Conference Session

DSAI Technical Session 4: Workshops, Professional Development, and Training

Collection

2025 ASEE Annual Conference & Exposition

Authors

yilin zhang, University of Florida; Bruce F. Carroll, University of Florida; Jinnie Shin, University of Florida; Kent J. Crippen, University of Florida

Tagged Divisions

Data Science and Artificial Intelligence (DSAI) Constituent Committee

Paper ID #48016PEER HELPER (Peer Engagement for Effective Reflection, Holistic EngineeringLearning, Planning, and Encouraging Reflection) Automated Discourse AnalysisFrameworkyilin zhang, University of FloridaDr. Bruce F. Carroll, University of Florida Dr. Carroll is an Associate Professor of Mechanical and Aerospace Engineering at the University of Florida. He holds an affiliate appointment in Engineering Education. His research interests include engineering identity, self-efficacy, and matriculation of Latine/x/a/o students to graduate school. He works with survey methods and overlaps with machine learning using

Conference Session

DSAI Technical Session 10: Research Infrastructure and Institutional Insights

Collection

2025 ASEE Annual Conference & Exposition

Authors

Pallavi Singh, University of South Florida; Joel Howell; Joshua Karl Thomas Ranstrom, University of South Florida; Wilfrido A. Moreno P.E., University of South Florida

Tagged Divisions

Data Science and Artificial Intelligence (DSAI) Constituent Committee

experiences.Inspired by a comparable business program, the PFE series was developed to address the pro-fessional formation of students, initially grounded in the National Association of Colleges andEmployers (NACE)’s Career Readiness Competencies. The program was introduced as techni-cal electives with small class sizes and led by a professor of practice. Within the PFE courses,students formulate action plans to enhance their professional networks and achieve specificcareer objectives.This paper presents a data-driven analysis of the Professional Formation of Engineers (PFE)program. Using data collected over time, students’ action plans with a focus on ambitionlevels, completion rates, and their correlation with career-related outcomes such as

Conference Session

DSAI Technical Session 3: Integrating Data Science in Curriculum Design

Collection

2025 ASEE Annual Conference & Exposition

Authors

Karl D. Schubert FIET, University of Arkansas; Carol S Gattis, University of Arkansas; Stephen R. Addison, University of Central Arkansas; Tara Jo Dryer, University of Arkansas; Adam Musto, Arkansas Department of Education

Tagged Topics

Diversity

Tagged Divisions

Data Science and Artificial Intelligence (DSAI) Constituent Committee

$80,000 to$120,000/year, making it an attractive career for both new graduates and those seekingadvancement. [2, 3] There are over 100 data science/analytics roles currently open in Arkansasaccording to the U.S. Bureau of Labor Statistics, and employment in this field is projected to grow36% from 2021 to 2031 [4].The Arkansas Economic Development Commission’s Science Advisory Committee submitted theupdated Arkansas Science & Technology Plan 2024, approved by Secretary of Commerce HughMcDonald. This plan aims to “enable the crystallization of focused research and innovationplanning and provide a focus for the Arkansas scientific community.” Key strategies includealigning research and education with the state’s key industries and expanding both

Conference Session

DSAI Technical Session 9: Student Reflections, Metacognition, and Competency Mapping

Collection

2025 ASEE Annual Conference & Exposition

Authors

Majd Khalaf, Norwich University; Toluwani Collins Olukanni, Norwich University; David M. Feinauer P.E., Virginia Military Institute; Michael Cross, Norwich University; Ali Al Bataineh, Norwich University

Tagged Topics

Diversity

Tagged Divisions

Data Science and Artificial Intelligence (DSAI) Constituent Committee

responses for two cohorts from the Spring of 2023 andSpring of 2024, focusing on the themes of collaboration and planning (teamwork), as well asproblem solving. Lessons learned about the process of applying the techniques, as well asinsights gained about the student experience as captured in their reflections, are shared in theconclusions section, along with the authors’ recommendations for the use of the AI-assistedprocess to analyze qualitative data as a means of better understanding the students’ projectexperience.This work advances the subject of engineering education by showing how automated naturallanguage processing (NLP) techniques may be used to evaluate student reflections, offering ascalable and effective substitute for conventional

Conference Session

DSAI Technical Session 9: Student Reflections, Metacognition, and Competency Mapping

Collection

2025 ASEE Annual Conference & Exposition

Authors

Juan Alvarez, University of Illinois at Urbana - Champaign; Max Fowler, University of Illinois at Urbana - Champaign; Jennifer R Amos, University of Illinois at Urbana - Champaign; Yael Gertner, University of Illinois at Urbana - Champaign

Tagged Divisions

Data Science and Artificial Intelligence (DSAI) Constituent Committee

introductory Engineering courses.1 IntroductionMetacognition refers to the self-regulation process that learners can use to measure their ownunderstanding and, thus, how effectively they are studying. Researchers have identified twolevels of metacognition: knowledge and regulation. The level of Knowledge entails knowingfacts about oneself and the demands of the task, procedural knowledge on strategies pertain-ing to the task, and knowing which strategies to apply in different situations. Regulationrefers to students’ ability to plan, monitor, and evaluate the effectiveness of their strategiesas well as debug when facing difficulties[4, 11].Metacognition skills have been shown to help students perform better academically[2, 3, 5, 6].Moreover, lack

Conference Session

DSAI Technical Session 1: K–12 and Early Exposure to Data Science and AI

Collection

2025 ASEE Annual Conference & Exposition

Authors

Faiza Zafar, Rice University; Carolyn Nichol, Rice University; Matthew Cushing, Rice University

Tagged Topics

Diversity

Tagged Divisions

Data Science and Artificial Intelligence (DSAI) Constituent Committee

participants collaborate with graduate studentmentors, engage in discussions with faculty members engaged in digital health research, explorereal datasets, and create grade-appropriate lesson plans. This paper focuses on the overallprogram design and the experiences of an elementary STEM teacher who participated in theprogram and implemented the lesson with her students. Literature ReviewArtificial Intelligence (AI) and Machine Learning (ML) in Elementary Curriculum The integration of AI and ML into elementary education is an emerging area of interestthat has the potential to equip young learners with foundational skills critical for the future [1].As technology continues to evolve, it is becoming

Conference Session

DSAI Technical Session 10: Research Infrastructure and Institutional Insights

Collection

2025 ASEE Annual Conference & Exposition

Authors

Jordan Esiason, SageFox Consulting Group; Talia Goldwasser, SageFox Consulting Group; Rebecca Zarch, SageFox Consulting Group; Alan Peterfreund, SAGE

Tagged Topics

Diversity

Tagged Divisions

Data Science and Artificial Intelligence (DSAI) Constituent Committee

education equity, to workforce data. Pre-college summer bridge STEM programs 17 Diversity action plans 15 B. Initial Tool Development Near peer mentoring 15 Entrepreneurial programs (at any level) 14 To meet these needs and facilitate discussion among stake- Reforming curriculum and teaching practices 14 Collaborative learning / living environments 11 holders, the CIDER team began the development of the Institutional leadership engagement 11 Engineering Education Ecosystem Landscape Framework 3 . Mentoring with peers of color

Conference Session

DSAI Technical Session 1: K–12 and Early Exposure to Data Science and AI

Collection

2025 ASEE Annual Conference & Exposition

Authors

Faiza Zafar, Rice University; Carolyn Nichol, Rice University; Matthew Cushing, Rice University

Tagged Divisions

Data Science and Artificial Intelligence (DSAI) Constituent Committee

providing adequate academic advising and counseling, such asstaffing shortages and limited resources [1,2]. With advisors often managing large caseloads,students sometimes struggle to receive the personalized guidance they need to succeedacademically, plan their careers, and navigate personal obstacles [3]. Similarly, while counselorsare available to offer emotional and mental health support, the availability of these services isoften limited, leaving students without timely assistance [1,2]. To address these gaps, AI-powered tools present a potential solution. While AI has been increasingly integrated intoeducational settings [4], its use for enhancing academic advising and counseling services remainsrelatively novel [5,6]. AI platforms can offer

Conference Session

DSAI Technical Session 3: Integrating Data Science in Curriculum Design

Collection

2025 ASEE Annual Conference & Exposition

Authors

Ashraf Badir, Florida Gulf Coast University; Ahmed S. Elshall, Florida Gulf Coast University

Tagged Divisions

Data Science and Artificial Intelligence (DSAI) Constituent Committee

proficient final report following recognized academic or professional standards.10. Presentation: Deliver a clear, organized, and effective class presentation to disseminate the project’s findings to a wider audience4.3 Schedule and AssessmentTo ensure the project is feasible, teams schedule a meeting with the instructor to discuss theirproposed project and obtain approval. Meetings are typically around 15 minutes but may beextended as needed. Teams need to obtain approval before they submit their project abstract.The project is graded according to the following schedule:• Project Abstract (10%): Two-page abstract outlining the proposed research question or industry-oriented problem, method, plan for implementation, and expected outcomes

Conference Session

DSAI Technical Session 8: Learning Analytics and Data-Driven Instruction

Collection

2025 ASEE Annual Conference & Exposition

Authors

Robert J. Rabb P.E., Pennsylvania State University; Ivan E. Esparragoza, Pennsylvania State University; Jennifer X Wu

Tagged Topics

Diversity

Tagged Divisions

Data Science and Artificial Intelligence (DSAI) Constituent Committee

Engineering Education, 2025 Data Analytics for Engineering Student Success and College OperationsAs resource constraints have driven calls for more transparency and accountability in highereducation, high demand disciplines like engineering are using data sets to justify decisions andshape strategic planning goals. However, engineering is also well-poised to employ data in visualand useful ways to analyze and synthesize years of data and trends. Serving a largeundergraduate engineering student body across multiple campuses and encompassing multipleengineering disciplines, the Penn State University’s College of Engineering can gain insightsinto the student population, faculty, and departments’ needs. The

Conference Session

DSAI Technical Session 8: Learning Analytics and Data-Driven Instruction

Collection

2025 ASEE Annual Conference & Exposition

Authors

Chuhao Wu, Pennsylvania State University; Sarah Zipf, Pennsylvania State University; Na Li, Penn State University; David Benjamin Hellar, The Pennsylvania State University

Tagged Divisions

Data Science and Artificial Intelligence (DSAI) Constituent Committee

’ online activity increased on days with a planned activity (asindicated by NSSE codes) than on days without a planned activity. The differences aresignificant as suggested by the ANOVA test (𝐹(3,387) = 33.31, 𝑝 < .001, 𝜂𝐺2 = .21). Forexample, Figure 2 shows noticeable spikes on Nov 7, 2022, and Nov 6, 2023, in the onlineactivity. These spikes are associated with collaborative learning but potentially also with theexams scheduled for four days later. The difference in average activity levels between differentNSSE codes is not significant. Higher-Order Learning Quantitative Reasoning ICAs NSSE ICAs NSSE

Conference Session

DSAI Technical Session 4: Workshops, Professional Development, and Training

Collection

2025 ASEE Annual Conference & Exposition

Authors

Neel Manmohan Parekh, University of Florida; Kevin Scroggins, University of Florida; Yolanda Gil, University of Southern California; Emmanuel J Dorley, University of Florida

Tagged Divisions

Data Science and Artificial Intelligence (DSAI) Constituent Committee

competencies emphasized in data science teams, suggesting thatadapting such frameworks could enhance collaboration instruction for data sciencestudents.Two of the most popular and widely used are the PISA 2015 CPS assessment model(PISA 2015) 8and the Assessment and Teaching of 21st Century Skills CPS Assessment(ATC21S) 7 . The PISA2015 model of CPS views it as a cross between collaboration and individual problem-solving.The cross between the three collaboration components(Establishing and maintaining sharedunderstanding, taking appropriate action to solve the problem, and establishing and maintainingteam organization) and the individual four problem-solving components(Exploring andUnderstanding, Representing and Formulating, Planning and Executing

Conference Session

DSAI Technical Session 8: Learning Analytics and Data-Driven Instruction

Collection

2025 ASEE Annual Conference & Exposition

Authors

Alyson Grace Eggleston, Pennsylvania State University; Robert J. Rabb P.E., The Pennsylvania State University; Eric Donnell, The Pennsylvania State University

Tagged Topics

Diversity

Tagged Divisions

Data Science and Artificial Intelligence (DSAI) Constituent Committee

also providing valuable insights to faculty and their mentors asthey plan for continued career development. Moving toward predictive models sets the stage forkey insights that are sensitive to an institutional context—in this case, the primacy ofinterdisciplinary teams for securing initial seed funding.Moving forward, BI dashboards also allow decision makers to steer pilot funding priorities toclosely track with the changing goals of federal funding agencies. By integrating key metrics,such as team strengths and applicant funding histories, a higher resolution footprint of researchimpact against particular grant funding mechanisms can be established.Finally, research administration BI dashboards facilitate continuous evaluation processes

Conference Session

DSAI Technical Session 4: Workshops, Professional Development, and Training

Collection

2025 ASEE Annual Conference & Exposition

Authors

Olatunde Olu Mosobalaje, Covenant University; Moses Olayemi, The University of Oklahoma

Tagged Divisions

Data Science and Artificial Intelligence (DSAI) Constituent Committee

[7]. • Industry collaborations, facilitated through the Society of Petroleum Engineers' Data Science and Engineering Analytics Technical Section (SPE DSEATS). • Resource planning, addressing funding needs for ICT infrastructure, travel, and conference participation.Additionally, the program sustainability is pre-conditioned on external factors such as institutionalsupport, participant commitment, and availability of funding. An On-going Precursor ImplementationRecognizing that educators require foundational programming skills to effectively integrate dataanalytics and machine learning into petroleum engineering curricula, we initiated a pre-requisiteprofessional development effort: the Python

Collection

2025 ASEE Annual Conference & Exposition

Authors

Xiaoning Jin; Sagar Kamarthi, Northeastern University

Tagged Divisions

Data Science and Artificial Intelligence (DSAI) Constituent Committee

career planning tools to provide end-to-end solutions.ConclusionDeveloping a recommendation engine leveraging GPT-4 and the RAG method the authorsdemonstrated a significant advancement in personalized learning solutions. By utilizingOpenAI’s text-embedding-3-large model and Pinecone’s vector database, the system efficientlyaddresses the challenges of personalization, scalability, and accuracy in courserecommendations. Integrating OpenAI's assistant API further enhances its capabilities, offeringseamless interactions and context-aware suggestions.Our results highlight the potential of LLMs to transform how individuals discover and engagewith learning opportunities. The positive outcomes underline the benefits of adopting cutting-edge AI

Conference Session

DSAI Technical Session 5: Educational Technology and Innovative Tools

Collection

2025 ASEE Annual Conference & Exposition

Authors

D. Matthew Boyer, Clemson University; Lukas Allen Bostick, Clemson University; Ibrahim Demir, The University of Iowa; Bijaya Adhikari; Krishna Panthi, Clemson University; Vidya Samadi, Clemson University; Mostafa Saberian, Clemson University; Carlos Erazo Ramirez, The University of Iowa

Tagged Divisions

Data Science and Artificial Intelligence (DSAI) Constituent Committee

related to the virtual format, noting its benefitsfor accessibility but expressing a preference for in-person interaction for certain aspects of theworkshop, such as team collaboration.Participants highlighted networking opportunities as a key benefit across findings, withinterviewees emphasizing the value of interdisciplinary collaboration and the potential for futurepartnerships. Both participants also discussed their plans to integrate workshop content into theirprofessional workflows. However, they acknowledged that doing so would require additionalpractice and reinforcement of the skills introduced during the workshop.Integrating Interview and Survey InsightsIn this section, we synthesize insights from the survey responses and follow-up

Conference Session

DSAI Technical Session 3: Integrating Data Science in Curriculum Design

Collection

2025 ASEE Annual Conference & Exposition

Authors

Md. Yunus Naseri, Virginia Polytechnic Institute and State University; Vinod K. Lohani, Virginia Polytechnic Institute and State University; Manoj K Jha P.E., North Carolina A&T State University; Gautam Biswas, Vanderbilt University; Caitlin Snyder; Steven X. Jiang, North Carolina A&T State University; Caroline Benson Sear, Virginia Polytechnic Institute and State University

Tagged Topics

Diversity

Tagged Divisions

Data Science and Artificial Intelligence (DSAI) Constituent Committee

potential of LLMs in enhancing data scienceeducation and plans several expansions incorporating these tools. Both students and instructorshave identified a significant need for personalized learning experiences due to varying levels ofdata science expertise and different learning pace requirements among students. Instructorsbelieve LLMs can help address these challenges by providing customized support for conceptunderstanding and a smooth introduction to data analysis tools such as coding, particularly forstudents with limited prior exposure to data science. However, instructors emphasize theimportance of treating LLMs as assistive tools rather than authoritative sources, encouragingstudents to maintain critical thinking and responsibility for

Conference Session

DSAI Technical Session 7: Natural Language Processing and LLM Applications

Collection

2025 ASEE Annual Conference & Exposition

Authors

Alexis Frias, University of California Merced; Shrivaikunth Krishnakumar, San Jose State University; Ayush Pandey, University of California Merced

Tagged Divisions

Data Science and Artificial Intelligence (DSAI) Constituent Committee

student self-efficacy and creativity in CS education by fostering independentproject development. We plan to study this hypothesis in future research. Additionally, we discussthe operational costs of our autograding system, its compatibility with existing frameworks, andthe current limitations of our approach. By enabling more creative and personalized assignments,FlexiGrader has the potential to transform assessment practices in introductory computer sciencecourses.1 IntroductionIt is well established in computer science (CS) education literature [1], that learning-by-doingand rigorous practice are effective for students to gain programming expertise. Consequently, theformative and summative assessments in CS courses often take the form of

Conference Session

DSAI Technical Session 6: Academic Success, Performance & Complexity

Collection

2025 ASEE Annual Conference & Exposition

Authors

Kristina A Manasil, The University of Arizona; Gregory L. Heileman, The University of Arizona; Melika Akbarsharifi, The University of Arizona; Roxana Akbarsharifi, The University of Arizona; Aryan Ajay Pathare, The University of Arizona

Tagged Divisions

Data Science and Artificial Intelligence (DSAI) Constituent Committee

explore strategies to increase graduation rates by 5% during thecurrent academic year. It focuses on identifying and supporting ’near completers’, students who,while slightly behind, need only a few additional credits to graduate at the end of the year. Us-ing progress analytics, the study identified near-completers as those who have completed 70% ormore of their degree requirements prior to the start of the current academic year. By analyzingfactors such as degree progress, credit utilization, and barriers to completion, the study examineshow targeted interventions can address common challenges faced by these students. Mid-yearevaluations conducted after the fall semester reassess student progress and inform refinements tospring enrollment plans

Conference Session

DSAI Technical Session 8: Learning Analytics and Data-Driven Instruction

Collection

2025 ASEE Annual Conference & Exposition

Authors

Clara Fang, University of Hartford

Tagged Divisions

Data Science and Artificial Intelligence (DSAI) Constituent Committee

thedatabase will also be provided.Task 3: Summary and Results Presentation: The project results will be communicated with theCT DOT. In addition, a research plan involving a long-range duration of data (e.g. over 10years) combined with other pertinent databases (e.g. environment) will be proposed andsubmitted to the CT DOT applying for external funding. The student will contribute to writingthis proposal and other research paper.The students will walk through each stage of this analytics pipeline that enables them to collect,clean, understand, model, and report data analyses. By paying close attention to data patterns,the stories behind outliers, relationships among data sets, and the external factors that may haveaffected the data, it is expected

Conference Session

DSAI Technical Session 7: Natural Language Processing and LLM Applications

Collection

2025 ASEE Annual Conference & Exposition

Authors

Kaiwen Guo, New York University Tandon School of Engineering; Malani Snowden, New York University Tandon School of Engineering; Rui Li, New York University

Tagged Topics

Diversity

Tagged Divisions

Data Science and Artificial Intelligence (DSAI) Constituent Committee

Kubernetes cluster. We never transmit student data to external APIs or third-partyservices, thus minimizing any risk of leakage. The script evaluate_llama.py encapsulatesthis offline inference process by loading the final JSON (produced by csv_to_json.py),using a local Llama installation for text generation, and then saving the results into a CSV.This approach gives us full control over data handling: ● Immediate Anonymization – Before or during the CSV-to-JSON conversion, identifiable student fields (e.g., names, emails) are replaced or hashed (planned for the next iteration) to ensure no personally identifiable information is exposed to the language model. ● GPU Acceleration – We execute the model on an NVIDIA A100 GPU, making it

Conference Session

DSAI Technical Session 6: Academic Success, Performance & Complexity

Collection

2025 ASEE Annual Conference & Exposition

Authors

Michael T Johnson, University of Kentucky; Johné M Parker, University of Kentucky

Tagged Topics

Diversity

Tagged Divisions

Data Science and Artificial Intelligence (DSAI) Constituent Committee

. Differentialcollege/university graduation retention numbers suggest that there are a small number of moderately-lowperformance indicators which are able to identify students who are much more likely to have academicsuccess in fields outside of engineering.Outcomes from these analyses include new mechanisms for early identification of at-risk students, for whomspecialized advising and success coaching would be beneficial, as well as the development of new curricularplanning options for students who are not yet calculus ready in their first semester and would benefit fromcustomized curricular planning to support better first-year performance.1 IntroductionThe demand for engineers in the workforce continues to grow [1], but the number of engineering

Conference Session

DSAI Technical Session 5: Educational Technology and Innovative Tools

Collection

2025 ASEE Annual Conference & Exposition

Authors

Dong Hun Lee, Purdue University at West Lafayette (COE); Anne M Lucietto, Purdue University at West Lafayette (PPI); Diane L Peters P.E., Kettering University

Tagged Divisions

Data Science and Artificial Intelligence (DSAI) Constituent Committee

, plan motion,and make real-time decisions [2]. Artificial intelligence-driven technologies, such asconvolutional neural networks (CNNs), have further enhanced AVs' capabilities, allowing themto detect and classify objects in complex and dynamic environments [1].Object Detection and Scene UnderstandingFor AVs to be effective, they need to be able to detect and react to objects and obstacles in real-time. Object detection models like Faster R-CNN and YOLO (You Only Look Once) havesignificantly improved vehicle perception by identifying pedestrians, traffic signs, and vehiclesmore accurately and efficiently [3][8].A complementary process called scene classification involves understanding the generalenvironment (a city, a highway, a rural area) and

Conference Session

DSAI Technical Session 1: K–12 and Early Exposure to Data Science and AI

Collection

2025 ASEE Annual Conference & Exposition

Authors

Sri Krishna Chaitanya Velamakanni, Pennsylvania State University; Suman Saha, Pennsylvania State University

Tagged Divisions

Data Science and Artificial Intelligence (DSAI) Constituent Committee

significantly increase dropout rates [21]. Conventionaleducational resources often do not align with the unique requirements of online learners.Additionally, studies emphasize the importance of providing students with content that can beaccessed in a non-linear, step-by-step manner, eliminating the need for manual searches to locatespecific information [21],[22],[23]. These challenges highlight the need for innovativeeducational strategies that offer efficient, targeted access to learning materials.One promising approach to addressing these challenges is microlearning, an innovativepedagogy involving the delivery of content in small, well-planned learning units and short-termlearning activities. Microlearning aligns with cognitive learning theories

Conference Session

DASI Technical Session 2: Artificial Intelligence in Higher Education

Collection

2025 ASEE Annual Conference & Exposition

Authors

Indu Varshini Jayapal, University of Colorado Boulder; James KL Hammerman; Theodora Chaspari, University of Colorado Boulder

Tagged Topics

Diversity

Tagged Divisions

Data Science and Artificial Intelligence (DSAI) Constituent Committee

equation: Factor Score ∼ Survey Time (pre/post) + Demographic Variable (1)3.5 Analysis of responses to open-ended essay questionsThe three open-ended essay questions asked participants to discuss their questions and concernsabout the design and implementation of AI systems across different domains in healthcare andemployment selection (Table 3). ID Question A machine learning (ML) algorithm has been designed to assist radiologists with estimating the level of damage COVID-19 has caused to patients’ lungs. This can help the physician in prescribing an appropriate medication and treatment plan for the patients. The ML

Conference Session

DSAI Technical Session 7: Natural Language Processing and LLM Applications

Collection

2025 ASEE Annual Conference & Exposition

Authors

Mikayla Friday, University of Connecticut; Michael Thomas Vaccaro Jr, University of Connecticut; Arash Esmaili Zaghi P.E., University of Connecticut

Tagged Divisions

Data Science and Artificial Intelligence (DSAI) Constituent Committee

emerged as powerful tools in education, offering thepotential to transform classroom dynamics through automation, personalization, and enhancedstudent engagement [1]. Educators have already begun utilizing LLMs to generate lesson plans,streamline grading, and provide personalized feedback to students [2]. Additionally, LLMs havebeen implemented as Intelligent Tutoring Systems, assisting students in gaining a deeperunderstanding of challenging topics by offering tailored explanations and interactive learningexperiences [3]. One particularly promising but underexplored application of LLMs in educationis their potential for personalized learning (PL), specifically in the realm of text adaptation.Unlike traditional PL approaches, which categorize

Conference Session

DSAI Technical Session 6: Academic Success, Performance & Complexity

Collection

2025 ASEE Annual Conference & Exposition

Authors

Gregory L. Heileman, The University of Arizona; Chaouki T Abdallah, Georgia Institute of Technology; Kristina A Manasil, The University of Arizona; Melika Akbarsharifi, The University of Arizona; Roxana Akbarsharifi, The University of Arizona

Tagged Topics

Diversity

Tagged Divisions

Data Science and Artificial Intelligence (DSAI) Constituent Committee

(a) (b)Figure 1: (a) An example electrical engineering program curriculum, organized as a degree plan over eightterms. The courses in the curriculum are shown as vertices, and the prerequisites are shown as directededges. (b) Highlighting the Calculus I course in this curriculum shows that Calculus I blocks 15 other coursesin the curriculum (shown in green), and the longest path in the curriculum that includes Calculus I (shownas a blue dashed line) has length 8. 20 300 number of curricula number of curricula

Conference Session

DASI Technical Session 2: Artificial Intelligence in Higher Education

Collection

2025 ASEE Annual Conference & Exposition

Authors

Ibukun Samuel Osunbunmi, Pennsylvania State University; Taiwo Raphael Feyijimi, University of Georgia; Lexy Chiwete Arinze, Purdue University at West Lafayette (COE); Viyon Dansu, Florida International University; Bolaji Ruth Bamidele, Utah State University; Yashin Brijmohan, Utah State University; Stephanie Cutler, The Pennsylvania State University

Tagged Topics

Diversity

Tagged Divisions

Data Science and Artificial Intelligence (DSAI) Constituent Committee

., Jun. 2024.[24] D. Ng, W. Luo, H. Chan, and S. Chu, “An examination on primary students’ development in AI literacy through digital story writing,” Ng T K Luo W Chan H M Chu K W 2022 Exam. Prim. Stud. Dev. AI Lit. Digit. Story Writ. Comput. Educ. Artif. Intell. 100054, vol. 4, 2022, Accessed: Jan. 14, 2025. [Online]. Available: https://www.researchgate.net/publication/358460136_An_examination_on_primary_student s'_development_in_AI_literacy_through_digital_story_writing[25] I. Ajzen, “From Intentions to Actions: A Theory of Planned Behavior,” in Action Control, J. Kuhl and J. Beckmann, Eds., Berlin, Heidelberg: Springer Berlin Heidelberg, 1985, pp. 11– 39. doi: 10.1007/978-3-642-69746-3_2.[26] D. Cetindamar, K

Conference Session

DSAI Technical Session 6: Academic Success, Performance & Complexity

Collection

2025 ASEE Annual Conference & Exposition

Authors

Cristian Saavedra-Acuna, Universidad Andres Bello, Concepcion, Chile; Monica Quezada-Espinoza, Universidad Andres Bello, Santiago, Chile; Danilo Alberto Gomez, Universidad Andres Bello, Concepcion, Chile

Tagged Topics

Diversity

Tagged Divisions

Data Science and Artificial Intelligence (DSAI) Constituent Committee

the 2024 IEEE International Technology Conference (OTCON), 2024. DOI: 10.1109/OTCON60325.2024.10688123.[11] L. M. Cruz Castro, T. Li, L. Ciner, K. A. Douglas, and C. G. Brinton, "Predicting Learning Outcome in a First-Year Engineering Course: A Human-Centered Learning Analytics Approach," presented at the ASEE Annual Conference & Exposition, 2022.[12] C. Burgos, M. L. Campanario, D. D. L. Peña, J. A. Lara, D. Lizcano, and M. A. Martínez, "Data mining for modeling students’ performance: A tutoring action plan to prevent academic dropout," Computers & Electrical Engineering, vol. 66, pp. 541–556, Feb. 2018, doi: 10.1016/j.compeleceng.2017.03.005.[13] P. B. Thomas, C. R. Bego, and A. D. Piemonte

Conference Session

DASI Technical Session 2: Artificial Intelligence in Higher Education

Collection

2025 ASEE Annual Conference & Exposition

Authors

Ananya Prakash, Virginia Polytechnic Institute and State University; Mohammed Seyam, Virginia Polytechnic Institute and State University

Tagged Topics

Diversity

Tagged Divisions

Data Science and Artificial Intelligence (DSAI) Constituent Committee

surveyed institutionsalready used Artificial Intelligence (AI) in their admissions process, and an additional 30%planned to do so in 2024. AI gives universities the advantage of increased efficiency, allowingthem to focus their limited resources on other critical tasks like selecting students for financialaid and scholarships [5]. Therefore, it is essential to innovate AI systems that assist in theadmissions process while still minimizing the possibility of biased outcomes.The rapid development of the technology industry led to an increased number of graduate degreeholders yet the diversity among these graduates has not shown comparable growth. For instance,the male-to-female ratio among master's graduates has remained nearly constant in the