2018-present
There is a resurgent interest in using locally-grounded, education data that is more “practical”, can more directly inform “improvement”, and are more locally relevant to teachers. The notion of practical analytics captures these data features. Dual challenges arise in utilizing practical analytics. (1) Such data are often expensive and time consuming to process at scale. Teachers either self-process or rely on other institutions (e.g., researchers) to develop data pipelines. And (2) developing usable analytics that validly relate to actionable, improvement decisions is difficult to achieve in practice. These observations motivate our project goals to develop systems to improve the processing of local education data that teachers already collect in school settings using a variety of human-computation and machine learning approaches.