Learning probabilistic classification and prediction models that generate accurate probabilities is essential in many prediction and decision-making tasks in machine learning and data mining. One way to achieve this goal is to post-process the output of classification models to obtain more accurate probabilities. These post-processing methods are…

This article introduces an accessible approach to implementing unmoderated remote research in developmental science -- research in which children and families participate in studies remotely and independently, without directly interacting with researchers. Unmoderated remote research has the potential to strengthen developmental science by: (1)…

In this work we introduce the system for adaptive practice of foundations of mathematics. Adaptivity of the system is primarily provided by selection of suitable tasks, which uses information from a domain model and a student model. The domain model does not use prerequisites but works with splitting skills to more concrete sub-skills. The student…

Purpose: In this paper, the challenging and thorny issue of assessing graduate attributes (GAs) is addressed. An interdisciplinary team at The University of Alberta -- developed a formative model of assessment centered on students and instructor interaction with course content. Design/methodology/approach: The paper starts by laying the…

In the age of big data, interactive data visualizations are becoming increasingly prevalent. The ability to focus on subsets of data is essential for exploring large temporal, geospatial, topical, and network datasets. In order to categorize all parts of data visualizations, various attempts have been made to build frameworks for how to interpret,…

In a wide range of fields, professional practice is being transformed by the increasing influence of digital analytics: the massive volumes of big data, and software algorithms that are collecting, comparing and calculating that data to make predictions and even decisions. Researchers in a number of social sciences have been calling attention to…

Introduction: In the big data age, we have to deal with a tremendous amount of information, which can be collected from various types of sources. For information search systems such as Web search engines or online digital libraries, the collection of documents becomes larger and larger. For some queries, an information search system needs to…

In educational technology and learning sciences, there are multiple uses for a predictive model of whether a student will perform a task correctly or not. For example, an intelligent tutoring system may use such a model to estimate whether or not a student has mastered a skill. We analyze the significance of data recency in making such…

This article analyzes 21 in-depth interviews of engineering and atmospheric science faculty at the University of Illinois Urbana-Champaign (UIUC) to determine faculty data management practices and needs within the context of their research activities. A detailed literature review of previous large-scale and institutional surveys and interviews…

Challenging the "bridge metaphor" theme of this conference, this article contends that current practice-research integration strategies are more like research-to-practice "pipelines." The purpose of this article is to demonstrate the potential of clinical data-mining studies conducted by practitioners, practitioner-oriented PhD…

Researchers use many different metrics for evaluation of performance of student models. The aim of this paper is to provide an overview of commonly used metrics, to discuss properties, advantages, and disadvantages of different metrics, to summarize current practice in educational data mining, and to provide guidance for evaluation of student…

Intelligent tutoring systems are adaptive learning environments designed to support individualized instruction. The adaptation embedded within these systems is often guided by user models that represent one or more aspects of students' domain knowledge, actions, or performance. The proposed project focuses on the development and testing of user…

With the increase in technology in all facets of our lives and work, there is an ever increasing set of expectations that people have regarding information availability, response time, and dependability. While expectations are affected by gender, age, experience, industry, and other factors, people have expectations of technology, and from…

Qualitative data offer advantages to evaluators, including rich information about stakeholders' perspectives and experiences. However, qualitative data analysis is labor-intensive and slow, conflicting with evaluators' needs to provide punctual feedback to their clients. In this method note, we contribute to the literature on rapid evaluation and…

The Exploring Engagement Fund provides risk capital for arts nonprofits to experiment with innovative ideas about how to engage diverse Californians. In order to understand the variety of Californians engaged in arts experiences, this guide is intended to support current and future Fund grantees in collecting participant information. Exploring…