No abstract

Abstract. In the context of Intelligent Tutoring Systems, there is a potential for adapting either content or its sequence to student as to enhance the learning experience. Recent theories propose the use of teamworking environments to improve even further this experience. In this paper an effective matching algorithm is presented in the context of peer reviewing applied to an educational setting. The problem is formulated as an optimization problem to search a solution that satisfies a set of given criteria modeled as "profiles". These profiles represent regions of the solution space to be either favored or avoided when searching for a solution. The proposed technique was deployed in a first semester computer engineering course and proved to be both effective and well received by the students.

Abstl'act-Peer review has been widely used in multiple contats ranging from childhood education to ocademic researr:h. Numer ous documents describe dijfel'f!ll t aspects of the reviewing process.Interestingly, barely any discuss ion is found about how to better match peer assessors and ll$5esses. In this paper an application of peer review in an educational environment is presented. In such context, it is considered as a pedagogical tool to improve the overall learning experience. It is shown that by carefully assigning reviewers to authors, peer review can be orienled to maximize the benefits of the process. Normally, the mapping between authors and reviewers is simplified to a blinded. random association. The propOsed adoptive strategy suggests an effective method for assigning reviewers and authors depending on user profiles and based on fozzy classification techniques. The strategy requires a set of prototypes (typical author reviewer pairs) and a set of corresponding weights specifying the interest of each prototype. Genetic algorithms are used to obtain a solution to optimize the QJsignments of reviewers to authors. L INTRODUCTIONPeer Review consists of evaluating II colleague's work. It has been widely used in multiple contexts, ranging from childhood education to academic research. In this paper, we focus on peer review use in education, a field to which peer review has been typically applied, to virtually any level and subject.The benefits as well as a detailed topology of peer review in education have been carefully studied (see [I] for an excellent survey). Despite the numerous experiences and tools deployed, little attention has been paid to how to take advantage of the matching procedure between authors and reviewers to improve the overall process. Is it possible to select the matching between authors and reviewers as to improve the overall learning experience? In this document a scheme is presented oriented toward this goal. First, a generic criterion is proposed to select the best pairing between authors and reviewers; then a concrete approach is described for the context of a multimedia programming course.The rest of the document is organized as follows. Sec tion II presents relevant work in the area of peer review in the educational context. Section 111 describes the context in which the model is applied. In Section IV, a survey of the peer review process as well as its potential influence in student learning is given. An adaptive strategy for matching authors and reviewers is proposed in Section V. Finally, results of adaptive peer review application to the context described are presented in Section VI followed by a set of conclusions in Section VII. II. RELATED WORKA large amount of documents can be found describing aspects of the reviewing process such as problems and benefits, successes and failures, supporting systems, etc. Relevant publications can be found about peer review applied to writing experiences [2]-[5], engineering [6], [7J and computer sci ence [8]-[10], to mention a few. A com...

No abstract