Using Quantitative Ethnography to Model Critical Data Literacies
In this project, we model how learners connect across their own personal knowledge, practices, values, and epistemologies and those of critical data science as they engage in designed learning experiences. To model and measure this learning, we use Quantitative Ethnography, a methodology that integrates qualitative and quantitative analyses. Through quantitative ethnography, the power of computation and the power of human interpretation are leveraged to reveal meaningful results about the process of learning. Specifically, we use automated coding methods and Epistemic Network Analysis to model developmental trajectories of learners’ data science knowledge and practices by measuring the co-occurrences of these elements and modeling their relationships over time.
Arastoopour Irgens, G., Vega, Hazel, Adisa, Ibrahim, & Bailey, C. Characterizing children’s conceptual knowledge and computational practices in a critical machine learning educational program. International Journal of Child-Computer Interaction. 34(Dec).
Arastoopour Irgens G. & Thompson, J. (2020). “Would You Rather Have it be Accurate or Diverse?” How Male Middle-School Students Make Sense of Algorithm Bias and Racial/Gender Discrimination. In M. Gresalfi and I.S. Horn (Eds.), The Interdisciplinarity of the Learning Sciences, 14th International Conference of the Learning Sciences (ICLS) 2020, Volume 2. (pp. 751 - 752). Nashville, Tennessee: International Society of the Learning Sciences.