Carlos Miguel Tobar

An Explanation Tool to Support Learning of Basic Programming

Intelligent tutoring systems (ITS) have assisted engineering students in several domains. The domains considered ideal for ITS contain easily represented issues in computational form and allow the interaction type between student and ITS be limited to a restricted set of words, symbols, and numbers. It is proposed to exploit intelligent system technology to support an explanation process in the context of ITS. A system was developed to support explanations of examples to assist the learning process of basic programming. Examples of C programs, previously elaborated by a teacher, are presented to a student from who are expected explanations to source-code regions. Using techniques of approximate natural language understanding, the system tries to recognize explanation contents to send the result to a module that classifies explanations as correct, incorrect, or incomplete according to the context of the proposed activity. The context can be configured by the teacher. After explanation processing, an ITS could determine the subsequent stages according to its educational strategy

A PMO Installation for TI Project Management in a R&D Institution

The search for standardization to productive processes improvements gets sharp during periods that are marked by global economic crisis. To look for alternatives aiming at staying present and competitive, considering new market requirements was the reaction of a research and development institute that works with Information Technology. This scenario triggered the motivation to perform the effort described in this article. This institution was chosen for a case study that aims at observing if there was an increase of compliance rates to the project management process that is adherent to the ISO 9001:2000 standard, with the focus on the hardware department. The compliance increase was imagined to be the result of the installation consequence of a Project Management Office (PMO). The performed actions for the PMO structuring were observed and documented, as well as the correlation of process compliance data from a two year period of developed projects, proving the impact of the PMO performance in projects outcomes.

Information Retrieval in Wikis Using an Ontology

This article addresses a question regarding relevant information in a social media such as a wiki that can contain huge amount of text, written in slang or in natural language, without necessarily observing a fixed terminology set. This text could not always be adherent to the discussed subject. The main motivation leads to the need of developing methods that would allow the extraction of relevant information in such scenario. A result system was designed upon ideas from the semantic Web combined with an adaptation of the classic vector model for information retrieval. The semantic information is not embedded in the media but within a structurally independent ontology. It was implemented using Java and a MySQL database. The objective was the achievement of, at least, 80% for recall and precision on the system results. The system was considered successful by achieving rates of 100% of recall and approximately 93% of precision.

Assessing a learning object standard adherence

New technology has the potential to relate teachers and students to diverse learning resources, bringing up the paradigm of learning objects. A learning object is any digital or non-digital entity that can be used in education through computing. There are many standards defining how to search, evaluate, acquire, share, and use this kind of resource by instructors, students, and automated software processes. Aiming to explore the learning-object paradigm, it was modeled, built, and tested a learning-object database that is part of a collaborative environment, which supports distance learning of computer programming languages. One of the available standards was adopted, the learning object metadata standard - LOM. In order to build and manipulate the learning-object database, some strategies showed to be necessary and thus they were defined. This paper presents an adherence analysis of the LOM standard, considering the development of a learning object repository. The features about LOM utilization by automatic software processes are targeted and some detected problems have their proposed solutions considered and discussed.

Using Collaborative Filtering Algorithms for Predicting Student Performance

Models that accurately predict student performance can be useful tools for planning educational interventions aimed at improving the results of the teaching-learning process, contributing to saving government resources and educators’ and students’ time and effort. In this paper it is studied the performance of collaborative filtering (CF) algorithms when applied to the task of student performance prediction. CF algorithms have been extensively and successfully used in recommender systems, but not in the considered educational scenario. The performances of two baseline methods and six state-of-the-art CF are compared when predicting if students would hit or miss multiple-choice questions, using two large educational datasets, created from the interaction between students and educational software. It was verified that CF algorithms account for consistently higher performance than the baselines for most metrics. Among the CF algorithms, memory based methods presented an overall better accuracy, precision, and recall. Nevertheless, all CF algorithms presented relatively low recall in identifying incorrect answers.

OntoHop: An information filtering agent using hopfield nets and ontologies

The size of the Web and its dynamic nature in addition to the fact that stored documents are written in natural language, and therefore intended to be read by people and not to be processed by computers, present major challenges to build automatic personalized information filtering systems. This article presents the architecture of an information filtering agent based on an implementation of a Hopfield neural network (HNN). Network nodes (neurons) represent relevant terms in the domain of interest and neuronal links represent asymmetric probabilities of term co-occurrences in the domain, or the relevance weight between a pair of terms. Relevant terms are automatically derived from a corpus related to the domain of interest using automatic indexing and an ontology. Co-occurrence probabilities are computed by a cluster function that produces asymmetric links between terms. At the moment of document filtering, input neurons are activated on the basis of the presence of terms in the document that are identical or semantically similar to the terms stored in the net. The semantic similarity between terms is calculated using a hierarchical ontology that describes concepts that exist in the domain of interest. Experiments conducted to evaluate the precision and recall of the agent with and without the use of ontologies show that ontology use tends to favor recall over precision. The degree to which this bias occurs can be adjusted by setting the minimum level of similarity required to consider a document and a network term similar.

Engineering capstone project an individual approach

This article presents a capstone project (CP) approach based on a two-semester effort developed individually to build up and reinforce skills fostered during a computer-engineering curriculum. The CP result is an artifact to be inserted in a context, which is developed, under guidance and monitoring. Besides the student, there are other three roles involved: the advisor for methodological issues; the co-advisor, for technical issues; and the client, to be the source for context knowledge. The student is responsible by planning, developing and managing the project, reporting it in a monograph that is presented in a public defense together with the artifact. The artifact must present a level of complexity that allows measuring some considered major skills. Student and co-advisor choose a methodology for the development effort, whose activities are planned and scheduled. The student should identify open problems in the considered context. One of these problems is chosen as an objective, which should be assessed. Assessment is considered an important issue in the development process. Results are promising: artifacts became real solutions, some even patented; students began graduation because of their CPs or were invited to work because of the acquired knowledge and skills; and students succeed with high self esteem and better communication skills.

Retrieving Wiki Content Using an Ontology

This chapter addresses a question regarding relevant information in a social media such as a wiki that can contain huge amount of text, written in slang or in natural language, without necessarily observing a fixed terminology set. This text could not always be adherent to the discussed subject. The main motivation leads to the need of developing methods that would allow the extraction of relevant information in such scenario. A result system was designed upon ideas from the semantic Web combined with adaptive mechanisms and a modification of the classic vector model for information retrieval. The semantic information is not embedded in the media but within a structurally independent ontology. It was implemented using Java and a MySQL database. The objective was the achievement of, at least, 80% for recall and precision on the system results. The system was considered successful by achieving rates of 100% of recall and approximately 93% of precision.

Auxiliar: a case-based system to assist online courses

This paper presents the REASONING, the third module of a computerized system (AUXILIAR), designed to help human-tutors redefine information for those students who have difficulties in grasping deployed educational topics. To this end, there is an intelligent mechanism that facilitates the assessment process and searches for similar cases produced by other students in past situations. This search enables the system to redefine the information content to be rendered to the student in order to eliminate deficiencies detected during a formative assessment without considerable intervention by the tutor. To reach these goals, concepts of artificial intelligence (case-based reasoning, more specifically) and man-machine interaction are exploited. Thereby, there are presented the format of a case, the structure of the case library, as well as the intelligent retrieval mechanism that was developed.

Extending adaptation frontiers for learning sets

Several models and frameworks have been proposed for adaptive hypermedia systems, but when it comes to the integration with application models these proposals lack expressiveness, blurring combinations of functional components or information categories, sometimes with abstractions layers. This is very clear for educational applications, where matters such as collaboration and cognitive styles are not cleanly integrated to hypermedia modeling issues. The extended abstract categorization map is being proposed as a comprehensive framework, considering educational applications, where complementary modeling perspectives are adequately separated but still integrated. The resulting separation of concerns yields a clearer understanding of how adaptation issues can be affected by educational goals.