Massive Open Online Courses (MOOCs) which enable large-scale open online learning for massive users have been playing an important role in modern education for both students as well as professionals. To keep users' interest in MOOCs, recommender systems have been studied and deployed to recommend courses or videos that a user might be interested…

Over the years, researchers have studied novice programming behaviors when doing assignments and projects to identify struggling students. Much of these efforts focused on using student programming and interaction features to predict student success at a course level. While these methods are effective at early detection of struggling students in…

Predicting academic performance using trace data from learning management systems is a primary research topic in educational data mining. An important application is the identification of students at risk of failing the course or dropping out. However, most approaches utilise past grades, which are not always available and capture little of the…

A growing subset of the web today is aimed at "teaching" and "explaining" technical concepts with varying degrees of detail and to a broad range of target audiences. Content such as tutorials, blog articles and lecture notes is becoming more prevalent in many technical disciplines and provides up-to-date technical coverage with…

Instructional content designers of online learning platforms are concerned about optimal video design guidelines that ensure course effectiveness, while keeping video production time and costs at reasonable levels. In order to address the concern, we use clickstream data from one Coursera course to analyze the engagement, motivational and…

This paper reports the results from a sensor-free detector of mind wandering during an online reading task. Features consisted of reading behaviors (e.g., reading time) and textual features (e.g., level of difficulty) extracted from self-paced reading log files. Supervised machine learning was applied to two datasets in order to predict if…

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…

In this paper, we propose a visual saliency algorithm for automatically finding the topic transition points in an educational video. First, we propose a method for assigning a saliency score to each word extracted from an educational video. We design several mid-level features that are indicative of visual saliency. The optimal feature combination…