ALLS Lecture Series, 7 November 2016

The ALLS Lecture Series
Monday, 7 November 2016, 3:00 to 4:30, Faura 206

The talks presented during this lecture series represent current research of the Ateneo Laboratory for the Learning Sciences. The November 7 talks will feature brief presentations from PhD Computer Science students who are about to defend their proposals.

Detecting Student Carefulness In An Educational Game For Physics
Michelle Banawan
The creators of the educational game Physics Playground (formerly known as Newton’s Playground) hypothesized that student carefulness could be quantified and identified in-game indicators of carefulness using various behaviors and actions. Carefulness, as defined by the American Heritage Dictionary, means giving close or cautious attention, being thorough and painstaking in action or execution, or being alert, attentive, heedful, or mindful. A careful student is most likely to avoid trivial and/or careless errors. Students who have high self-discipline have been found to be more careful and avoid careless mistakes which can improve student performance. Moreover, carefulness has been found to be a non-cognitive determinant of student performance within an Intelligent Tutoring System (ITS) such that when students are more careful with their tasks, they make fewer mistakes and hence, better educational effectiveness is achieved as students no longer have to receive materials that they already mastered, most especially true for computer-based learning environments. The principal objective of this work is to create a detector for carefulness among students working on Physics Playground. The work begins with the establishment of a baseline quantitative carefulness model based on theoretical models of carefulness as published, but as of yet unvalidated, by the program’s lead researchers and then expands the detector to include other factors that social science theories link with carefulness. This work will provide empirical validation, using the educational data mining framework, to the student carefulness construct to be able to refine and extend it accordingly.

Intelligent Learning System for Automata (ILSA) and Learners’ Achievement Goal Orientation
Cesar Alipiz Tecson
Studying automata theory exposes the students to the theoretical foundation of Computer Science where they learn abstraction, generalization, and reasoning. However, teaching and learning automata is challenging because of the involved abstract notions and mathematical background. It is often regarded to be more affiliated with mathematics than with Computer Science. Many students experience difficulty in understanding the computability concepts. Yet, Computer Science programs everywhere require a course on automata theory and formal languages. . Hence, recent advances in teaching the course focus on the development of different pedagogical tools that can be used to facilitate the learning of automata theory and formal languages. Developments of tutoring systems for automata, like simulators, are continuously advancing. Fundamental efforts on features of automata simulators, based on the open literature, are focused on the following: visual creation, animation, conversion (transformation), interaction, logs generation, and saving and exporting facility. They do not support customization based on learners’ performance in the tutor environment, like provision of individualized learning path and feedback. While these existing tutors facilitate teaching and understanding of the concepts, they do not focus on identifying whether learning is achieved. Another factor that mediates student achievement is goal orientation. This theory suggests that students’ behavior and response to the learning environment are guided by goals. Some students are performance-oriented while others are mastery-oriented. These personal goals interact with the learning environment, sometimes referred to as classroom goals. How these classroom goals align with students’ individual goals can have an effect on both a student’s achievement and learning experience. Hence, the first goal of this study is to augment the capabilities of an automata simulator to characterize Intelligent Tutoring System (ITS) that is driven by a learner model to support individualized learning path, feedback, and support. The second goal of this work is to include features in the ITS that are intended to cater to the different achievement goal orientations of learners. The last goal would be to determine relationships between and among learners’ in-tutor behavior, their goal orientations, and learning.

To register, click here.

Comments are closed.