|Presenting Helpers in MOOCs
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.
|experimental design, statistical analysis, ANOVA, MOOCs, learning science|
|Python Processing MOOC Logfiles
Logfile processing was necessary in order to do the analysis from the Presenting Helpers in MOOCs experiment. To clean the data and prepare it for analysis in external programs (like JMP or SPSS), I learned some Python. 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.
|software engineering, log analysis, LDA, pandas, Python|
|Up/Downvoting and Targeted Email Prompts in a SPOC
Inspired by earlier research results showing that up/downvoting might have a negative effect on help seeking, and that it's possible to alleviate these negative effects, 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.
|experimental design, statistical analysis, learning science, software engineering, log analysis, LDA, pandas, Python|
|Social Role and Social Presence of Pedagogical Robots for Help Seeking|
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.
|experimental design, statistical analysis, ANCOVA, robots, learning science|
|Posting to a Social Network for Maximum Community Response|
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.
|machine learning, statistical analysis, linear regression, software engineering, social networks, HCI, LDA, Java, C#|
|Operationalizing Sociolinguistics for Insights into Social Positioning|
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.
|linguistic analysis, statistical analysis, discourse analysis, ANCOVA, learning science, HCI|
|Infrastructure for Randomly Assigning Participants to Experimental Conditions & Pairs|
For a field experiment in a classroom I needed to assign participants to one of three conditions, and assign them to one of three types of pairs (homogenousx2, heterogeneous) based on their self-reported self-efficacy. My Java condition assigner computed each student's self-efficacy, determined the median (to create "high" and "low" self-efficacy categorizations), created pairs, and evenly assigned types of pairs to one of three conditions.
|software engineering, experimental design, Java|
|Accountable Talk Lego Comic|
Part of performing field experiments in real classrooms requires developing learning materials. I created and authored an engaging comic for 9th grade biology students to learn about Accountable Talk discussion moves for a field experiment.
|graphic design, learning science|
|Co-organizing Opportunities for Undergraduate Research in Computer Science Conference|
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.
|event organization, service|
|Arduino for HCI in the Physical World|
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.
|software engineering, hardware engineering, robots, Processing|
|Tracing Images in Adobe Illustrator for Custom Clip Art and Research Graphics|
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 Through Textiles|
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.
|spatial reasoning, textiles|
|Batman Virtual Pet|