected the robustness of the findings.
Similarly, the absence of specifics about the analytical tools and techniques used, coupled with limited
information on the sampling strategy, such as participant diversity and sample size, impacted the
representativeness and reliability of the primary data. Scaling the research for broader applicability also
posed challenges, as the heavy reliance on qualitative methods could have been supplemented with
quantitative approaches. Statistical tools analysing larger datasets might have validated the qualitative
insights and provided more generalizable findings. Moreover, improving the timeliness and specificity of
secondary data and adopting a more integrated approach combining qualitative and quantitative methods
would have enhanced the research's comprehensiveness and applicability. These aspects represent key
areas for improvement in future research.
 c) Linking to Research Objectives

1. Primary Research Alignment with Objectives

o The use of surveys and interviews directly supported the research objective of gathering
specific, firsthand insights into user interactions with AI-driven systems.

o This method provided tailored and detailed data to understand user perceptions and
behaviours in relation to personalized systems powered by AI.

2. Role of Secondary Research

o Secondary research was essential for establishing a theoretical foundation by reviewing

existing literature and identifying gaps in current knowledge.

o This approach ensured that the research was contextualized within broader academic and
professional landscapes, addressing relevant trends and challenges.

3. Use of Qualitative Methods o the qualitative approach effectively aligned with the objectives by
capturing nuanced and subjective aspects of user experiences. o It allowed for a deeper
exploration of personal perspectives, which are vital for analysing the impact of personalized
systems.

4. Structured Research Process

o The step-by-step process—from problem identification to data presentation—ensured that

each phase of the research was purpose-driven.

o This structured approach allowed all methods to collectively contribute toward fulfilling the
study's goals.

5. Comprehensive Integration

o The combination of primary, secondary, and qualitative methods created a coherent

framework.

o This integration ensured a thorough investigation into how AI enhances user engagement in
personalized systems, aligning all efforts with the research objectives.

P7. Consider alternative research methodologies and lessons learnt in view of the outcomes
1. Alternative Research Methods and Techniques

While the current research utilized qualitative and secondary research methods, considering alternative
methodologies could address some of the observed limitations:
 • Experimental Research:
This approach involves manipulating variables under controlled conditions to establish causal
relationships. For example, conducting A/B testing on AI-driven features of a personalized system
could provide direct evidence of the effectiveness of specific features. Advantages:

o Clear causal relationships.

o Replicable results for verification. Reasons for Selection:

o Offers precise, data-driven validation of findings.

o Aligns well with technological testing environments.

• Mixed-Methods Research:
Combining qualitative and quantitative methods could provide a comprehensive view of the
subject. Surveys (quantitative) could collect broad trends, while interviews (qualitative) could
explore user perspectives in-depth. Advantages:

o Balances depth with generalizability.

o Enables triangulation of data for robust conclusions. Reasons for Selection:

o Enhances reliability and validity by addressing the weaknesses of standalone methods.

o Cost-efficient and relatively easy to implement with current resources.

• Case Study Research:

This method allows in-depth analysis of a specific organization or scenario implementing
personalized AI systems. Advantages:

o Provides real-world insights into challenges and successes.

o Facilitates hypothesis generation for further research. Reasons for Selection:

o Contextualizes findings, making them applicable to similar scenarios.

o Requires minimal new data collection, saving time and costs.

2. Weaknesses of Current Research

Several limitations were observed in the existing research methods and outcomes:

• Time Constraints:

o Qualitative methods like interviews required extensive time for scheduling and analysis.

o Limited project timeline restricted sample size and the depth of insights.
 • Participant Recruitment:

o Difficulty in recruiting diverse participants, leading to a smaller and potentially biased

dataset.

o Some participants lacked sufficient knowledge of AI systems, impacting the quality of

feedback.

• Lack of Quantitative Insights:

o While surveys provided numerical data, they were insufficient to explore causal relationships
or test hypotheses comprehensively.

• Secondary Research Quality:

o Some secondary sources were outdated or lacked relevance to the specific focus of the
study.

• Resource Constraints:

o Budget and tool limitations restricted access to advanced analytics and usability testing
platforms.

3. Lessons Learned

The research process yielded valuable lessons for future studies:

• Diverse Methodology is Key: Combining qualitative, quantitative, and experimental methods can
provide richer, more reliable insights. For instance, statistical analysis of large datasets could
complement interviews.

• Participant Selection: Recruitment strategies should target diverse and knowledgeable participants
to ensure comprehensive data collection.

• Data Validation: Evaluating the reliability and relevance of secondary sources is crucial to avoid
biases and ensure credibility.

• Time Management: Prioritizing tasks and streamlining data analysis processes can optimize time
use and allow for deeper exploration of findings.

• Budget Optimization: Leveraging free or low-cost tools for surveys and analysis, such as Google
Forms or open-source statistical software, can mitigate resource limitations.

+ Entity-Relationship Diagram (ERD):

 Figure 49

+ Use Case Diagram:

Figure 50
+ Package Diagram:

Figure 51
Project result

Figure 52

Figure 53
Figure 54

Figure 55
Figure 56

Figure 57
Figure 58

Figure 59
Figure 60

Figure 61
Figure 62

Figure 63
 Figure 64

Test Plan
ID Functionality Test Description Expected Outcome Priority Status

TC1 Login User enters Successful login if High Run

email and correct
password to log information, error
in. message if
incorrect.

TC2 Register User enters Account is High Run

Account personal successfully
information to created and
create an success message is
account. displayed.

TC3 Update User updates Information is Medium Run

Account Info name, email, or updated
password in successfully and
their profile. displayed on the
user's profile.

TC4 Display The product All products are High Not Run
Product List page displays a displayed with
 list of all names, prices, and
products. images.

TC5 Search User searches Products matching High Run

Product for a product by the search keyword
name or are displayed.
category.

TC6 Add to Cart User adds Product is High Run

products from successfully added
the list to their to the cart and
cart. displayed in the
cart.

TC7 Place Order User places an Order is High Run

order from the successfully
cart. created with the
status 'Processing'.

TC8 View Order User views the All past orders are High Run
History list of their past displayed with
orders. status, total price,
and products.

TC9 View Order User views Full details of the Medium Run
Details details of a order, including
specific order. products, quantity,
price, and status,
are displayed.

TC10 Logout User logs out of Successful logout High Run

their account. and redirection to
the login page.

TC11 Admin: Admin adds, Products are High Run

Manage edits, or deletes successfully added,
Products products in the updated, or
system. removed and
reflected in the
product list.
 TC12 Admin: Admin activates User account is Medium Run
Manage or deactivates activated or
Users user accounts. deactivated
successfully, and
the status is
updated.

TC13 Admin: View Admin views Accurate statistics High Run

Statistics reports on and charts for
revenue and revenue and
order volume. orders over time
are displayed.

o ID: Identifier for each test case. o Function:

Specific feature to be tested. o Test description: What
to test in the test case.
o Expectation: Expected result when performing the
test. o Priority: The importance level of the test case.
o Status: The status of the test.

3. Identify Limitations and Challenges:

- Although the techniques used in this study yielded insightful results, they were not without
drawbacks. The following are some significant obstacles and limitations that arose along the
research process:

+ Time-Consuming Data Collection

Challenge: - Conducting user interviews and usability testing required significant time to schedule
sessions and engage participants.
- Analysing qualitative data was also labour-intensive.
• Impact: This limited the number of participants and iterations we could include within the project
timeline.

+ Difficulty in Collecting Data

• Challenge: - Recruiting participants for surveys and interviews who were representative of the
target audience was more difficult than expected. Many potential participants were either
unresponsive or unwilling to participate.
- Some participants lacked the technical understanding needed to provide meaningful
feedback about AI-integrated features.
 • Impact: This resulted in a smaller dataset, which may have reduced the reliability and
generalizability of the findings.

+ Insufficient Depth of Results

• Challenge: - While the use of surveys provided numerical insights into user preferences, they
lacked the depth needed to understand the "why" behind user behaviours.
- Similarly, secondary research, although valuable, sometimes lacked specific details
related to our context.
• Impact: This limited our ability to fully understand nuanced user needs and led to assumptions that
may not fully reflect real-world use cases.

+ Technical Challenges in Diagram Design

• Challenge: - Creating accurate and detailed Erdos and package diagrams required extensive
knowledge of the system and collaboration among team members.
- Miscommunications occasionally led to revisions, which delayed progress. Impact:
This slowed down the design phase and sometimes caused discrepancies between
design and implementation.

+ Limited Budget and Resources

• Challenge: Budget constraints limited access to advanced research tools, such as analytics platforms
or usability testing software.
• Impact: This necessitated reliance on manual methods, which were less efficient.

Conclusion
This research project examined the role of AI in personalized systems, highlighting its potential to enhance user
engagement. By combining primary and secondary research, the study provided valuable insights into AI-driven
customization and user experience. Key findings emphasized the impact of AI technologies like predictive analytics
and natural language processing in creating adaptive, user-cantered systems.

Despite limitations related to sample size and generalizability, the research effectively achieved its objectives
through a structured approach. Future studies could benefit from incorporating experimental methods to validate
findings on a larger scale. Overall, this project offers a strong foundation for the development of more effective,
user-focused AI systems.
References

Brusilovsky, P. &. M. E., 2007. [Online]

Available at: https://link.springer.com/chapter/10.1007/978-3-540-72079-9_1

Johnson, A., 2023. Research Methods and Approaches. Research Insights Online.. [Online]
Available at: www.researchinsights.com/methods

Khalil, M. &. E. M., 2016. [Online]

Available at: https://www.igi-global.com/gateway/article/1735

Li, F. W. B. L. R. W. H. &. D. P. (., 2009. [Online]

Available at: https://www.igi-global.com/gateway/article/1735

Luckin, R. H. W. G. M. &. F. L. B., 2016. Pearson. [Online]

Available at: https://www.pearson.com/news-and-research/working-
learning/learning/education/intelligence-unleashed.html

Popenici, S. A. D. &. K. S., 2017. [Online]

Available at: https://telrp.springeropen.com/articles/10.1186/s41039-017-0062-8

Slang, A., 2024. [Online]

Available at: https://edtechmagazine.com/k12/article/2024/09/ai-education-2024-educators-
express-mixed-feelings-technologys-future-perfcon

Smith, J., 2020. Research Methods for Social Sciences. In: s.l.:s.n.

WEST, U. C., 2024. [Online]

Available at: https://www.ucanwest.ca/blog/education-careers-tips/advantages-and-
disadvantages-of-ai-in-education/