Our work on building learning analytics dashboards is described in this paper:
Bassen, J., Howley, I., Fast, E., Mitchell, J., Thille, C. (2018). OARS: exploring instructor analytics for online learning. Proceedings of the ACM Conference on Learning at Scale.
Students in Massive Open Online Courses often do not receive the help they need from their course discussion boards. A social recommendation algorithm can select appropriate helpers for a student's question, but how do we present these helpers in such a way as to encourage help seeking? I answer this question by applying Expectancy Value Theory in this field experiment.
Logfile processing was necessary in order to do the analysis from the Presenting Helpers in MOOCs experiment. Using Python and Gensim, I applied LDA to automatically assign topics to message board posts. I also designed a Python PANDAS script for descriptive statistics and plotting, as well as one and two way Analysis of Variance and Interaction analysis and graphs.
Inspired by earlier research results showing that up/downvoting might have a negative effect on help seeking, we designed an experiment in a Small Private Online Course (SPOC) to examine up/downvoting's effect in a more traditional forum setting, and how targeted email prompts may be able to mitigate the potential negative effects.
While one-on-one human tutors are considered the gold standard of learning paradigms, why is it easier to seek help from computer tutors? Evaluation anxiety increases with heightened social presence and social role of the tutor, and in this experiment I investigate how social role (teacher or helper) and social presence (human or robot tutor) impacts help seeking in a lab experiment.
In this log analysis, I apply machine learning and text mining techniques to understand what features of members' posts increase community response in Microsoft's interest sharing network, So.cl. I used C# to gather and clean the data and machine learning packages developed in Java.
Linguistic behaviors in group work positions individuals in such a way as to increase or decrease their opportunities to engage and learn in educational settings. In this large body of work I present a multi-dimensional linguistic framework derived from sociolinguistics for identifying social positioning through language choices.
Starting in 2007, Carnegie Mellon's Women@SCS group has hosted the OurCS conference as a way to expose undergraduate women to the breadth of computer science research opportunities available to them. I began as an attendee in 2007 and helped organize the conference in 2011, culminating as a co-organizer of the poster session at the 2013 OurCS conference.
A series of smaller Arduino projects using simple mechanisms, LEDs, button inputs, servo and DC motors, resistors, H-bridges, etc. culminated in a term project using spinning pinwheels to indicate which of a collaborating pair is dominating the conversation.
In this tutorial I describe the basic skills for tracing images in Adobe Illustrator to produce your own custom clip art and diagrams.
Spatial reasoning ability has been connected with success in Science, Technology, Engineering, and Math (STEM), and this relationship has been documented repeatedly. Spatial reasoning is part of the reason for why I became a computer scientist, and I have my suspicions about where I obtained the most practice in this skill: sewing.
A simple "Virtual Pest" Javascript program from 2003 with emotional states and primitive regular expression parsing. ...not to mention some really sweet Microsoft Paint artwork!