Evelyn Yarzebinski

Studying the Effect of Tutor Learning Using a Teachable Agent that Asks the Student Tutor for Explanations

We have built Sim Student, a computational model of learning, and applied it as a peer learner that allows students to learn by teaching. Using Sim Student, we study the effect of tutor learning. In this paper, we discuss an empirical classroom study where we evaluated whether asking students to provide explanations for their tutoring activities facilitates tutor learning - the self-explanation effect for tutor learning. The results showed that students in the self-explanation condition displayed the same amount of learning gain as students in the non-self-explanation condition, but with a significantly smaller number of problems tutored (during the same time). The study also showed an apparent increase in effectiveness relative to a prior study, which is arguably due to improvement of the system based on the iterative system-engineering effort.

Learning by teaching SimStudent: an initial classroom baseline study comparing with cognitive tutor

This paper describes an application of a machine-learning agent, SimStudent, as a teachable peer learner that allows a student to learn by teaching. SimStudent has been integrated into APLUS (Artificial Peer Learning environment Using SimStudent), an on-line game-like learning environment. The first classroom study was conducted in local public high schools to test the effectiveness of APLUS for learning linear algebra equations. In the study, learning by teaching (i.e., APLUS) was compared with learning by tutored-problem solving (i.e., Cognitive Tutor). The results show that the prior knowledge has a strong influence on tutor learning - for students with insufficient training on the target problems, learning by teaching may have limited benefits compared to learning by tutored problem solving. It was also found that students often use inappropriate problems to tutor SimStudent that did not effectively facilitate the tutor learning.

The Effects of Culturally Congruent Educational Technologies on Student Achievement

Dialectal differences are one explanation for the systematically reduced test scores of children of color compared to their Euro-American peers. In this work, we explore the relationship between academic performance and dialect differences exhibited in a learning environment by assessing 3rd grade students’ science performance after interacting with a “distant peer” technology that employed one of three dialect use patterns. We found that our participants, all native speakers of African American Vernacular English (AAVE), demonstrated the strongest science performance when the technology used AAVE features consistently throughout the interaction. These results call for a re-examination of the cultural assumptions underlying the design of educational technologies, with a specific emphasis on the way in which we present information to culturally-underrepresented groups.

Browser Language Preferences as a Metric for Identifying ESL Speakers in MOOCs

Open access and low cost make Massively Open Online Courses (MOOCs) an attractive learning platform for students all over the world. However, the majority of MOOCs are deployed in English, which can pose an accessibility problem for students with English as a Second Language (ESL). In order to design appropriate interventions for ESL speakers, it is important to correctly identify these students using a method that is scalable to the high number of MOOC enrollees. Our findings suggest that a new metric, browser language preference, may be better than the commonly-used IP address for inferring whether or not a student is ESL.

Studying the Effect of a Competitive Game Show in a Learning by Teaching Environment

In this paper we investigate how competition among tutees in the context of learning by teaching affects tutors’ engagement as well as tutor learning. We conducted this investigation by incorporating a competitive Game Show feature into an online learning environment where students learn to solve algebraic equations by teaching a synthetic peer, called SimStudent. In the Game Show, pairs of SimStudents trained by students beforehand competed against each other by solving challenging problems to attain higher ratings. The results of a classroom study with 141 7th through 9th grade students showed the following: (1) Students improved their proficiency to solve equations after teaching SimStudent, but there was no observed improvement in their conceptual understanding. (2) Overall, the competitive Game Show promoted students’ extrinsic and intrinsic motivations—when the competitive Game Show was available, students’ engagement in tutoring (intrinsic motivation) was increased; students who arguably had a higher desire to win strategically selected opponents with lower proficiency for an easy win (extrinsic motivation). (3) The availability of the competitive Game Show did not affect tutor learning; there was no notable correlation between students’ motivation (intrinsic or extrinsic) and tutor learning. Based on these findings, we propose design improvements to increase tutor learning.

Understanding Students’ Use of Code-Switching in a Learning by Teaching Technology

Personalized learning systems have shown significant learning gains when used in formal classroom teaching. Systems that use pedagogical agents for teaching have become popular, but typically their design does not account for multilingual classrooms. We investigated one such system in classrooms in the Philippines to see if and how students used code-switching when providing explanations of algebra problem solving. We found significant amounts of code-switching and explored cognitive and social factors such as explanation quality and affective valence that serve as evidence for code-switching motivations and effects. These results uncover complex social and cognitive interactions that occur during learning interactions with a virtual peer, and call for more affordances to support multilingual students.

Cognitive Tutor Use in Chile: Understanding Classroom and Lab Culture

As technological capabilities flourish around the world, intelligent tutoring systems are being deployed globally to provide learners with access to quality educational interventions. Such systems have been widely studied in in-vivo deployments in the Western world, allowing for the development of sophisticated models of behavior within the system that have been shown to accurately represent and support learning. Yet, these models have recently been shown not to reliably transfer across cultures. In this paper, we report on our quantitative field observations of student behaviors in two different schools (urban and rural) and two different learning contexts (ITS lab and the math classroom) in central Chile. We observed that students across schools exhibit different behaviors in the ITS lab vs the classroom, especially with respect to student interaction, movement, and on-task behavior, yet these students behave altogether differently from previously observed U.S. student populations. These results have implications for future modeling efforts of help-seeking and engagement in advanced learning technologies in new global contexts.

Going Global: Understanding English Language Learners’ Student Motivation in English-Language MOOCs

Massive Open Online Courses (MOOCs) offer high quality, free courses to anyone with an Internet connection. However, these courses may be relatively inaccessible to the large global population of students who are English Language Learners (ELLs). Current efforts to understand student motivation in MOOCs do not take into account the specific needs of ELL students. Through interviews with 12 ELL online students, and a survey with 20,084 ELL respondents, we investigate ELL students’ motivations for taking online courses. We show that ELL students’ motivations are highly socialized strategies for achieving long-term goals of economic, social, and geographic mobility. Although research studies show that ELLs interact sparingly with other students in MOOCs, we present evidence that they have unmet needs for interaction, and discuss how student interaction systems in MOOCs can better address these needs. Finally, we show evidence that ELLs deliberately use English MOOCs to improve their language skills, even when the content is not language-related. This implies that meeting ELL students’ needs and access to MOOCs involves translating MOOCs to their local languages, but also providing language support in English-language MOOCs.

How Do English Language Learners Interact with Different Content Types in MOOC Videos

English Language Learners (ELLs) are a substantial portion of the students who enroll in MOOCs. In order to fulfill the promise of MOOCs – i.e., making higher education accessible to everyone with an internet connection – appropriate interventions should be offered to students who struggle with the language of course content. Through the analysis of clickstream log data gathered from two MOOC courses deployed on Coursera, Introduction to Psychology and Statistical Thermodynamics, we show that compared to native English speakers, ELL students have distinct behavioral patterns in how they engage with MOOC content including increased interaction with content that contains text, increased seeking away from content without visual support, and decreased video play rates. These patterns are expressed differently in response to different types of course content and domains. Our findings not only suggest more fine-grained methods for automatically identifying students who need language interventions, but also have further implications for the design of language support interventions and MOOC videos.

Characterizing ELL Students' Behavior During MOOC Videos Using Content Type

Making MOOCs accessible to English Language Learners (ELLs) requires that students understand the language of instruction, and that instructional strategies address their unique learning challenges. Through the analysis of clickstream log data gathered from two MOOC courses deployed on Coursera, Introduction to Psychology and Statistical Thermodynamics, we show that ELL students exhibit distinct struggle behaviors in video portions without visual aids e.g., narrations without slides. Our findings challenge widely accepted multimedia design principles such as the split attention effect, provide insights into designing MOOC videos, and emphasize the need for adaptivity to increase MOOC access for ELLs.