top of page

Project Description

This project aims to serve the national interest by developing an online platform that will help to improve retention in introductory computing courses. The US Bureau of Labor Statistics predicts that the demand for computing jobs will continue to grow in the coming years. However, the projected number of computer science graduates does not meet the predicted demand. One of the reasons for this is the high dropout rates of computing majors. A computer science degree is tied to developing technical skills, which may be taught while students solve problems involving challenging tasks. Solving such challenging tasks helps students to learn but often results in struggles with the material. While such struggles are usually linked with diminishing self-efficacy, these struggles can become instruments to promote learning and self-efficacy, thus becoming productive struggles. Converting classroom challenges to productive struggles as a means for learning may help to improve retention in introductory computer science classes. The online platform, called PULSE (Productive strUggle for deveLoping Self Efficacy), is intended to foster productive struggles, improve self-efficacy, and enhance skill development.

PULSE will make use of long-form computer programming assignments outside the classroom. The platform will use machine learning-driven approaches to identify the obstacles students face while solving a programming assignment. This will enable instructors to intervene when students struggle, allowing students to learn from the struggles and improve their work before the submission deadline. The project should advance computer science education by generating new knowledge about student struggles and programming activity patterns in solving coding problems outside the classroom. The insights of the proposed research may provide ways to reduce student dropout rates in introductory computing classes in college. PULSE will be released as open-source software allowing other institutions to deploy it in their programming courses. The NSF IUSE: EHR Program supports research and development projects to improve the effectiveness of STEM education for all students. Through the Engaged Student Learning track, the program supports the creation, exploration, and implementation of promising practices and tools. This project is also supported by the NSF IUSE:HSI program, which has the goals of enhancing the quality of undergraduate STEM education, and increasing the recruitment, retention, and graduation rates of students pursuing associate’s or baccalaureate degrees in STEM.

Key Collaborators

monika.jpeg

I am an Assistant Professor of the Department of Computer Science at The University of Texas at El Paso (UTEP). I joined the department in Fall 2017. Before that, I was a Research Assistant Professor and the Assistant Director of CyberShare Center of Excellence at UTEP.

I graduated with a Ph.D. from the Department of Computer Science at Virginia Tech. I received my MS from Montana State University-Bozeman in Computer Science, and BS from Shahjalal University of Science and Technology in Computer Science and Engineering.

I work in the broad areas of data science, specially information retrieval and integration, data mining, prediction, and recommendation. I use data science concepts to address computational challenges in application areas of cyber-security, educational games, and gamification.

Monika Akbar, PhD
Assistant Professor

utep cs logo.png
shahriar.jpeg

 

 

I am an Associate Professor in the Department of Computer Science at the University of Texas at El Paso (UTEP). I have put on a few mascots over the last few years: Trojan (Virginia State University), Hokie (Virginia Tech), and Bobcat (Montana State University). I am now a proud Miner (UTEP).

I received a Ph.D. in Computer Science from Virginia Tech in 2012 and joined the Department of Computer Science at UTEP in 2013.

My research focuses on Data Science, with a specialization in Big Data Mining and Machine Learning. My recent research interests cover modeling of evolving natural languages, predicting future-topics of interest in news, hypotheses generation, and video mining. I collaborate with researchers from the government sector (such as the U.S. Army), industry, and academia in designing algorithms to solve critical data analytic problems. ​

I have a passion for "computing for all." I have built a website, computing4all.com, where I write my thoughts on computing-related topics. I have a plan to develop computing-related educational materials for non-computer science audience and publish via computing4all.com.

M. Shahriar Hossain, PhD
Associate Professor

utep cs logo.png

Key Outcomes

22_09_UTEP_ABC_lab_logo_full_color_main_edited.png

$299,950
NSF Funded

22_09_UTEP_ABC_lab_logo_full_color_main_edited.png

 1
Graduate Student Research Assistant Mentored

bottom of page