Ateneo Laboratory for the Learning Sciences

An ALLS paper on Augmented Reality was accepted into the upcoming 14th Philippine Computing Science Congress.

The paper entitled “A Mobile Authoring Tool for Augmented Reality Content Generation Using Images as Annotations“ by Jayzon Ty, Marc Ericson Santos, and Ma. Mercedes T. Rodrigo was accepted for oral presentation at the University of Immaculate Conception, Davao City on March 6 to 8, 2014.

Abstract. Augmented Reality is a technology that allows the superimposition of virtual objects onto the real world. Various fields, such as education, medicine, and architecture, started adapting Augmented Reality technology in order to enhance the experience of the users of their systems. However, developing Augmented Reality application and its contents requires a specialized knowledge in computer programming, computer graphics, and software development, which results in only specific people being able to experience Augmented Reality. This paper describes a tool that allows users to produce content for Augmented Reality viewing without the need for specialized knowledge. Furthermore, the tool enables users to create and edit Augmented Reality content on the spot, without the need for a separate application in order to do so.

An ALLS paper was accepted as a journal paper in the Philippine Information Technology Journal.

The paper, entitled “Exploring the use of biometric readings to predict levels of viewer engagement ”, was written by Mary Josephine Co, the high school student who interned at ALLS over the summer, Dr. Didith Rodrigo, and Ivan Jacob Pesigan.

This paper describes the use of biometrics readings, specifically electrodermal activity (EDA) and body temperature, to predict levels of video viewer engagement. Test subjects were asked to watch a series of video clips of different types. We collected their EDA and temperatures while they were watching clips using the Affectiva Q sensor. After each clip, they were asked to rate how engaging they found the video. We then created a linear model that predicted their ratings. Unfortunately, the model was not significant. Subsequent statistical tests on the data showed no significant difference in EDA and temperature among the different levels of engagement. The experiences documented in this paper may serve as experiment design notes for researchers who intend to conduct similar studies.

See full paper →

Two ALLS papers were accepted as journal papers in the Philippine Computing Journal..

The first paper, entitled “Educational data mining: Current research and open questions”, was written by Dr. Didith Rodrigo.

Educational data mining (EDM) refers to the application of statistical and machine learning methods to educational data in order to achieve one of four typical ends: improvement of student models, improvement of subject matter domain structures, studying pedagogical support and refining educational theories. An interdisciplinary field, EDM draws on mathematics, computer sciences, cognitive psychology, education theory, sociology and others. This paper walks the reader through the EDM process and then discusses recent work and open questions in the first three application areas. The paper hopes to introduce young researchers to the field and suggest problems that are still open for investigation.

See full paper →

The second paper, entitled “Exploring the implications of tutor negativity towards a synthetic agent in a learning-by-teaching environment”, was written by Dr. Didith Rodrigo, Regina Ira Antonette Geli, Aaron Ong, Gabriel Jose Vitug, Rex Bringula, Roselle Basa, Cecilio dela Cruz, and Noboru Matsuda.

The researchers examine the implications of negativity in free-form dialogue between student tutors and a synthetic agent in APLUS, a learning-by-teaching online learning environment for Algebra. They attempt to determine whether the negativity of a student tutor’s discourse with the agent indicates that the student is learning more or less of the material and whether the feedback they give the synthetic agent is more or less accurate. They found a weak negative correlation between tutor negativity and learning gains and a strong negative correlation between tutor negativity and accuracy of feedback. Negativity might indeed indicate that student tutors lack mastery of the subject matter and need assistance themselves and detecting negativity during tutoring and providing appropriate assistance might enhance the effectiveness of APLUS and other intelligent tutoring systems.

See full paper →

Two ALLS papers were accepted as journal papers in the Research and Practice in Technology Enhanced Learning Journal.

The first paper, entitled “Challenges to transferring western field research methods to developing world contexts”, was written by Dr. Didith Rodrigo, Jessica Sugay, Jen Agapito, and JR Reyes.

Abstract. Much of the research currently undertaken in the area of intelligent tutoring systems hails from the Western countries. To counteract any bias that this situation produces, to gain greater representation from the rest of the world, and to produce systems and publications that take cultural factors in to account, experts recognize the need for more intercultural evaluations and collaborations. For these collaborations to be successful, though, methods and materials require modification. Field work methodologies used in developed countries have to be nuanced when transferred to developing world contexts. In specific, the paper describes five challenges that researchers must address in the transfer process: technology adoption, school support, infrastructure, student culture, and force majeure.

Download full paper.

The second paper, entitled “An Exploratory Study of Factors Indicative of Affective States of Students using SQL-Tutor”, was written by Thea Guia, Dr. Didith Rodrigo, Michelle Dagami, Jessica Sugay, Francis Macam, and Antonja Mitrovic.

Abstract. The goal of this study was to model the affective states exhibited by students using SQL-Tutor. Based on current literature, we selected academic affective states of interest and measured their incidence among students during an SQL-Tutor session. We observed that students using SQL-Tutor most often exhibited engaged concentration, confusion and boredom; however, none of these states were correlated with student achievement on the final exam. Using D’Mello’s Likelihood metric, L, we found that boredom and frustration tended to persist. We then correlated features extracted from SQL-Tutor log files with these two states’ L values. We found that boredom was negatively correlated with the number of completed/attempted problems, and the number of constraints used. It was positively correlated with the average time needed to complete problems and the average number of attempts. Persistent boredom was negatively correlated with the number of solved problems and positively correlated with the mean time to solve problems and the average number of attempts per solved problem. Frustration was not significantly correlated with any of the factors, but persistent frustration was negatively correlated with the number of constraints used and positively correlated with the average number of attempts per solved problem.

Download full paper.