A critical issue in using fine-grained gameplay data to measure learning processes is the development of indicators and the algorithms used to derive such indicators. Successful development--that is, developing traceable, interpretable, and sensitive-to-learning indicators--requires understanding the underlying theory, how the theory is…

Accounting for complex interactions between contextual variables and learners' individual differences in aptitudes and background requires building the means to connect and access learner data at large scales, across time, and in multiple contexts. This paper describes the ASU Learning@Scale (L@S) project to develop a digital learning network…

Many national science frameworks (e.g., Next Generation Science Standards) argue that developing mathematical modeling competencies is critical for students' deep understanding of science. However, science teachers may be unprepared to assess these competencies. We are addressing this need by developing virtual lab performance assessments that…

Consistency of learning behaviors is known to play an important role in learners' engagement in a course and impact their learning outcomes. Despite significant advances in the area of learning analytics (LA) in measuring various self-regulated learning behaviors, using LA to measure consistency of online course engagement patterns remains largely…

Modern social intelligence includes the ability to watch videos and answer questions about social and theory-of-mind-related content, e.g., for a scene in "Harry Potter," "Is the father really upset about the boys flying the car?" Social visual question answering (social VQA) is emerging as a valuable methodology for studying…

In this paper, we consider a minimalistic and behavioristic view of AIS to enable a standardizable mapping of both the behavior of the system and of the learner. In this model, the "learners" interact with the learning "resources" in a given learning "environment" following preset steps of learning…

Imagine a large randomized controlled trial study of a mathematics educational intervention planned in two large urban districts. District 1 gets a new administrator and drops out. In the meantime, the state test changed, so one of the planned outcome measures is no longer usable. Teacher dropout is high. And, as the analysis is being completed,…

The results of educational research studies are only as accurate as the data used to produce them. Drawing on experiences conducting large-scale efficacy studies of classroom-based algebra interventions for community college and middle school students, I am developing practice-based data cleaning procedures to support scholars in conducting…

How should a wide variety of educational activities be sequenced to maximize student learning? Although some experimental studies have addressed this question, educational data mining methods may be able to evaluate a wider range of possibilities and better handle many simultaneous sequencing constraints. We introduce Sequencing Constraint…

The well-studied Baker et al., affect detectors on boredom, frustration, confusion and engagement concentration with ASSISTments dataset were used to predict state tests scores, college enrollment, and even whether a student majored in a STEM field. In this paper, we present three attempts to improve upon current affect detectors. The first…

We explore in this paper if automated scaffolding delivered via a pedagogical agent within a simulation can help students acquire data collection inquiry skills. Our initial analyses revealed that such scaffolding was effective for helping students who initially did not know two specific skills, designing controlled experiments and testing stated…

The field of learning analytics is rapidly developing techniques for using data captured during online learning. In this article, we develop an additional application: the use of analytics for improving implementation fidelity in a randomized controlled efficacy trial. In an efficacy trial, the goal is to determine whether an innovation has a…

Student models for adaptive systems may not model collaborative learning optimally. Past research has either focused on modeling individual learning or for collaboration, has focused on group dynamics or group processes without predicting learning. In the current paper, we adjust the Additive Factors Model (AFM), a standard logistic regression…

When validating assessment models built with data mining, generalization is typically tested at the student-level, where models are tested on new students. This approach, though, may fail to find cases where model performance suffers if other aspects of those cases relevant to prediction are not well represented. We explore this here by testing if…

In this paper we explored whether engaging in two inquiry skills associated with data collection, designing controlled experiments and testing stated hypotheses, within microworlds for one physical science domain (density) impacted the acquisition of inquiry skills in another domain (phase change). To do so, we leveraged educational data mining…