The significance of ethics in data science research has attracted considerable attention in recent years. While there is widespread agreement on the importance of teaching ethics within computing contexts, there is no clear method for its implementation and assessment. Studies focusing on methods for integrating ethics into data science courses…

Parent rating scales are used at increasing rates across disciplines to track child development and determine diagnoses/needs. This study explored relationships among parental stress and the validity of parents' ratings of their child's behaviors. Participants include children who were referred for assessment of behavioral, social-emotional, and…

This paper presents an analysis of learning analytics practices which aimed to achieve personalised learning. It addresses the need for a systematic analysis of the increasing amount of practices of learning analytics which are targeted at personalised learning. The paper summarises and highlights the characteristics and trends in relevant…

Despite the increasing interest in data science education in the world, its teaching is not included in the curricula (junior secondary) and there is little information about it. Google Trends is discussed as a tool and database in school data science. Also, in different subjects, students were able to create and interpret graphs using this tool.…

As data are 'numbers with context' (Cobb & Moore, 1997), contextual knowledge plays a prominent role in dealing with statistics. While insights about a specific context can further the depth of interpreting and evaluating outcomes of data analysis, research shows how it can also hinder relying on data especially if results differ from…

Protection of student privacy is critical for scaling up the use of learning analytics (LA) in education. Poorly implemented frameworks for privacy protection may negatively impact LA outcomes and undermine trust in the discipline. To design and implement models and tools for privacy protection, we need to understand privacy itself. To develop…

Drawing on the data collected via a European funded project with eleven higher education partners, the article proposes a five-stage working model which can be adopted in and adapted to different institutional contexts so as to shift perceptions, strengthen engagement and channel commitment with a view to developing the desired quality culture.…

We contribute to research on social inequalities in educational attainment by examining the role of institutional contexts for students' study abroad (SA) intent and participation. To do so, we extend the individual-level rational choice model predicting SA intent and participation depending on students' socioeconomic status (SES) into a…

Realist evaluation (RE) is a research design increasingly used in program evaluation, that aims to explore and understand the influence of context and underlying mechanisms on intervention or program outcomes. Several methodological challenges, however, are associated with this approach. This article summarizes RE key principles and examines some…

This article introduces researchers in the science concerned with developing and studying research methods, measurement, and evaluation (RMME) to the educational data mining (EDM) community. It assumes that the audience is familiar with traditional priorities of statistical analyses, such as accurately estimating model parameters and inferences…

The What Works Clearinghouse (WWC) at the Institute of Education Sciences reviews rigorous research on educational practices, policies, programs, and products with a goal of identifying 'what works' and making that information accessible to the public. One critique of the WWC is the need to more closely examine 'what works' for whom, in which…

The purpose of this paper is to analyze various dimensions for measurement of human behavior. Human behaviour is complex. Behaviors, emotions, cognitions, and attitudes can rarely be described in terms of one or two variables. It is multimodal in nature. Furthermore, the traits, modalities and dimensions cannot be measured directly, but must be…

Increasingly, student work is being conducted on computers and online, producing vast amounts of learning-related data. The educational analytics fields have produced many insights about learning based solely on tutoring systems' automatically logged data, or "log data." But log data leave out important contextual information about the…

The poor level of engagement in learning mathematics is primarily caused by ineffective methods of instruction. Therefore, the purpose of this study was to investigate how context-based problem-posing and solving instructional approaches influence students' engagement in learning data handling using a concurrent embedded quasi-experimental…

We introduce DeepPerfEmb, or DPE, a new deep-learning model that captures dense representations of students' online behaviour and meta-data about students and educational content. The model uses these representations to predict student performance. We evaluate DPE on standard datasets from the literature, showing superior performance to the…