We present an empirical study on the use of keystroke analytics to capture and understand how writers manage their time and make inferences on how they allocate their cognitive resources during essay writing. The results suggest three distinct longitudinal patterns of writing process that describe how writers approach an essay task in a writing…

The distributed practice effect suggests that students retain learning content better when they pace their practice over time. The key factors are practice dosage (intensity) and timing (when to practice and how in between). Inspired by the thriving development of image recognition, this study adopts one of the successful techniques,…

Academic achievement of a student in college always has a far-reaching impact on his further development. With the rise of the ubiquitous sensing technology, students' digital footprints in campus can be collected to gain insights into their daily behaviours and predict their academic achievements. In this paper, we propose a framework named…

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…

This paper addresses a key challenge in Educational Data Mining, namely to model student behavioral trajectories in order to provide a means for identifying students most at risk, with the goal of providing supportive interventions. While many forms of data including clickstream data or data from sensors have been used extensively in time series…

Behavioral records collected through course assessments, peer assignments, and programming assignments in Massive Open Online Courses (MOOCs) provide multiple views about a student's study style. Study behavior is correlated with whether or not the student can get a certificate or drop out from a course. It is of predominant importance to identify…

Students' interactions with online tools can provide us with insights into their study and work habits. Prior research has shown that these habits, even as simple as the number of actions or the time spent on online platforms can distinguish between the higher performing students and low-performers. These habits are also often used to predict…

The extraction of student behavior is an important task in educational data mining. A common approach to detect similar behavior patterns is to cluster sequential data. Standard approaches identify clusters at each time step separately and typically show low performance for data that inherently suffer from noise, resulting in temporally…

During the semester break, 36 second-grade students accessed a set of resources and completed a series of online math activities focused on the application of the model method for arithmetic in two contexts 1) addition/subtraction and 2) multiplication/division. The learning environment first modeled and then supported the use of a scripted series…

Our learning-by-teaching environment, Betty's Brain, captures a wealth of data on students' learning interactions as they teach a virtual agent. This paper extends an exploratory data mining methodology for assessing and comparing students' learning behaviors from these interaction traces. The core algorithm employs sequence mining techniques to…

The purpose of this paper is to investigate the relationship between psychological traits and voting behavior. Investigated is the thesis that psychological traits are useful concepts for political scientists as predictors of consistency in behavior. Contending that previous trait theory research has been generally unimpressive, the author…

This paper presents some findings of a detailed analysis of infants' approach behavior in a familiar, naturalistic setting. A total of 26, white, middle-class infant-mother pairs were observed in the home every three weeks during the first year of the child's life. Instances of infant approach to both mother and observer were coded from the…

The study explored the effect of membership in nonpolitical voluntary associations upon the degree of political activity of members. In particular, the authors asked whether or not these effects were found in a relatively uniform pattern across different age groups. On the basis of the reported levels of political discussion in 14 types of…

The richness of the information available in cross-classification tables, compared to the information conveyed in the typical correlation coefficient, is emphasized in this paper. The kinds of information to be found in cross-classification tables are described, and several examples of the use of cross-classification patterns in research are…

Ethnographic research (1) observes human behavior in its natural setting over a substantial period of time, (2) claims that classes of events are better understood through intensive examination of carefully selected particular cases, (3) incorporates as many of the complexities and variables into a setting as possible, and (4) is usually comprised…