Jaclyn Ocumpaugh

Associate Director, Penn Center for Learning Analytics

Contact

ojaclyn@upenn.edu

Education

Ph.D. (Linguistics) Michigan State University, 2010
M.A. (English Language and Linguistics) North Carolina State University, 2002
B.A. (Linguistics) The University of Texas at Austin, 1999

Programs

Data Science Methods for Digital Learning Platforms

Programs

Learning Analytics M.S.Ed. (Online)

Bio Nav

Biography

Professional Biography

Dr. Ocumpaugh has been working in the field of Learning Analytics for over a decade. She is currently serving as the Associate Director of the Penn Center for Learning Analytics, where she uses her prior training in sociolinguistics to better understand both human-to-human and human-to-computer interaction, as well as affective and motivational constructs that are relevant to learning. She is also using this training to help improve issues related to algorithmic fairness.

Dr. Ocumpaugh’s work centers around the development of use of automated detectors of student engagement. She has contributed to the development of several suites of engagement detectors for different learning systems, many of which were developed without sensors using the Baker Rodrigo Ocumpaugh Monitoring Protocol—a method which she helped to formalize using her training in sociolinguistic fieldwork. This method has now been adapted to seven different countries, using culturally sensitive frameworks.

More recently, she has begun to develop and formalize strategies for data-driven classroom interviewing (DDCI). In these studies, previously developed detectors of student affect and engagement-related behaviors are used to trigger in situ interviews with students. In this way, interviews can take place in-the-moment, allowing us to better understand what is driving the student engagement patterns that were captured by the detectors. Ocumpaugh and her colleagues can then use these interviews to develop actionable insights about the detector data.

Research Interests and Current Projects

Dr. Ocumpaugh is currently working on a large number of projects related to student engagement, including a recent NSF grant award to study the development of student interest in STEM. In this project, she is collaborating with colleagues at the University of Pennsylvania and the University of Illinois Urbana Champaign to conduct data-driven classroom interviews. These interviews will be used to better understand students’ in-the-moment experiences so that we can better assist educators, STEM software developers, and other stakeholders in improving engagement and interest in STEM.

Publications

Selected Publications

Belitz, C., Ocumpaugh, J., Ritter, S., Baker, R. S., Fancsali, S. E., & Bosch, N. (2023). Constructing categories: Moving beyond protected classes in algorithmic fairness. Journal of the Association for Information Science and Technology, 74(6), 663–668. https://doi.org/10.1002/asi.24643

van Stee, E. G., Heath, T., Baker, R. S., Andres, J. A. L., & Ocumpaugh, J. (2023). Help seekers vs. help accepters: Understanding student engagement with a mentor agent. In Wang, N., Rebolledo-Mendez, G., Matsuda, N., Santos, O. C., & Dimitrova, V. (Eds.), Artificial Intelligence in Education: 24th international conference, AIED 2023, Tokyo, Japan, July 3–7, 2023, proceedings (pp. 139–150). Springer Nature. https://doi.org/10.1007/978-3-031-36272-9_12

Nasiar, N., Zambrano, A. F., Ocumpaugh, J., Hutt, S., Goslen, A., Rowe, J., Lester, J., Henderson, N., Wiebe, E., Boyer, K., & Mott, B. (2023). It’s good to explore: Investigating silver pathways and the role of frustration during game-based learning. In Wang, N., Rebolledo-Mendez, G., Dimitrova, V., Matsuda, N., & Santos, O. C. (Eds.), Artificial Intelligence in Education: Posters and late breaking results, workshops and tutorials, industry and innovation tracks, practitioners, doctoral consorium and blue sky, 24th international conference, AIED 2023, Tokyo, Japan, July 3–7, 2023, proceedings (pp. 497–503). Springer Nature. https://doi.org/10.1007/978-3-031-36336-8_77

Andres, J. A. L., Hutt, S., Ocumpaugh, J., Baker, R. S., Nasiar, N., & Porter, C. (2022). How anxiety affects affect: A quantitative ethnographic investigation using affect detectors and data-targeted interviews. In Wasson, B., & Zörgő, S. (Eds.), Advances in Quantitative Ethnography: Third international conference, ICQE 2021, virtual event, November 6–11, 2021, proceedings 3 (pp. 268–283). Springer. https://doi.org/10.1007/978-3-030-93859-8_18

Hutt, S., Baker, R. S., Ocumpaugh, J., Munshi, A., Andres, J. M. A. L., Karumbaiah, S., Slater, S., Biswas, G., Paquette, L., Bosch, N., & van Velsen, M. (2022). Quick Red Fox: An app supporting a new paradigm in qualitative research on AIED for STEM. In Ouyang, F., Jiao, P., McLaren, B. M., & Alavi, A. H. (Eds.), Artificial intelligence in STEM education: The paradigmatic shifts in research, education, and technology (pp. 319–332). CRC Press.

Ocumpaugh, J. (2015). Baker Rodrigo Ocumpaugh monitoring protocol (BROMP) 2.0 technical and training manual. Teachers College, Columbia University and Ateneo Laboratory for the Learning Sciences.

Ocumpaugh, J., Baker, R., Gowda, S., Heffernan, N., & Heffernan, C. (2014). Population validity for educational data mining models: A case study in affect detection. British Journal of Educational Technology, 45(3), 487–501. https://doi.org/10.1111/bjet.12156

Baker, R. S., Gowda, S. M., Wixon, M., Kalka, J., Wagner, A. Z., Salvi, A., Aleven, V., Kusbit, G. W., Ocumpaugh, J., & Rossi, L. (2012). Towards sensor-free affect detection in cognitive tutor algebra. In Yacef, K., Zaïane, O., Hershkovitz, A., Yudelson, M., & Stamper, J. (Eds.), Proceedings of the 5th International Conference on Educational Data Mining (pp. 126–133). International Educational Data Mining Society.