Usage of Graph Patterns for Knowledge Assessment Based on Concept Maps

Grundspeņķis, Jānis; Strautmane, Maija

doi:10.2478/v10143-009-0005-y

Cited by 13 publications

(8 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Thus, the evaluation algorithm is based on the set of patterns specified in Figure 5. However, improvement of the algorithm is continued by studying possibility to reveal extra relationships in learners' concept maps [17]. Figure 6 displays a situation when some relationships are "hidden": there are only 3 relationships in the teacher's concept map (Figure 6.a), but 2 more relationships can be derived (Figure 6.b).…”

Section: Evaluation Algorithmmentioning

confidence: 99%

“…With aim to determine extra relationships 6 types of relationships are considered [17]:is a -a relationship between concepts meaning that one of the concepts is a sub-class of other, part of -a relationship between concepts meaning that one of the concepts is a part of other, attribute -a relationship between a concept and its attribute, example -a relationship between a general concept and a particular example of it, value -a relationship between an attribute and its value, kind of -a relationship between levels of hierarchy. Figure 7 shows the structure of a pattern further explained in Figure 8.…”

Section: Evaluation Algorithmmentioning

confidence: 99%

See 1 more Smart Citation

Incremental Improvement of the Evaluation Algorithm in the Concept Map Based Knowledge Assessment System

Anohina

Viļķelis

Lukašenko

2009

INT J COMPUT COMMUN

View full text Add to dashboard Cite

The paper is devoted to the knowledge assessment system that has been developed at the Department of Systems Theory and Design of Riga Technical University for the last four years. The system is based on concept maps that allow displaying the knowledge structure of a particular learner in the form of a graph. Teacher's created concept maps serve as a standard against which learner's concept maps are compared. However, it is not correct to compare teacher's and learners' concept maps by examining the exact equivalence of relationships in both maps, because people construct knowledge in different ways. Thus, an appropriate mechanism is needed for the flexible evaluation of learners' concept maps. The paper describes the algorithm implemented in the concept map based knowledge assessment system and its evolution through four prototypes of the system.

show abstract

Section: Evaluation Algorithmmentioning

confidence: 99%

Section: Evaluation Algorithmmentioning

confidence: 99%

Incremental Improvement of the Evaluation Algorithm in the Concept Map Based Knowledge Assessment System

Anohina

Viļķelis

Lukašenko

2009

INT J COMPUT COMMUN

View full text Add to dashboard Cite

show abstract

“…More sophisticated checking of propositions based on larger patterns, e.g. patterns containing three concepts and two relationships is under the development [22]. It will help to separate which parts of a student's CM is different from a teacher's CM and which are just different reflections of the same structure, as well as to increase the level of automation of knowledge assessment.…”

Section: The Fourth Prototypementioning

confidence: 99%

Evolution of the Concept Map Based Adaptive Knowledge Assessment System: Implementation and Evaluation Results

Grundspeņķis¹,

Anohina²

2009

Scientific Journal of Riga Technical University. Computer Sciences

Self Cite

View full text Add to dashboard Cite

Evolution of the Concept Map Based Adaptive Knowledge Assessment System: Implementation and Evaluation ResultsThe paper represents the concept map based adaptive knowledge assessment system. Advantages of concept maps are analyzed emphasizing that the approach offers a reasonable balance between requirements to assess higher levels of knowledge according to Bloom's taxonomy and complexity of a system. Concept maps allow revealing of student's knowledge structure, promote system thinking and support process oriented learning where a study course is divided into stages in each of which knowledge assessment is carried out. The developed knowledge assessment system consists from a teacher's, learner's and administrator's modules and is implemented as a multiagent system. Four prototypes of the system developed within four projects are described. The first prototype supports only fill-in-the-map tasks where a learner must put given concepts in correct places. The second prototype provides changing the degree of task difficulty, thus, performing adaptation to a learner's knowledge level. The set of tasks are also extended by construct-the-map tasks. Improvements implemented in the third prototype allow using of directed arcs and standard relationships in concept maps. The three-tier architecture used in the fourth prototype is chosen to rise the security level of the system. Besides that learner's support is considerably expanded giving help and tutoring to a learner. Results of evaluation of the developed system's prototypes in different study courses are presented. The paper concludes with the comparison of all four prototypes using all main characteristics of the developed knowledge assessment system.

show abstract

“…At the moment the system can recognize more than 36 different patterns of correct and partly correct propositions in students' CMs [3]. Recently the improvement of the mentioned algorithm was made by considering the so called "hidden" relationships [11] in students' CMs which are nothing else than the derivation of relationships presented in a teacher's CM. The hidden relationships are recognized as correct too and could appear in students' CMs.…”

Section: Overview Of the Systemmentioning

confidence: 99%

Feedback in the Concept Map Based Intelligent Knowledge Assessment System

Lukašenko¹,

Anohina-Naumeca²,

Viļķelis³

et al. 2010

Scientific Journal of Riga Technical University. Computer Sciences

Self Cite

View full text Add to dashboard Cite

-The paper presents the concept map based intelligent knowledge assessment system developed by the Department of Systems Theory and Design of the Faculty of Computer Science and Information Technology of Riga Technical University. The main attention is devoted to the implementation of various kinds of feedback intended for promotion of effective learning and informing of a teacher about students' progress. The feedback is considered from three points of view: feedback generated automatically by the system and given to a student and to a teacher, and feedback provided by a student using questionnaires embedded into the system. All feedback types are discussed in detail and demonstrated using screenshots. Related works are presented as well. The calculation of the concepts' mastering degree and composition of the text summary informing a student about the best and the poorly known concepts within a task is described. The constituent parts of the questionnaire system (the questionnaire designer, the questionnaire filler and the questionnaire reporting system) are specified and all kinds of questions available in the questionnaire designer are demonstrated. The overall functionality of the system is presented paying attention to the goal of the system, scenario of the use and range of provided tasks.

show abstract

Usage of Graph Patterns for Knowledge Assessment Based on Concept Maps

Cited by 13 publications

References 6 publications

Incremental Improvement of the Evaluation Algorithm in the Concept Map Based Knowledge Assessment System

Incremental Improvement of the Evaluation Algorithm in the Concept Map Based Knowledge Assessment System

Evolution of the Concept Map Based Adaptive Knowledge Assessment System: Implementation and Evaluation Results

Feedback in the Concept Map Based Intelligent Knowledge Assessment System

Contact Info

Product

Resources

About