Ryan Carlson

Bio: Ryan Carlson is an academic researcher from Carnegie Mellon University. The author has contributed to research in topics: Intelligent tutoring system & Parallel programming model. The author has an hindex of 5, co-authored 6 publications receiving 210 citations.

Social factors that contribute to attrition in MOOCs

Abstract: In this paper, we explore student dropout behavior in a Massively Open Online Course (MOOC). We use a survival model to measure the impact of three social factors that make predictions about attrition along the way for students who have participated in the course discussion forum.

Rudeness and rapport: insults and learning gains in peer tutoring

Abstract: For 20 years, researchers have envisioned artificially intelligent learning companions that evolve with their students as they grow and learn. However, while communication theory suggests that positivity decreases over time in relationships, most tutoring systems designed to build rapport with a student remain adamantly polite, and may therefore inadvertently distance the learner from the agent over time. We present an analysis of high school friends interacting in a peer tutoring environment as a step towards designing agents that sustain long-term pedagogical relationships with learners. We find that tutees and tutors use different language behaviors: tutees express more playfulness and face-threat, while tutors attend more to the task. This face-threat by the tutee is associated with increased learning gains for their tutor. Additionally, a small sample of partners who were strangers learned less than friends, and in these dyads increased face-threat was negatively correlated with learning. Our findings support the idea that learning companions should gradually move towards playful face-threat as they build relationships with their students.

Chestnut: a GPU programming language for non-experts

Abstract: Graphics processing units (GPUs) are powerful devices capable of rapid parallel computation. GPU programming, however, can be quite difficult, limiting its use to experienced programmers and keeping it out of reach of a large number of potential users. We present Chestnut, a domain-specific GPU parallel programming language for parallel multidimensional grid applications. Chestnut is designed to greatly simplify the process of programming on the GPU, making GPU computing accessible to computational scientists who have little or no parallel programming experience, as well as a useful and powerful language for more experienced programmers. In addition, Chestnut has an optional GUI programming interface that makes GPU computing accessible to even novice programmers.Chestnut is intuitive and easy to use, while still powerful in the types of parallelism it can express. The language provides a single simple parallel construct that allows a Chestnut programmer to "think sequentially" in expressing her Chestnut program; the programmer is freed from having to think about parallelization, data layout, GPU to CPU memory transfers, and synchronization. We demonstrate Chestnut's programmability with example solutions to a variety of parallel applications. Performance results from our prototype implementation of Chestnut show that Chestnut applications perform almost as well as hand-written CUDA code for a set of several parallel applications. In addition, Chestnut code is much simpler and much smaller than handwritten CUDA code.

Building a conversational simstudent

Abstract: SimStudent, an intelligent-agent architecture that generates a cognitive model from worked-out examples, currently interacts with human subjects only in a limited capacity. In our application, SimStudent attempts to solve algebra equations, querying the user about the correctness of each step as it solves, and the user explains the step in natural language. Based on that input, SimStudent can choose to ask further questions that prompt the user to think harder about the problem in an attempt to elicit deeper responses. We show how text classification techniques can be used to train models that can distinguish between different categories of student feedback to SimStudent, and how this enables interaction with SimStudent in a pilot study.

Learner Differences and Hint Content

Abstract: Because feedback affects learning, it is central to many educational technologies. We analyze properties of hint feedback in an intelligent tutoring system for high school geometry. First, we examine whether feedback content or feedback sequence is a better predictor of student performance after feedback. Second, we investigate whether linguistic features of hints affect performance. We find that students respond to different hint types differently even after accounting for student proficiency, skill difficulty, and prior practice. We also find that hint content, but not linguistic features affects performance. The findings suggest that tutoring system developers should focus on individual learner differences and feedback content.

Massive Open Online Course Completion Rates Revisited: Assessment, Length and Attrition

Abstract: This analysis is based upon enrolment and completion data collected for a total of 221 Massive Open Online Courses (MOOCs). It extends previously reported work (Jordan, 2014) with an expanded dataset; the original work is extended to include a multiple regression analysis of factors that affect completion rates and analysis of attrition rates during courses. Completion rates (defined as the percentage of enrolled students who completed the course) vary from 0.7% to 52.1%, with a median value of 12.6%. Since their inception, enrolments on MOOCs have fallen while completion rates have increased. Completion rates vary significantly according to course length (longer courses having lower completion rates), start date (more recent courses having higher percentage completion) and assessment type (courses using auto grading only having higher completion rates). For a sub-sample of courses where rates of active use and assessment submission across the course are available, the first and second weeks appear to be critical in achieving student engagement, after which the proportion of active students and those submitting assessments levels out, with less than 3% difference between them.

Sentiment Analysis in MOOC Discussion Forums: What does it tell us?

Abstract: Sentiment analysis is one of the great accomplishments of the last decade in the field of Language Technologies. In this paper, we explore mining collective sentiment from forum posts in a Massive Open Online Course (MOOC) in order to monitor students’ trending opinions towards the course and major course tools, such as lecture and peer-assessment. We observe a correlation between sentiment ratio measured based on daily forum posts and number of students who drop out each day. On a user-level, we evaluate the impact of sentiment on attrition over time. A qualitative analysis clarifies the subtle differences in how these language behaviors are used in practice across three MOOCs. Implications for research and practice are discussed.

Where is Research on Massive Open Online Courses Headed? A Data Analysis of the MOOC Research Initiative

Abstract: This paper reports on the results of an analysis of the research proposals submitted to the MOOC Research Initiative (MRI) funded by the Gates Foundation and administered by Athabasca University. The goal of MRI was to mobilize researchers to engage into critical interrogation of MOOCs. The submissions – 266 in Phase 1, out of which 78 was recommended for resubmission in the extended form in Phase 2, and finally, 28 funded – were analyzed by applying conventional and automated content analysis methods as well as citation network analysis methods. The results revealed the main research themes that could form a framework of the future MOOC research: i) student engagement and learning success, ii) MOOC design and curriculum, iii) self-regulated learning and social learning, iv) social network analysis and networked learning, and v) motivation, attitude and success criteria. The theme of social learning received the greatest interest and had the highest success in attracting funding. The submissions that planned on using learning analytics methods were more successful. The use of mixed methods was by far the most popular. Design-based research methods were also suggested commonly, but the questions about their applicability arose regarding the feasibility to perform multiple iterations in the MOOC context and rather a limited focus on technological support for interventions. The submissions were dominated by the researchers from the field of education (75% of the accepted proposals). Not only was this a possible cause of a complete lack of success of the educational technology innovation theme, but it could be a worrying sign of the fragmentation in the research community and the need to increased efforts towards enhancing interdisciplinarity.