Vive Kumar

Assessing process in CSCL: An ontological approach

Educational technology innovations enable students to collaborate in online educational tasks, across individual, institutional, and national boundaries. However, online interactions across these boundaries are seldom transparent to each other. As a result, students are not motivated to share their best learning practices. Also, there is no singular basis on which one can compare learning practices of multiple students. In addressing these problems, we offer a solution that encourages students to record and share their learning interactions using our ontology-oriented theory-centric software tool. In doing so, students not only observe the products of their learning but also the process of how they learnt. These unique and computationally formal recordings of learning interactions not only allow educators to observe how learners learn, but also provide opportunities for learners to reflect on their understanding of meta-cognitive processes that they employed or neglected in their learning. Further, these recordings feed our software system to autonomously analyze students learning behaviour and to actively promote self- and co-regulation among learners. This article presents the need for such a system, the architecture of the system, and concludes with key experimental observations from software prototypes.

Rating learning object quality with distributed Bayesian belief networks: the why and the how

As differing evaluation instruments are adopted in learning object repositories serving specialized communities of users, what methods can be adopted for translating evaluative data across instruments in order to share this data among different repositories? How can evaluation from different reviewers be properly integrated? How can explicit and implicit measures of preference and quality be combined to recommend objects to users? In this research we studied the application of Bayesian belief network (BBN) to the problem of insufficient and incomplete reviews during learning objects evaluation, and translating and integrating data among different quality evaluation instruments and measures. Two BBNs were constructed to probabilistically model relationships among different roles of reviewers as well as among items of different evaluation measurements. Initial testing using hypothetic data showed that the model was able to make potentially useful inferences about different dimensions of learning object quality. We further extend our model over geographic distances assuming that the reviewers would be distributed and that each reviewer would change the underlying BBN network (to a certain extent) to suit his/her expertise. We highlight issues that arise due to a highly distributed and personalized BBN network that can be used to make valid inferences about learning object quality.

Effects of self-regulated learning in programming

Effects of self-regulated learning (SRL) have been investigated in a variety of contexts. In this research, we explore advanced learning technologies based on the information processing model of SRL in the context of structured programming. We conducted an experiment to study ways to enhance the use of programmers working memory, to develop tactics to carry out task level activities during programming, and to learn how to program more effectively. The results of the experiment indicate that programmers who received SRL-based treatment outperformed programmers who did not receive the treatment. We argue that the infusion of SRL-based technological interfaces would have a positive influence on the performances in programming.

Teaching programming through games

Research has discovered preliminary evidence that games are effective in motivating students to learn. Beyond being used solely as a motivational tool, educational games are understood to integrate educational content extrinsically and/or intrinsically. We extend this to a broader +taxonomy of game/curriculum integration and develop and discuss an example which applies this approach to teaching programming skills.

Assisting online helpers

Online help for learners can be classified along many dimensions including, passive to active, canned to knowledge-based, generic to task specific, collaborative to autonomous, and centralised to distributed. Across these dimensions, software tools that support online help employ techniques such as dialogue analysis, user modelling, context-specific inferencing, collaborative communication, and task-specific pedagogies. In this paper, we present a framework that seamlessly integrates help tools and techniques to facilitate three-way dialogues between a person who requires help (learner), a person who provides help (helper), and the online assistant help system (Helpers Assistant) that mediates between the learner and the helper. The focus of the framework is to provide personalised and context-specific help. We present a case for the need for such online assistants, review some of the key techniques employed in help systems, discuss the salient features of the framework in assisting online helpers, and describe the design and analysis of a study investigating the effectiveness of Helpers Assistant. The novelty in this approach lies particularly in the fact that the focus of the assistant is helping the helper and not the learner directly.

Innovations in e-Pedagogy

E-learning aims to enrich learning by blending traditional and innovative learning models; conceptualizing courseware in multiple media; standardizing interoperable content representation; personalizing learning experiences to custom learning devices; integrating administrative functionalities with other academic units; and not the least, ensuring expected quality of learning. An underlying theme that pervades all of these technological, sociological, and cognitive aspirations is e-Pedagogy. This tutorial focus on advances in e-pedagogy, with real- world examples from a number of toolkits. The toolkits include a metacognition-enabled study environment (gStudy), a theory-centric discussion tool (TextWeaver), a knowledge engineering toolkit for instructors (Semnet+gChat), and a real-time ontological knowledge dissemination environment (MI-EDNA & MICE).

Towards Mixed-Initiative Interactions in Novice Programming

As part of their education, Computer Science students develop hundreds of computer programs and receive only summative feedback on the end results of their program designs and code. We demonstrate a need for a formative feedback mixed-initiative system able to reflect on the progress of students and identify opportunities to prompt students when they venture into poor programming styles

A Theory-Centric Real-Time Assessment of Programming

The instructional design of many introductory programming courses in computer science do not include introduction to programming styles. In most cases, these courses offer an introduction to syntax constructs of the programming language as a means to translate problem statements to program design and how to handle a compiler. Notably, students are offered only summative feedback on their code. Skill development in programming is an evolutionary process. Skilled programmers exhibit expertise in contextualizing language constructs, design issues, efficient debugging, standards requirements, best practices, coding resources, and ability to successfully collaborate with colleagues. We propose a pedagogical mechanism to guide students through a formative process and present empirical evidence in support of a real-time and theory-centric assessment and feedback of styles of programming.

Critical Mass in E-Education

Technology innovations by default are designed to be generic - discussion boards, LMS, learning objects, Semantic Web technology, OWL, and SCORM. However, educational artifacts that are created employing these technologies, in most cases, could only be utilized locally within classrooms, within courses, and within institutions. This is so because while employing these generic technologies educators customize the resultant artifacts to suit individual needs. Hence, when being used, the scope of these artifacts are localized to classrooms, courses, or at best institutions. Thus, instances of SCORM-based courses, learning objects, and discussion boards are, in most cases, localized, in spite of their potential to be interoperable. A natural follow up question to ask is, what more can technology innovations do to make their application mainstream in e-education? We can approach this question by associating a ldquocritical massrdquo measure for each recognized educational technology. Once the critical mass is surpassed the corresponding educational technology innovation could be said to be mainstream.

Causal Models for Learning Technology

New statistical methods allow discovery of causal models from observational data in some circumstances. These models permit both probabilistic and causal inference for models of reasonable size. Many domains can benefit from such methods. Educational research does not easily lend itself to experimental investigation. Research in laboratories is artificial while research in authentic environments is complex and difficult to control. The variables are typically hidden and change over the long term, making them challenging and expensive to investigate experimentally. We present an analysis of causal discovery algorithms and their applicability to educational research and learning technology, an engineered causal model of self-regulated learning (SRL) theory based on the literature, and an evaluation of the potential for discovering such a model from observational data using the new statistical methods.