top of page

Project Description

With the advent and increased use of the internet, social media has become an integral part of people’s lives. Platforms such as Facebook, Twitter, and TikTok generate a large volume of data that can be analyzed for a range of insights. This underscores the need for educational opportunities in which students can explore big data approaches to extract, visualize, and critically analyze complex algorithms and data structures. This demonstration project will develop a big data curriculum that uses cutting-edge social media data mining techniques via Twitter and a culturally relevant design to engage students from underrepresented groups in the West Texas/El Paso region. The curriculum will be co-designed by a team of teachers and students, and then piloted in El Paso high schools, which have a large population of students who are underrepresented. The outcomes of this project have the potential to transform models of computing and data literacy in which students access their own personal interests to participate in the creation of computational artifacts and navigate the products of others.

This BPC Demonstration Project aims to provide evidence-based insights on “Big Data”-centric computer and data science teaching and learning with underrepresented pre-college student populations. The team will iteratively develop and pilot a culturally relevant data mining and analytics curricular unit with groups of teachers and students who, respectively, serve or come from underrepresented groups. The team will leverage mixed-methodological approaches to examine learning outcomes for CS education and the learning sciences. This research is guided by two research questions: (1) What critical learning and instructional resources are needed to productively sustain a CS curricular intervention that emphasizes culturally relevant data mining and analytics?, (2) What learning experiences and outcomes result when implementing a CS education program that emphasizes culturally relevant data mining and analytics?

Key Collaborators


Amanda Barany is a postdoctoral scholar for the Louis Stokes Alliance for Minority Participation (LSAMP) research initiative, working in the School of Education at Drexel University, and a co-PI for the NSF project “Coding Like a Data Miner: A Culturally Relevant Data Analytics Intervention for High School Students.” She currently works as a researcher in the Games and Learning in Interactive Digital Environments (GLIDE) lab, which unifies her research interests in online learning, the design of digital learning experiences, and long-term learning and identity development.

Amanda has 7 years of experience leveraging quantitative ethnographic techniques such as epistemic network analysis to study learning, identity, and motivation. She is co-chair for the 2022 International Conference on Quantitative Ethnography, and incoming 2022-2023 chair for the Technology, Instruction, Cognition and Learning (TICL) special interest group for the annual American Education Research Association conference. Prior positions include project manager for the Games + Learning + Society research and design lab and graduate researcher in the Harackiewicz interest and motivation lab at the University of Wisconsin-Madison. 

Amanda is passionate about the design, development, and implementation of immersive, interdisciplinary virtual and in-person learning environments. She is also a self-proclaimed methods nerd who will chat at length about how to model learner changes over time. 

Amanda Barany, PhD
Postdoctoral Scholar

omar image_edited.jpg



Dr. Badreddin (aka Badreldin) is an Associate Professor and Associate Director at Northeastern University. He is the director of the Super Twin Research Laboratory; AI-Enabled Software and Hardware Continuous Re-Design. His research is focused on predicting software and systems evolution with the goal of enhancing upfront designs and enabling effective continuous re-engineering. This research creates Super Digital Twins (Digital Twins augmented with the power of predictive analytics), which opens up new discovery pathways in resilient and adaptable architectures.


This research enables engineers to proactively address vulnerabilities even before they materialize.

This research entails investigations of the fundamentals of software design and the development of novel approaches and advanced software analytical tools. Dr. Badreddin contributes to the UML standard and key open-source projects, including EclipseUmpleModelMine, and Susereum. His research explores opportunities to reduce software and data complexities, and the complexity of the tools used for software development and data management.

Omar Badreddin, PhD
Associate Professor

Key Outcomes


NSF Funded


Graduate Student Research Assistants Mentored


Pubs and Presentations

bottom of page