Link to the University of Pittsburgh Homepage
Link to the University Library System Homepage Link to the Contact Us Form

Tools for Academic Advisors Based on Existing University Student Data

Ong, Nathan (2024) Tools for Academic Advisors Based on Existing University Student Data. Doctoral Dissertation, University of Pittsburgh. (Unpublished)

This is the latest version of this item.

[img] PDF (Final Version)
Restricted to University of Pittsburgh users only until 22 January 2025.

Download (7MB) | Request a Copy


Universities already maintain vast stores of student data, but such data are underutilized and unstructured. Typical student data analytics approaches maintain their focus on unstructured data and create tools that give predictions without the structured context the data came from, requiring users to recontextualize the results to be able to diagnose issues and perform interventions. Academic advisors are no different: despite being stewards of the programs they advise for, it is impossible for them to know every concept from every course, let alone understand the relationships between them. Furthermore, it is just as impossible for advisors to know every student and be able to determine what recommendations may be better for current students that are similar to other historical groups of students.

I propose reintroducing structured context back into the data flow, with the goal of providing advisors with easy-to-interpret tools that provide data-driven insights. I first show that structured student schedule and grade data can uncover new observations when using existing techniques for student grade prediction, specifically that instructors have a larger than anticipated effect on student grades. With the knowledge that structured data can lead to useful information, I then developed two tools that utilize structured data at different granularities that cater to advisors: (a) StudentPaths, for unsupervised machine learning insights into student performance and scheduling at the course level, and (b) Concept Progression Maps, for insights into student performance within a course at the concept level. These tools were developed and utilized in a single-blind study with academic advisors and students, where only advisors had access to the tools and information. From the studies, I found that despite the challenges that advisors had with the tools, the information derived from these tools can change the conversational dynamic in academic advising sessions and demonstrate that these changes have the potential to make a positive impact on future student performance in their courses.


Social Networking:
Share |


Item Type: University of Pittsburgh ETD
Status: Unpublished
CreatorsEmailPitt UsernameORCID
Ong, Nathannro5@pitt.edunro50009-0003-3806-4894
ETD Committee:
TitleMemberEmail AddressPitt UsernameORCID
Committee ChairMosse,
Committee MemberWalker,
Committee MemberZnati,
Committee MemberBesterfield-Sacre,
Committee MemberLesgold,
Date: 22 January 2024
Date Type: Publication
Defense Date: 17 August 2023
Approval Date: 22 January 2024
Submission Date: 25 August 2023
Access Restriction: 1 year -- Restrict access to University of Pittsburgh for a period of 1 year.
Number of Pages: 270
Institution: University of Pittsburgh
Schools and Programs: School of Computing and Information > Computer Science
Degree: PhD - Doctor of Philosophy
Thesis Type: Doctoral Dissertation
Refereed: Yes
Uncontrolled Keywords: Student Trajectory, Concept Map, Academic Advising, Qualitative Analysis, Student Data Analytics, Student Grade Prediction
Date Deposited: 22 Jan 2024 16:52
Last Modified: 22 Jan 2024 16:52

Available Versions of this Item


Monthly Views for the past 3 years

Plum Analytics

Actions (login required)

View Item View Item