Probabilistic machine learning increasingly informs critical decisions in medicine, economics, politics, and beyond. To aid the development of trust in these decisions, we develop a taxonomy delineating where trust in an analysis can break down: (1) in the translation of real-world goals to goals on a particular set of training data, (2) in the…

In real-world settings, vision language models (VLMs) should robustly handle naturalistic, noisy visual content as well as domain-specific language and concepts. For example, K-12 educators using digital learning platforms may need to examine and provide feedback across many images of students' math work. To assess the potential of VLMs to support…

Educational technologies are often developed such that students work on specific social levels (e.g., individual, small group, whole class) at specific times. However, in the reality of the classroom, learning activities are not so cleanly divided, with transitions occurring between social levels for students at different times. To support these…

To investigate the variation in active learning used in college science courses, the authors analyzed 57 comparison studies published in three prominent science education journals. Focusing on three sources of variation--(a) the active learning activities, (b) other pedagogical features, and (c) course structure/design--they found that most…

Background: Implementation strategies used to enhance the implementation of interventions during efficacy and effectiveness studies are rarely reported. Tracking and reporting implementation strategies during these phases has potential to improve future research studies and real-world implementation. We present an exemplar of how this might be…

When researchers code behavior that is undetectable or falls outside of the validated ordinal scale, the resultant outcomes often suffer from informative missingness. Incorrect analysis of such data can lead to biased arguments around efficacy and effectiveness in the context of experimental and intervention research. Here, we detail a new…

Open-ended comprehension questions are a common type of assessment used to evaluate how well students understand one of multiple documents. Our aim is to use natural language processing (NLP) to infer the level and type of inferencing within readers' answers to comprehension questions using linguistic and semantic features within their responses.…

In this study, the authors examined the impact of a vocabulary intervention designed to support vocabulary depth, or the building of semantic networks, in preschool children (n = 30). The authors further investigated the effect of specific instructional strategies on growth in vocabulary depth. The intervention employed shared book reading and…

Small-group discussions in which teachers and students interact with text are common in language arts classrooms. As documented in the extant literature, teacher discourse moves affect how the discussion unfolds and the resulting quality of the talk. What is not present in the literature is a unified lexicon or taxonomy for defining and…

Reading is a pervasive activity in the classroom, as well as in everyday activities: comprehending text and discourse is crucial to success and survival in the modern world. Nonetheless, many students struggle to understand text at even a basic level, and even more fail to construct deep level understandings of content. Particularly for complex…

An NLP algorithm was developed to assess question quality to inform feedback on questions generated by students within iSTART (an intelligent tutoring system that teaches reading strategies). A corpus of 4575 questions was coded using a four-level taxonomy. NLP indices were calculated for each question and machine learning was used to predict…

This study assesses the extent to which machine learning techniques can be used to predict question quality. An algorithm based on textual complexity indices was previously developed to assess question quality to provide feedback on questions generated by students within iSTART (an intelligent tutoring system that teaches reading strategies). In…

Fatigue is common in individuals with a variety of chronic health conditions and can have significant negative effects on quality of life. Although limited in scope, recent work suggests persons with hearing loss may be at increased risk for fatigue, in part due to effortful listening that is exacerbated by their hearing impairment. However, the…

Many students do not meet expected standards of writing performance, despite the need for writing competence in and out of school. As policy instruments, writing content standards have an impact on what is taught and how students perform. This study reports findings from an evaluation of the content of a sample of seven diverse states' current…

The purpose of this article is to describe the Taxonomy of Intervention Intensity, which articulates 7 dimensions for evaluating and building intervention intensity. We explain the Taxonomy's dimensions of intensity. In explaining the Taxonomy, we rely on a case study to illustrate how the Taxonomy can systematize the process by which special…