We are thrilled to announce that D2D was recently funded to use cutting edge machine learning tools to investigate how student outcomes from engaging in research vary across the many different contexts that D2D is taught in. For example, members in our network teach D2D in first-quarter freshman classes and senior-level capstone classes; D2D is integrated into organic chemistry labs and in molecular genetics courses, and everything in between! How does experiencing this research project in these different environments impact student outcomes that we care about, like changes in psychosocial attributes that are associated with STEM persistence? We hypothesize that our data set can be explored with machine learning to uncover meaningful trends that our human eyes might miss. If successful, we aim to make these methods super accessible to non-experts such that other educators can both learn from our findings and the tools we build in this project! Please don't hesitate to reach out with questions (awvater@ucdavis.edu). Grant abstract can be found here.