Shamya Karumbaiah

Shamya Karumbaiah
Carnegie Mellon University | CMU · Human-Computer Interaction Institute

PhD. MS. BE.

About

33
Publications
5,487
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
181
Citations
Introduction
I’m a postdoctoral fellow at Carnegie Mellon University working in the Human-Computer Interaction Institute. My research lies in the intersection of machine learning and learning sciences - promoting student engagement and learning in virtual environments in a fair and equitable manner.

Publications

Publications (33)
Conference Paper
Full-text available
Identifying struggling students in real-time provides a virtual learning environment with an opportunity to intervene meaningfully with supports aimed at improving student learning and engagement. In this paper, we present a detailed analysis of quit prediction modeling in students playing a learning game called Physics Playground. From the interac...
Article
Full-text available
Learning analytics has matured significantly since its early days. The field has rapidly grown in terms of the reputation of its publication venues, established a vibrant community, and has demonstrated an increasing impact on policy and practice. However, the boundaries of the field are still being explored by many researchers in a bid to determin...
Article
Full-text available
Affect dynamics, the study of how affect develops and manifests over time, has become a popular area of research in affective computing for learning. In this paper, we first provide a detailed analysis of prior affect dynamics studies, elaborating both their findings and the contextual and methodological differences between these studies. We then a...
Article
Full-text available
Educational technology (EdTech) designers need to ensure population validity as they attempt to meet the individual needs of all students. EdTech researchers often have access to larger and more diverse samples of student data to test replication across broad demographic contexts as compared to either the small-scale experiments or the larger conve...
Conference Paper
Full-text available
Despite the abundance of data generated from students' activities in virtual learning environments, the use of supervised machine learning in learning analytics is limited by the availability of labeled data, which can be difficult to collect for complex educational constructs. In a previous study, a subfield of machine learning called Active Learn...
Article
Phishing is an increasing threat that causes billions in losses and damage to productivity, trade secrets, and reputations each year. This work explores how security gamification techniques can improve phishing reporting. We contextualized the cognitive evaluation theory (CET) as a kernel theory and constructed a prototype phishing reporting system...
Conference Paper
Full-text available
Considerable amount of research in educational data mining has focused on developing efficient algorithms for Knowledge Tracing (KT). However, in practice, many real-world learning systems used at scale struggle to implement KT capabilities, especially if they weren't originally designed for it. One key challenge is to accurately label existing ite...
Conference Paper
Full-text available
Several emotional theories that inform the design of Virtual Learning Environments (VLEs) categorize affect as either positive or negative. However, the relationship between affect and learning appears to be more complex than that. Despite several empirical investigations in the last fifteen years, including a few that have attempted to complexify...
Article
Full-text available
Artificial Intelligence in Education research for STEM domains has largely been quantitative in nature, but qualitative research offers several advantages as part of a mixed-methods approach. In particular, qualitative research enables researchers to develop deeper phenomenological understanding of how learners represent their activity to themselve...
Conference Paper
Full-text available
Research studies in Educational Data Mining (EDM) often involve several variables related to student learning activities. As such, it may be necessary to run multiple statistical tests simultaneously, thereby leading to the problem of multiple comparisons. The Benjamini-Hochberg (BH) procedure is commonly used in EDM research to address this issue,...
Conference Paper
Full-text available
Several aspects of education, including student learning, testing, school assignments, and teacher evaluations are being impacted by a rapid increase in the use of data-driven and automated algorithmic systems. These systems have now come under scrutiny for their discriminatory behaviors that also closely resemble historical injustices. Yet, the re...
Article
Full-text available
Affect dynamics, the investigation of how student affect transitions from one state to another, is a popular area of research in adaptive learning environments. Recently, the commonly used transition metric L has come under critical examination when applied to data that exclude self-transitions (i.e., transitions where a student remains in the same...
Conference Paper
Full-text available
The study of how affect develops and manifests over time during learning is a popular area of research called affect dynamics. Students' affective states are recorded in authentic settings like classrooms using direct observations by culturally sensitive, trained, and certified coders. A popular approach to studying affect dynamics in the last deca...
Conference Paper
Full-text available
This paper explores how early grade school students’ math performance relates to human ratings of students’ affect, identity, and social awareness based on the content of messages to an online tutoring system avatar. There is an expanding body of research which investigates connections between these features and success in mathematics. This study u...
Conference Paper
Full-text available
Now that the modeling of affective states is beginning to mature, understanding affect dynamics has become an increasingly realistic endeavor. However, the results from empirical studies have not always matched those of theoretical models, which raises questions as to why. In this study, we explore the relationship between affective sequences that...
Article
Full-text available
Research that has examined relationships among mathematics success and student language patterns has typically focused on features of students’ language production such as linguistic sophistication, sentiment, and cognitive measures. There is also a small but growing body of research on how motivational and affective measures derived through survey...
Poster
Full-text available
Sensor-free affect detectors can detect student affect using their activities within intelligent tutoring systems or other online learning environments rather than using sensors. This technology has made affect detection more scalable and less invasive. However, existing detectors are either interpretable but less accurate (e.g., classical algorith...
Conference Paper
Full-text available
Understanding why students quit a level in a learning game could inform the design of appropriate and timely interventions to keep students motivated to persevere. In this paper, we study student quitting behavior in Physics Playground (PP)-a Physics game for secondary school students. We focus on student cognition that can be inferred from their i...
Conference Paper
Full-text available
Previous studies have demonstrated strong links between students' linguistic knowledge, their affective language patterns and their success in math. Other studies have shown that demographic and click-stream variables in online learning environments are important predictors of math success. This study builds on this research in two ways. First, it...
Conference Paper
Full-text available
Demographic information often proves useful for finding subpopulations in educational data. Unfortunately, it is often not collected in the log files of online learning systems, which serve as one of the primary sources of data for the Educational Data Mining community. Recent work has sought to address this issue by investigating school-level diff...
Conference Paper
Full-text available
Affect dynamics, the study of how affect develops and manifests over the course of learning, has become a popular area of research in learning analytics. Despite some shared metrics and research questions, researchers in this area have some differences in how they pre-process the data for analysis [17]. Specifically, researchers differ in how they...
Conference Paper
Full-text available
Reinforcement Learning (RL) has been applied successfully to Intelligent Tutoring Systems (ITSs) in a limited set of well-defined domains such as mathematics and physics. This work is unique in using a large state space and for applying RL to tutoring inter-personal skills. Interpersonal skills are increasingly recognized as critical to both social...
Conference Paper
Full-text available
Education research has explored the role of students' affective states in learning, but some evidence suggests that existing models may not fully capture the meaning or frequency of how students transition between different states. In this study we examine the patterns of educationally-relevant affective states within the context of Betty's Brain,...
Conference Paper
Full-text available
Education research has explored the role of students' affective states in learning, but some evidence suggests that existing models may not fully capture the meaning or frequency of how students transition between different states. In this study we examine the patterns of educationally-relevant affective states within the context of Betty's Brain,...
Conference Paper
Full-text available
A better understanding of the relationship between self-concept in mathematics and fine-grained behavior logs from students' interactions with intelligent tutoring systems (ITSs) could help researchers better understand self-concept, which in turn could lead to improved designs in interventions intended to improve a student's self-concept. Yet, to...
Poster
Full-text available
Teaching computational thinking (CT) in K-12 curricula requires supporting teachers in developing relevant knowledge and skills. In this paper, we present a participatory design approach for in-service teachers' professional development which takes a distributed expertise stance in engaging teachers as co-designers of their learning. Our qualitativ...
Conference Paper
Full-text available
D'Mello and Graesser's (2012) highly-cited model of affect dynamics proposes a sequence of theoretically-grounded transitions between affective states during learning. However, empirical studies in a range of contexts have not produced the predicted results. Several factors may explain this lack of replication, including the demographics of the pop...
Conference Paper
Full-text available
Facial expression trackers output measures for facial action units (AUs), and are increasingly being used in learning technologies. In this paper, we compile patterns of AUs seen in related work as well as use factor analysis to search for categories implicit in our corpus. Although there was some overlap between the factors in our data and previou...
Conference Paper
Full-text available
Digital games have evolved as an engaging medium for learning. This paper studies the interaction between game design and student affective experience. Data from 137 students playing a learning game was analyzed to identify the factors correlating with student frustration. Results suggest that in this well-designed game, difficulty associated with...
Conference Paper
Full-text available
We present results of a randomized controlled study that compared different types of affective messages delivered by pedagogical agents. We used animated characters that were empathic and emphasized the malleability of intelligence and the importance of effort. Results showed significant correlations between students who received more empathic mess...
Conference Paper
Full-text available
Scenario-based tutoring systems influence affective states due to two distinct mechanisms during learning: (1) reactions to performance feedback and (2) responses to the scenario context or events. To explore the role of affect and engagement, a scenario-based ITS was instrumented to support unobtrusive facial affect detection. Results from a sampl...

Network

Cited By