Personalization and choice in learning activities can increase student engagement, satisfaction, and learning gains. But does this effect hold when implemented at scale? The current work explores the effects of personalization and learner's choice in a Climate Science MOOC. We manipulated these by creating two versions of course assignments. Learners who completed the assignments (N=219) received either Generic assignments focusing on global climate issues or Personalized assignments in which learners explored their own regions. Following the manipulation, learners in the Personalization group reported equal understanding of both Global and Local climate issues while learners in the Generic group reported better understanding of global issues and reduced understanding of local issues. Further, personalization did not affect interest or assignment length. We describe opportunities for personalization at scale and discuss their outcomes.

Video-based learning (VBL) is widespread; however, there are numerous challenges when teaching and learning with video. For instructors, creating effective instructional videos takes considerable time and effort. For students, watching videos can be a passive learning activity. Artificial intelligence (AI) has the potential to improve the VBL experience for students and teachers. This half-day workshop will bring together multi-disciplinary researchers and practitioners to collaboratively envision the future of VBL enhanced by AI. This workshop will be comprised of a group discussion followed by a presentation session. The goal of the workshop is to facilitate the cross-pollination of design ideas and critical assessments of AI approaches to VBL.

As videos become increasingly ubiquitous, so is video-based commenting. To contextualize comments, people often reference specific audio/visual content within video. However, the literature falls short of explaining the types of video content people refer to, how they establish references and identify referents, how video characteristics (e.g., genre) impact referencing behaviors, and how references impact social engagement. We present a taxonomy for classifying video references by referent type and temporal specificity. Using our taxonomy, we analyzed 2.5K references with quotations and timestamps collected from public YouTube comments. We found: 1) people reference intervals of video more frequently than time-points, 2) visual entities are referenced more often than sounds, and 3) comments with quotes are more likely to receive replies but not more "likes". We discuss the need for in-situ dereferencing user interfaces, illustrate design concepts for typed referencing features, and provide a dataset for future studies.

While video becomes increasingly prevalent in educational settings, current research has yet to investigate what feedback instructors need regarding their students' engagement and learning despite video technologies being equipped to provide viewing analytics and collect student feedback. In this paper we investigate instructors' requirements from video analytics. We used a Grounded Theory Approach and interviewed 16 instructors who teach using video to determine the advantages for using video in their teaching and the different requirements for analytics and feedback in their existing practice. Based on our analysis of the interviews, we found three categories of information that instructors want to inform their teaching. Instructors are looking to see if their students have watched their videos, how much they understood in those videos, and how useful the videos are to the students. These categories provide the foundations and design implications for instructor-centric educational video analytics interfaces.

Video is an increasingly popular medium for education. Motivated by the problem of video as a one-way medium, this paper investigates the ways in which learners» active interaction with video materials contributes to active learning. In this study, we examine active viewing behaviors, specifically seeking and highlighting within videos, which may suggest greater levels of participation and learning. We deployed a system designed for active viewing to an undergraduate class for a semester. The analysis of online activity traces and interview data provided novel findings on video highlighting behavior in educational contexts.

Video-based learning is most effective when students are engaged with video content; however, the literature has yet to identify students' viewing behaviors and ground them in theory. This paper addresses this need by introducing a framework of active viewing, which is situated in an established model of active learning to describe students' behaviors while learning from video. We conducted a field study with 460 undergraduates in an Applied Science course using a video player designed for active viewing to evaluate how students engage in passive and active video-based learning. The concept of active viewing, and the role of interactive, constructive, active, and passive behaviors in video-based learning, can be implemented in the design and evaluation of video players.

Exploratory learning environments, such as virtual labs, support divergent learning pathways. However, due to their complexity, building computational models of learning is challenging as it is difficult to identify features that (i) are informative with respect to common learning strategies, (ii) abstract similar actions beyond surface differences, and (iii) differentiate groups of learners. In this paper, we present a visualization tool that addresses these challenges by facilitating a novel analytic approach to aid in the knowledge engineering process, focusing on five main capabilities: data-driven hypotheses raising, visualizing behavior over time, easily grouping related actions, contrasting learners' behaviors on these actions, and comparing the behaviors of groups of learners. We apply this analytic approach to better understand how students work with a popular interactive physics virtual lab. By splitting learners by learning gains, we found that productive learners performed more active testing and adapted more quickly to the task at hand by focusing on more relevant testing instruments. Implications for online virtual labs and a broader class of complex learning environments are discussed throughout.

Using aggregated Learning Management System data and course evaluation data from 26 online courses, we evaluated the relationship between measures of online activity, course and assessment structure, and student perceptions of course value. We find relationships between selected dimensions of learner engagement that reflect current constructivist theories of learning. This work demonstrates the potential value of pooled, easily accessible, and anonymous data for high-level inferences regarding design of online courses and the learner experience.