The Impact of Structured Prompt-Driven Generative AI on Learning

Data Analysis in Engineering Students

a
Ashish Garg and Ramkumar Rajendran
IDP in Educational Technology, Indian Institute of Technology Bombay, Mumbai, India

Keywords: Large Language Model, Structured Prompt, Programming, Data Analysis.

Abstract: This paper investigates the use of Generative AI chatbots, especially large language models like ChatGPT, in
enhancing data analysis skills through structured prompts in an educational setting. The study addresses the
challenge of deploying AI tools for learners new to programming and data analysis, focusing on the role of
structured prompt engineering as a facilitator. In this study Engineering students were trained to adeptly use
structured prompts in conjunction with Generative AI, to improve their data analysis skills. The t-test
comparing pre-test and post-test scores on programming and data analysis shows a significant difference,
indicating learning progress. Additionally, the task completion rate reveals that 45% of novice participants
completed tasks using Generative AI and structured prompts. This finding highlights the transformative
impact of Generative AI in education, indicating a shift in learning experiences and outcomes. The integration
of structured prompts with Generative AI not only aids skill development but also marks a new direction in
educational methodologies.

1 INTRODUCTION especially for beginners in programming and data

analysis. Previous research has focused on AI code-
This study highlights the significant impact of generators for experienced programmers,
Generative AI, especially large language models like overlooking its potential for novices, particularly in
OpenAI's ChatGPT, on education. These AI systems, introductory data analysis (Vaithilingam, P., Zhang,
known for their human-like text generation, are T., & Glassman, E. L., 2022). The research aims to
revolutionizing education by providing interactive fill this gap by examining how Generative AI can
and tailored learning experiences (Firaina, R., & facilitate learning and enable independent data
Sulisworo, D., 2023). In educational contexts, analysis. It is driven by a research question on
Generative AI goes beyond a simple tool, becoming Generative AI's practical use and its educational
key in creating dynamic learning spaces that address impact through structured prompt engineering.
diverse student needs (Ruiz-Rojas, L. I., et al., 2023). RQ: How does structured prompt engineering
Transitioning to the specific context of with Generative AI, influence the mastery of
programming and data analysis, the application of programming and data analysis concepts among
Generative AI assumes a critical role. These complex, learners with no prior programming experience?
data-intensive fields benefit from AI's ability to In response to the research questions, this study
analyze intricate data and identify patterns (Dhoni, P., involved 20 participants aged 24 to 29, all beginners
2023). This transition enhances conceptual in text-based programming and data analysis, from
understanding, allowing learners to explore the various engineering fields. They participated in
theoretical foundations of these disciplines. structured training to understand basic data analysis
Generative AI's incorporation is set to transform concepts and use Generative AI tools. During a four-
conventional educational models, providing a richer hour session, they engaged in prompt engineering
learning experience (Sarkar, A., 2023). with Generative AI to address data analysis tasks. The
Building on this foundation, this study study showed significant learning improvements,
investigates Generative AI's role in education, with a large effect size of 0.89 and a p-value < 0.05 in

a
https://orcid.org/0000-0002-0411-1782

270
Garg, A. and Rajendran, R.
The Impact of Structured Prompt-Driven Generative AI on Learning Data Analysis in Engineering Students.
DOI: 10.5220/0012693000003693
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 270-277
ISBN: 978-989-758-697-2; ISSN: 2184-5026
Proceedings Copyright © 2024 by SCITEPRESS – Science and Technology Publications, Lda.
 The Impact of Structured Prompt-Driven Generative AI on Learning Data Analysis in Engineering Students

the paired sample t-test on programming knowledge summaries, and computer code (Rajabi, P.,
and data analysis concepts. These findings suggest Taghipour, P., Cukierman, D., & Doleck, T., 2023).
the benefits of incorporating Generative AI and Transitioning from the applications of generative
structured prompts in education, especially in AI to its specific role in programming, recent studies
domains like programming and data analysis. have explored the impactful role of generative AI. An
experimental study showcased how the programming
tool Codex, powered by generative AI, outperformed
2 BACKGROUNDS AND learners in a CS1 class on a rainfall problem, ranking
in the top quartile (Denny, P. et al., 2023). Another
LITERATURE REVIEW investigation used the flake8 tool to assess code
generated by AI against the PEP8 coding style,
The literature review examines the application of revealing a minimal syntax error rate of 2.88% (Feng,
Generative AI in educational settings, with a focus on Y. et al., 2023). A notable study involved Github's
ChatGPT's contributions to various learning generative AI platform, which initially failed to solve
environments. This section highlights the critical role 87 Python problems; however, applying prompt
of structured prompt engineering and evaluates the engineering techniques enabled it to resolve
limited existing studies on Generative AI's use in approximately 60.9% of them successfully (Finnie-
programming and data analysis. This section Ansley, J. et al., 2022).
identifies areas that require further investigation to The Above findings collectively highlight the
fully understand the educational benefits and efficacy of generative AI in code generation. This
opportunities of Generative AI. transition into the realm of prompt engineering, a
critical aspect of maximizing the potential of
2.1 Generative AI in Education generative AI in educational contexts, leads us to the
next section of the literature review, focusing on the
Generative AI tools, such as ChatGPT, have become nuances of prompt engineering.
popular for their capacity to generate responses and
content that mimic human interaction, using 2.2 Prompt Engineering
advanced deep learning algorithms and vast amounts
of text data (Dai, Y. et al., 2023). To explore the Maximizing Generative AI's benefits in education
applications and potential advantages of these AI relies on the proficient use of prompt engineering, a
tools in education, a systematic literature review was key skill that significantly affects AI model
conducted, The applications of Generative AI are interactions (Kohnke, L., Moorhouse, B. L., & Zou,
summarized as follows D., 2023). Effective prompt engineering requires
Personalized Tutoring: AI provides customized understanding AI's operational principles, and
tutoring and feedback, tailoring the learning ensuring prompts are clear and precise to improve
experience to each student's needs and progress tokenization and response accuracy. Including
(Bahrini, A. et al., 2023). detailed context in prompts also enhances the AI's
Automated Essay Grading: AI systems are trained ability to form relevant connections, boosting
to grade essays by identifying characteristics of response quality.
effective writing and offering feedback (De Silva, D. The art of prompt engineering also involves
et al., 2023). specifying the desired format of the AI's responses,
Language Translation: AI translates educational ensuring they align with user expectations in terms of
materials into multiple languages, ensuring accurate structure and style. Controlling verbosity within
and understandable translations (Kohnke, L., prompts is another key aspect, allowing users to
Moorhouse, B. L., & Zou, D., 2023). manage the level of detail in the AI's responses, thus
Interactive Learning: AI creates dynamic learning tailoring the information density to suit specific
environments with a virtual tutor that responds to needs.
student inquiries (Bahrini, A. et al., 2023). However, understanding these principles is just
Adaptive Learning: AI adjusts teaching strategies the beginning. Practical application demands a
based on student performance, customizing the structured approach, embodied in the CLEAR
difficulty of problems and materials (Bahrini, A. et framework. This framework provides a systematic
al., 2023). strategy for crafting prompts that effectively harness
Content Creation: AI generates a variety of the capabilities of AI language models. It's a synthesis
content, including articles, stories, poems, essays, of clarity, context, formatting, and verbosity control,

271
CSEDU 2024 - 16th International Conference on Computer Supported Education

all working in concert to elevate the communication 2.3 Gaps in Existing Literature
process with AI, making it efficient and impactful in
educational settings (Lo, L. S., 2023). The framework The existing research focuses on generative AI's
elements are presented below as ability in code generation and problem-solving but
Concise: Prompts should be succinct, clear, and often misses its wider educational effects and
focused on the task's core elements to guide AI interactions with learners. Key areas needing further
towards relevant and precise responses. exploration include:
Logical: Prompts need a logical flow of ideas, Educational Impact in Data Analysis: The
helping AI understand context and relationships educational benefits of using tools like ChatGPT in
between concepts, resulting in coherent outputs. teaching data analysis are unclear. Their influence on
Explicit: Prompts must specify the expected output student motivation, comprehension of data analysis
format, content, or scope to avoid irrelevant principles, and lasting skill acquisition needs
responses. examination, especially for newcomers to data
Adaptive: Prompts should be flexible, allowing analysis.
experimentation with different structures and settings Prompt Engineering in Education: The role of
to balance creativity and specificity. prompt engineering in educational settings is largely
Reflective: Continuous evaluation and refinement of unexplored. Recognized for enhancing AI
prompts are crucial, using insights from previous performance, it has the potential to help learners
responses to improve future interactions (Lo, L. S., articulate data analysis problems, think critically, and
2023). engage creatively with tasks that need exploration.
Additionally, some strategies mentioned in open The literature review highlights the need for this
AI documentation for writing prompts are presented study, focusing on prompt engineering's unexplored
below potential in education, especially in data analysis. It
identifies a gap in understanding how Generative AI,
Strategy: Write Clear Instructions with structured prompts, affects analytical skills and
self-directed learning. This research aims to bridge
I. Include details in your query to get relevant this gap, providing insights into integrating
answers. Generative AI effectively in education and advancing
II. Ask the model to adopt a persona using the data analysis practices.
system message.
III. Use delimiters to indicate distinct parts of the
input.
3 STUDY DESIGN
Strategy: Provide Reference Text
In this part, the research method is explained,
I. Instruct the model to answer using a reference including the tasks created, the data used for these
text. tasks, and the tests conducted before and after to
II. Instruct the model to answer with citations assess the results. The discussion also covers the SUS
from a reference text. survey used to evaluate user satisfaction and the
training provided for effective prompt crafting.
Strategy: Split Complex Tasks into Simpler
Subtasks 3.1 Selection of Concept of Data
Analysis for the Task
I. Use intent classification to identify the most
relevant instructions. The study focuses on two essential data analysis
II. Summarize long documents piecewise and skills: data aggregation and merging. Aggregation
construct a full summary recursively (OpenAI, simplifies data, revealing trends and easing novices
2023). into complex tasks, much like learning the alphabet
The strategic application of prompt engineering before forming sentences (McKinney, W., 2022).
tactics significantly refines AI interactions, ensuring Merging integrates diverse datasets, essential in the
responses are both precise and contextually relevant. data landscape, offering a unified view (McKinney,
W., 2022).

272
 The Impact of Structured Prompt-Driven Generative AI on Learning Data Analysis in Engineering Students

3.2 Dataset for the Task and Problem concepts through Python programming. These
Statement for the Task Questions are designed across three levels of Bloom's
taxonomy, the test comprises five questions each
3.2.1 Dataset ● Understanding (L1)
● Applying (L2)
The dataset includes data from September to January, ● Analyzing (L3)
capturing attributes such as student video usage, These questions emphasized practical application
student ID, school ID, view count, and last access also over mere rote learning and ensured relevance to
date and time. Each month's dataset contains over the task at hand. These questions originated from the
10,000 observations, providing a comprehensive official panda's documentation and underwent
view of student engagement with video content. This multiple validations by industry experts, ensuring
dataset is created for the task and the discussed their efficacy in gauging participant performance.
concept of data analysis. However, this dataset draws
inspiration from the school education program where 3.3.2 SUS Survey
students are provided tablets to enhance learning.
The System Usability Scale (SUS) was adapted to
3.2.2 Task gather feedback on the Generative AI tool in data
analysis, providing a reliable evaluation of its
Based on the given dataset, the task is designed that effectiveness and user experience (Brooke, J., 1995).
way so that it cannot be completed with no Combining SUS scores with task performance and
programming software like Excel and Tableau, etc., learning metrics allows for a detailed assessment of
The following are the problem statements of the task the tool's impact on user proficiency.
T1: Calculate the total daily video usage for each
student across all months. 3.4 Design of Structured Prompt
T2: Given the unique data capture cycle of student Training
video usage (the 26th of one month to the 25th of the
next), compute the monthly total video usage for each A one-hour training session has been designed to
student, for example, compute the student total video introduce participants to prompt engineering,
usage for October (1st October to 31st October). employing an example-based approach. Initially, the
T3: Calculate the monthly video usage for each CLEAR framework and strategies from OpenAI's
school over all the months. documentation are explained to lay the foundation.
For the completion of the tasks, Python Subsequently, two examples of structured prompts
programming is selected because it is preferred in are presented to illustrate the concepts in practice.
data analytics due to its simplicity, extensive libraries The first example is non-contextual, featuring a
like pandas and NumPy, and compatibility with big question from the Union Public Service Commission
data and machine learning. Its strong community and ethics exam, a well-known civil service recruitment
relevance in real-world applications, along with examination in India as shown in Figure 1. This
market demand as highlighted by Zheng, Y. (2019), example is chosen for its general nature, ensuring that
make it superior to alternatives like R and Weka, even students with limited programming or data
justifying its choice for this study. analysis experience can grasp the concept of
structured prompts. The structured prompt for this
3.3 Instrument Designed question is crafted to build trust and provide an easy
introduction to the topic. However, the prompt for
The study selects specific tools to ensure the findings this case is written this way “At the beginning of the
are valid and reliable. It aims to closely examine the prompt, the full question is clearly stated, followed by
experiences, needs, and performance of participants a detailed context explaining that this is a UPSC exam
to fully understand the research goals. question, the nature of the exam, the selection
process, and the roles of those selected. The
3.3.1 Pre and Post-Test requirement to limit the response to 250 words is
specifically highlighted. The prompt then instructs to
A set of 15 MCQs was designed, focusing adopt the persona of an evaluator, whose profile is
predominantly on the concepts of aggregation and clearly outlined, to ensure the response meets the
merging. These questions aimed to assess the evaluator's expectations. Additionally, a strategy is
participants' comprehensive understanding of the provided to organize the answer logically, enhancing

273
CSEDU 2024 - 16th International Conference on Computer Supported Education

the overall response utilizing concepts from the a relevant context but also prepares students for the
CLEAR framework and Open AI strategies. types of tasks they will encounter. This careful, step-
by-step approach ensures that all participants,
regardless of their background, can effectively engage
with and understand the principles of prompt
engineering, setting a solid foundation for their
subsequent tasks in data analysis

4 USER STUDY
This study examined the impact of Generative AI and
structured prompt engineering on novices learning
Figure 1: Example 1- Structured prompt for answering
UPSC exam question. data analysis, using a four-hour session with Python
and AI tools. Participants independently completed
The second example is contextual and directly related tasks, with researcher guidance and continuous AI
to the field of study. It involves showing students an access, to assess how structured prompts affect
Excel file with a dataset different from the one used learning in a condensed time frame.
in the tasks. For this dataset, a structured prompt is
written based on a specific problem statement as 4.1 Participants
shown in Figure 2,
This study involved 20 graduate-level participants, all
familiar with ChatGPT or similar AI tools but without
formal training in programming or data analytics.
This selection ensured a uniform baseline of
understanding across the 12 male and 8 female
participants, aged 24 to 29. Each participant had
access to ChatGPT 3.5 and shared English as their
formal education language, minimizing language
barriers. Their lack of prior prompt engineering
experience set a consistent starting point for all,
crucial for examining the impact of structured prompt
training on their data analysis skills using Generative
Figure 2: Example 2-Structured Prompt for writing Python AI. This Purposive sampling was important for
code for the comparison of scores for the given training maintaining a controlled study environment and
dataset. focusing on the specific research objectives.

In this case, the prompt is structured using the CLEAR 4.2 Study Procedure
framework and Open AI strategies. It starts by clearly
defining the problem statement. Next, it specifies the In this study, as shown in Figure 3 participants were
requirement for a Python code, it begins by stating the initially briefed on the impact of Generative AI in
file path of the dataset, followed by explicitly naming data analysis and consented to ethical data collection
the columns in this dataset. It then instructs to focus and privacy practices. A pre-test then assessed their
only on the columns relevant to the problem. Based on existing knowledge, establishing a baseline for
the problem statement, it first outlines the comparison subsequent phases. During the training phase, they
metrics and then provides instructions for advanced engaged in a one-hour session on structured prompt
analysis, including checking assumptions. It also writing, essential for effective interaction with
clearly states what actions to take if the assumptions Generative AI tools like OpenAI's ChatGPT, and
are not met. This is all organized in a logical sequence. practiced crafting prompts through contextual and
At the end of the prompt, there's a request to provide non-contextual examples. In the task phase, they
the code and explain each part of the syntax step by applied prompting skills over three hours, tackling
step. This helps the user understand the process and various data analysis tasks and refining their
learn in segments. This approach not only proficiency. Post-intervention, their skills were
demonstrates the application of structured prompts in reassessed to quantify the training's effectiveness.

274
 The Impact of Structured Prompt-Driven Generative AI on Learning Data Analysis in Engineering Students

that there is no significant difference between test

score before and after the intervention.
From Table 2, for all three levels of Bloom's
taxonomy and the total score, the null hypothesis for
the t-test was rejected, indicating a statistically
significant difference in scores post-intervention test.

Table 2: Paired sample t-test statistics for pre-test and post-

test scores of the participants.
Sr. No Level Test P value Effe
Statistic ct
t (1,19) Size
Figure 3: Flow chart of conducted study. 1 L1 6.77 9.04E-07 0.84
2 L2 6.097 3.66 E-06 0.81
Comprehensive data collection included a consent 3 L3 4.29 1.97 E-04 0.70
form, pre and post-tests, output file task-wise, and a 4 Total score 8.66 2.51 E-08 0.89
System Usability Scale survey, providing a
multidimensional understanding of the participants' From the assessment of task output files, the task
learning journeys and the influence of Generative AI completion data reveals a clear trend in students'
tools on enhancing data analysis learning. performance, with a higher success rate observed in
the initial task (T1) compared to the complex
subsequent task (T2, T3). Specifically, 70% of
5 RESULT students completed T1 successfully, while only 55%
and 45% of students were able to complete tasks T2
In this part, we look at the data gathered to understand and T3 respectively. This trend shows that while
how structured prompt engineering and Generative students could manage simple data analysis tasks,
AI affect learning results. they found it difficult when the tasks needed more
Following the initial overview, the analysis began advanced skills, especially in merging data.
with the Levene Test on pre-test scores for Bloom's The System Usability Scale (SUS) survey yielded
taxonomy levels: understanding (L1), applying (L2), a mean score of 72.38 and a standard deviation of
and analyzing (L3), to check variance homogeneity 8.45, indicating a generally positive reception of the
among participants, it is essential for valid statistical Generative AI tool's usability in data analysis
analysis. The Levene test's null hypothesis assumed learning. Participants perceived the tool as user-
no difference in the variance of scores across all three friendly and effective, reflecting a satisfactory user
levels. Detailed test results are presented in Table 1, experience overall.
laying the groundwork for further analysis. Concluding the data analysis, we observed
significant advancements in learning outcomes
Table 1: Levene’s test on pre-test score of participant. through structured prompt engineering and
Generative AI. Moving into the discussion section,
Sr. No Level Levene’s P we explored the deeper implications of these findings.
Test value
value
1 L1_Pre_Test 0.13 0.72
2 L2_Pre_Test 2.66 0.12 6 DISCUSSION AND
3 L3_Pre_Test 0.13 0.72 CONCLUSION
4 Total_score_Pre_Test 0.15 0.70
In addressing RQ, the study's focus was to understand
P value >0.05 from Table 1, suggests that the null the influence of structured prompt engineering with
hypothesis is accepted and it confirms homogeneity Generative AI on the mastery of programming and
among participants, the analysis advanced to compare data analysis concepts among learners with no prior
pre and post-intervention test performances across experience. The quantitative analysis, initiated with
Bloom's taxonomy levels: understanding, applying, the Levene Test, established a uniform baseline
and analyzing and overall scores, for the comparison across participants, ensuring the validity of
paired sample t-test is used with the null hypothesis subsequent comparisons. The paired sample t-tests
revealed a statistically significant improvement in

275
CSEDU 2024 - 16th International Conference on Computer Supported Education

participants' performance across all levels of Bloom's detailed learner interactions and perceptions. A key
taxonomy post-intervention, indicating an improved focus will be evaluating the quality of participants'
understanding and application of programming prompts to enhance critical thinking and refine
concepts crucial for data analysis. training methods. Expected to enrich learning
The substantial effect sizes reported in the t-test theories and Human-Computer Interaction
results underscore the profound impact of the frameworks, this research will help explore how
intervention on learners' ability to grasp and apply Generative AI can innovate pedagogy and create
programming principles within the context of data personalized, accessible educational experiences
analysis. Additionally, task completion rates after worldwide.
structured prompt training with Generative AI
suggest the significant influence of the intervention
on participants' ability to understand and execute data REFERENCES
analysis tasks. This progress goes beyond mere
memorization, indicating a shift towards the Bahrini, A. et al. (2023). ChatGPT: Applications,
comprehension of the underlying principles. opportunities, and threats. 2023 Systems and
Furthermore, the System Usability Scale (SUS) Information Engineering Design Symposium (SIEDS),
survey results, indicating a positive reception of the Charlottesville, VA, USA, 274-279.
Generative AI tool's usability, complement the https://doi.org/10.1109/SIEDS58326.2023.10137850
study's findings. A user-friendly and effective tool is Brooke, J. (1995, November 30). SUS: A quick and dirty
crucial in an educational setting, as it can significantly usability scale. Usability Evaluation in Industry, 189.
reduce the cognitive load on learners, allowing them Dai, Y., et al. (2023). Reconceptualizing ChatGPT and
generative AI as a student-driven innovation in higher
to concentrate on understanding and applying the
education. Procedia CIRP, 119, 84-90.
concepts rather than navigating the tool itself. https://doi.org/10.1016/j.procir.2023.05.002
This study sheds light on the potential of De Silva, D., Mills, N., El-Ayoubi, M., Manic, M., &
Generative AI and structured prompt engineering to Alahakoon, D. (2023). ChatGPT and generative AI
transform educational methods. The results of this guidelines for addressing academic integrity and
research suggest that Generative AI can play a crucial augmenting pre-existing chatbots. Proceedings of the
role in helping learners understand complex subjects IEEE International Conference on Industrial
like programming and data analysis. Moreover, the Technology, 2023-April.
usability of structured prompts has been instrumental https://doi.org/10.1109/ICIT58465.2023.10143123
Denny, P., Kumar, V., & Giacaman, N. (2023). Conversing
in providing students with clear, actionable guidance
with Copilot: Exploring prompt engineering for solving
through intricate learning tasks, enhancing their CS1 problems using natural language. In Proceedings
engagement and help them to master skills. of the 54th ACM Technical Symposium on Computer
However, the study acknowledges its limitations, Science Education (SIGCSE 2023) (pp. 1-7). ACM.
including the absence of log data analysis and https://doi.org/10.1145/3545945.356982
qualitative data like interviews which could provide Dhoni, P. (2023, August 29). Exploring the synergy
deeper insights into the behavioral patterns of high between generative AI, data, and analytics in the
and low performers. The relatively small sample size modern age. TechRxiv.
also restricts the generalizability of the findings. https://doi.org/10.36227/techrxiv.24045792.v1
Feng, Y., Vanam, S., Cherukupally, M., Zheng, W., Qiu,
M., & Chen, H. (2023). Investigating code generation
performance of ChatGPT with crowdsourcing social
7 FUTURE WORK data. In 2023 IEEE 47th Annual Computers, Software,
and Applications Conference (COMPSAC) (pp. TBD).
Future research on integrating Generative AI and IEEE.
Finnie-Ansley, J., Denny, P., Becker, B.A., Luxton-Reilly,
structured prompt engineering in education, A., & Prather, J. (2022). The robots are coming:
especially in programming and data analysis, is set to Exploring the implications of OpenAI Codex on
deepen our understanding of its effects on learning. introductory programming. In Proceedings of the 24th
Planned comparative studies can examine the Australasian Computing Education Conference (pp.
learning outcomes of groups with varying levels of TBD). Virtual Event, February 14–18, 2022.
access to ChatGPT and prompt training, aiming to Firaina, R., & Sulisworo, D. (2023). Exploring the usage of
understand the role of Generative AI in learner ChatGPT in higher education: Frequency and impact on
engagement and educational processes. These studies productivity. Buletin Edukasi Indonesia, 2(01), 39–46.
can expand participant diversity and employ methods https://doi.org/10.56741/bei.v2i01.310
like structured interviews and task analysis to capture

276
 The Impact of Structured Prompt-Driven Generative AI on Learning Data Analysis in Engineering Students

Kohnke, L., Moorhouse, B. L., & Zou, D. (2023). ChatGPT

for language teaching and learning. RELC Journal,
54(2), 537-550.
https://doi.org/10.1177/00336882231162868
Lo, L. S. (2023). The art and science of prompt engineering:
A new literacy in the information age. Internet
Reference Services Quarterly.
https://doi.org/10.1080/10875301.2023.222762
McKinney, W. (2022). Python for data analysis: Data
wrangling with pandas, NumPy, and Jupyter (3rd ed.).
OpenAI. (n.d.). Best practices for using GPT. Retrieved
October 20, 2023, from
https://platform.openai.com/docs/guides/gpt-best-
practices
Rajabi, P., Taghipour, P., Cukierman, D., & Doleck, T.
(2023). Exploring ChatGPT's impact on post-secondary
education: A qualitative study. ACM International
Conference Proceeding Series, art. no. 9.
https://doi.org/10.1145/3593342.3593360
Ruiz, L., Acosta-Vargas, P., De-ta-Llovet, J., & Gonzalez,
M. (2023). Empowering education with generative
artificial intelligence tools: Approach with an
instructional design matrix. Sustainability, 15(15),
11524. https://doi.org/10.3390/su151511524
Sarkar, A. (2023). Will code remain a relevant user
interface for end-user programming with generative AI
models? In Proceedings of the 2023 ACM SIGPLAN
International Symposium on New Ideas, New
Paradigms, and Reflections on Programming and
Software (Onward! 2023) (pp. 153–167). Association
for Computing Machinery.
https://doi.org/10.1145/3622758.3622882
Vaithilingam, P., Zhang, T., & Glassman, E. L. (2022).
Expectation vs. experience: Evaluating the usability of
code generation tools powered by large language
models. In CHI Conference on Human Factors in
Computing Systems Extended Abstracts (pp. 1–7).
Zheng, Y. (2019). A comparison of tools for teaching and
learning data analytics. Conference on Information
Technology Education, 26 Sep 2019, pp. 160

277