Recent Publications and Awards
Woolf, B.P., Arroyo, I., Muldner, K., Burleson, W., Cooper, D., Dolan, R., Christopherson, R.M., (submitted) The Effect of Motivational Learning Companions on Low-Achieving Students and Students with Learning Disabilities, submitted to the International Conference on Intelligent Tutoring Systems, 2010, Pittsburgh.
- Abstract. We report the results of a randomized controlled evaluation of the effectiveness of pedagogical agents as providers of affective feedback. These digital learning companions were embedded in an intelligent tutoring system for mathematics, and were used by approximately one hundred high school students in two public high schools. Students in the control group did not receive the learning companions. Results indicate that low-achieving students—one third of whom have learning disabilities—had higher affective needs than their higher-achieving peers, as they initially considered math problem-solving more frustrating, less exciting, and felt more anxious when solving math problems. However, after they interacted with the affective pedagogical agents, low-achieving students improved their affective outcomes, e.g., reported reduced frustration and anxiety.
Cooper, D., Muldner, K., Arroyo, I., Woolf, B.P., Burleson, W., Dolan, R., Ranking Feature Sets for Emotion Models used in Classroom Based Intelligent Tutoring Systems, submitted to the International Conference on Uesr Modeling and Adaptive Presentation, 2010, Hawaii.
- Abstract. Recent progress has been made in using sensors with Intelligent Tutoring Systems in classrooms in order to predict the affective state of students users. If tutors were able to interpret sensor data with new students based on past experience, rather than having to be individually trained, then tutor developers could evaluate various methods of adapting to each student's affective state using consistent predictions. Our classifiers for emotion have predicted student emotions with an accuracy between 78% and 87%. However, it is still unclear which sensors are best, and the educational technology community needs to know this to develop better than baseline classifiers, e.g. ones that use only frequency of emotional occurrence to predict affective state. This paper suggests a method for comparing classifiers using different sensors as well as a method for validating the classifiers on a novel population. This involves training our classifiers on data collected in the Fall of 2008 and testing them on data collected in the Spring of 2009. Results of the comparison show that the classifiers for some affective states are significantly better than the baseline, and a validation study found that not all classifier rankings generalize to new settings. The analysis suggests that though there is some benefit gained from simple linear classifiers, more advanced methods are needed for better results.
Arroyo, I., Woolf, B.P., Burleson, W., Muldner, K., Tai, M., Cooper, D., Royer, J.M., (submitted) Gender Matters: The Impact of Animated Agents on Students’ Affect, Behavior and Learning, submitted to the International Conference on User Modeling and Adaptive Presentation, 2010, Hawaii.
- Abstract. We report on the reactions of males and females to the presence of animated agents that provided emotional or motivational feedback. One hundred (100) high school students used agents embedded in an Intelligent Tutoring System for Mathematics and randomized controlled evaluations compared students with and without learning companions. Positive results indicate that affective pedagogical agents can improve affective outcomes of students in general and particularly so for female students, who reported being more frustrated and less confident while solving math problems prior to using the tutoring system. We discuss issues of incorporating gender into user models and of generating responses tailored to gender.
Arroyo, I., Woolf, B.P., Royer, J.M., Tai, M., English, S., (Submitted) Improving Learning Through Intelligent Tutoring and Basic Skills Training, submitted to the International Conference on Intelligent Tutoring Systems, 2010, Pittsburgh.
- Abstract. This research asks how we can support meaningful and successful participation in mathematics for all students. Certain groups of students (African-American, Hispanics, women, and particularly women of color) score significantly lower in standardized achievement tests and these scores have significant impact in a student’s future. We studied the effectiveness of a math fact fluency tool integrated with an intelligent tutor as a means to improve student performance in such tests. Efficacy data shows improved student performance on tests and positive impact on learning. The study evaluated the impact of Math Facts Retrieval Training (MFRT) on 250 middle school students and analyzed the main effects of the training by itself and also as a supplement to the Wayang Tutoring System on easy and hard items of the test. We also report on interaction effects of MFRT with student gender.
Dragon, T., Floryan, M., Woolf, B.P., Murray, T., (submitted) Recognizing Dialogue Content in Student Collaborative Conversation, submitted to the International Conference on Intelligent Tutoring Systems, 2010, Pittsburgh.
- Abstract. This paper describes efforts to both promote and recognize student dialogue in free-entry text discussion within an inquiry-learning environment. First, we discuss collaborative tools that enable students to work together and how these tools can potentially focus student effort on subject matter. We then show how our tutor uses an Expert Knowledge Base to recognize (with 88% success rate) when students are discussing content relevant to the problem and can correctly link (with 70% success) that content with an actual topic. Subsets of the data indicate that even better results are possible. This research provides solid support for the concept of using a knowledge base to recognize content in free-entry text discussion, and the paper concludes by demonstrating how this content recognition can be used to support students engaged in problem-solving activities.
Arroyo, I., Cooper, D., Burleson, W., Woolf, B.P., Cooper, D., (In Press) Bayesian Networks and Linear Regression Models of Students’ Goals, Moods and Emotions, Chapter for Handbook of Educational Data Mining, Series: Chapman & Hall/CRC. Editors Romero Cristobal, Ventura Sebastian, Rita Viola Silvia, Pechenizkiy Mykola, Baker Ryan,
- Abstract If computers are to interact naturally with humans, they should recognize students’ affect and express social competencies. Research has shown that learning is enhanced when empathy or support is provided and that improved personal relationships between teachers and students leads to increased student motivation. Therefore, if tutoring systems can embed affective support for students they should be more effective. However, previous research has tended to privilege the cognitive over the affective and to view learning as information processing, marginalizing or ignoring affect. This chapter describes two data-driven approaches toward the automatic prediction of affective variables by creating models from students’ past behavior (log-data). The first case study shows the methodology and accuracy of an empirical model that helps predict students’ general attitudes, goals and perceptions of the software and the second develops empirical models for predicting students’ fluctuating emotions while using the system. The vision is to use these models to predict students’ learning and positive attitudes in real time. Special emphasis is placed in this chapter on understanding and inspecting these models, to understand how students express their emotions, attitudes, goals and perceptions while using a tutoring system.
- Cooper, David, Arroyo,Ivon, Woolf, Beverly Sensing Student Emotion and Responding Appropriatly (Best Interactive Presentation AIED 2009)
- Ivon Arroyo, David G. Cooper, Winslow Burleson, Beverly Park Woolf, Kasia Muldner and Robert Christopherson Emotoin Sensors Go To School (Best Paper AIED 2009)
- Arroyo, I., Woolf, B.P., Royer, J.M., Tai, M. (2009) Affective Gendered Learning Companion, International Conference on Artificial Intelligence and Education, Brighton, England, IOS Press
- Ivon ARROYO, David G. COOPER, Winslow BURLESON Beverly Park WOOLF, Kasia MULDNER, Robert CHRISTOPHERSON (2009) Emotion Sensors Go To School
- Toby Dragon, Ivon Arroyo, Beverly P. Woolf, Winslow Burleson, Rana el Kaliouby, Hoda Eydgahi (2008) Viewing Student Affect and Learning through Classroom Observation and Physical Sensors
- Beverly Woolf, Winslow Burleson, Ivon Arroyo, Toby Dragon, David Cooper, Rosalind Picard (2008) Affect-Aware Tutors: Recognizing and Responding to Student Affect
- Ivon ARROYO, Kimberly FERGUSON, Jeff JOHNS, Toby DRAGON, Hasmik MEHERANIAN, Don FISHER, Andrew BARTO, Sridhar MAHADEVAN, Beverly P. WOOLF(2007) Repairing Disengagement With Non-Invasive Interventions
- Kimberly Ferguson, Ivon Arroyo, Sridhar Mahadevan, Beverly Woolf, Andy Barto (2006) Improving Intelligent Tutoring Systems: Using
Expectation Maximization To Learn Student Skill Levels - Ivon ARROYO, Beverly Park WOOLF Inferring learning and attitudes from a Bayesian Network of log file data
- Ivon ARROYO, Kasia MULDNER, Winslow BURLESON, Beverly WOOLF, and David COOPER Designing Affective Support to Foster Learning, Motivation and Attribution
- David G. Cooper, Ivon Arroyo, Beverly Park Woolf, Kasia Muldner, Winslow Burleson, and Robert Christopherson, Sensors Model Student Self Concept in the Classroom
