Topic extraction and extension to support concept mapping

Proceedings of the twenty-sixth …, 2004

Concept mapping is widely used in educational and other settings to aid knowledge construction, sharing, and comparison; concept maps are also used as a vehicle for assessing understanding. To aid the concept mapping process, projects at Indiana University and the Institute for Human & Machine Cognition (IHMC) are developing "intelligent suggesters" to support users as they build concept maps, by presenting them with relevant information from existing knowledge models and the Internet. This depends on identifying important concepts in the concept map under construction. This paper presents and evaluates models of the influence of concept map layout and structure on the selection of concepts expected to be relevant to the topic of concept maps. It presents and assesses a set of potentially-relevant structural factors and evaluates how these factors combine to affect human judgments of concept importance. Twenty subjects were asked to judge the relative importance of concepts in concept maps selected to highlight particular characteristics, and three models were compared to their judgments. Analysis of the results shows that subjects were significantly influenced by concept map topology, but little influenced by other aspects of concept map layout. The results suggest that layout-independent models of concept maps can provide a suitable representation for guiding retrieval of topicrelevant information to support concept map construction, provided that the representation reflects topologically-based influences. The results are applied in the design of the suggesters' similarity assessment procedures for retrieving relevant concept maps.

2004

Electronic concept mapping tools provide a flexible vehicle for constructing concept maps, linking concept maps to other concept maps and related resources, and distributing concept maps to others. As electronic concept maps are constructed, it is often helpful for users to consult additional resources, in order to jog their memories or to locate resources to link to the map under construction. The World Wide Web provides a rich range of resources for these tasks—if the right resources can be found. This paper presents ongoing research on how to automatically generate Web queries from concept maps under construction, in order to proactively suggest related information to aid concept mapping. First, it examines how concept map structure and content can be exploited to automatically select terms to include in initial queries, based on studies of (1) how concept map structure influences human judgments of concept importance, and (2) the relative value of including information from conc...

2015

Abstract. Information visualization has been a research topic for many years, leading to a mature field where guidelines and practices are well established. Knowledge visualization, in contrast, is a relatively new area of research that has received more attention recently due to the interest from the business com-munity in Knowledge Management. In this paper we present the CmapTools software as an example of how concept maps, a knowledge visualization tool, can be combined with recent technology to provide integration between knowl-edge and information visualizations. We show how concept map-based knowl-edge models can be used to organize repositories of information in a way that makes them easily browsable, and how concept maps can improve searching algorithms for the Web. We also report on how information can be used to complement knowledge models and, based on the searching algorithms, im-prove the process of constructing concept maps. 1 Introduction: Information and Knowledge V...

Proceedings of the Fifteenth …, 2001

Concept maps capture knowledge about the concepts and concept relationships in a domain, using a two-dimensional visually-based representation. Computer tools for concept mapping empower experts to directly construct, navigate, share, and criticize rich knowledge models. This paper describes ongoing research on augmenting concept mapping tools with systems to support the user by proactively suggesting relevant concepts and associated resources (e.g., images, video, and text pages) during concept map creation. Providing such support requires efficient and effective algorithms for judging concept similarity and the relevance of prior concepts to new concept maps. We discuss key issues for such algorithms and present four new approaches developed for assessing conceptual similarity for concepts in concept maps. Two use precomputed summaries of structural and correlational information to determine the relevance of stored concepts to selected concepts in a new concept map, and two use information about the context in which the selected concept appears. We close by discussing their tradeoffs and their relationships to research in areas such as information retrieval and analogical reasoning. £

Concept maps: Theory, …, 2004

Electronic concept mapping tools provide a flexible vehicle for constructing concept maps, linking concept maps to other concept maps and related resources, and distributing concept maps to others. As electronic concept maps are constructed, it is often helpful for users to consult additional resources, in order to jog their memories or to locate resources to link to the map under construction. The World Wide Web provides a rich range of resources for these tasks-if the right resources can be found. This paper presents ongoing research on how to automatically generate Web queries from concept maps under construction, in order to proactively suggest related information to aid concept mapping. First, it examines how concept map structure and content can be exploited to automatically select terms to include in initial queries, based on studies of (1) how concept map structure influences human judgments of concept importance, and (2) the relative value of including information from concept labels and linking phrases. Second, it examines how a concept map can be used to refine future queries by reinforcing the weights of terms that have proven to be good discriminators for the topic of the concept map. The described methods are being applied to developing "intelligent suggesters" to support the concept mapping process.

2006

The intent of the article is to provide experience-based, basic, practical observations regarding expert knowledge elicitation with concept maps. This article contains a description of techniques for the interactive, collaborative construction of concept maps by a domain expert and a facilitator (who is typically not a domain expert) and the selection or creation of accompanying resources. After a brief review of relevant literature, this article provides a description of the value of and approaches to advance preparations for concept mapping sessions, strategies and tactics that help sessions to get off to a good start, the process of creating hierarchical organizations of concept maps, making decisions regarding what to capture in concept maps and what to capture by accompanying resources, and the refinement and verification of knowledge models.

2040

The purpose of the project was to "conduct research and design concept maps about the knowledge base in higher education" and to "prototype these concept maps and the ways in which they may be used to help navigate and search Internet resources." This Technical Report and demonstrations to ERIC staff are the primary deliverables.

2002

We have developed a JAVA prototype of a templatebased Concept Mapping Tool, the CM-ED tool, that supports the above mentioned applications. In this paper we will show how CM-ED can be used within an Intelligent Tutoring System authoring tool, the IRIS authoring tool, to represent the domain knowledge. In this paper, the authors show the benefits of using a concept mapping tool for gathering the domain knowledge in the computer-aided learning area. Concretely, we show how CM-ED is used integrated in the IRIS Intelligent Tutoring System authoring tool. First, the paper describes the structure of the domain knowledge in IRIS. Then, the main characteristics of CM-ED are listed. Finally, the new concept map based interface for domain acquisition in IRIS is presented.

Proceedings of the Fourteenth …, 2001

Knowledge management depends on effective methods for capturing knowledge in useful forms and making it available when needed. Electronic concept maps provide a promising representation for knowledge models that can be developed directly by the experts themselves, but the flexibility of concept mapping raises questions of how to support the knowledge modeling process and to standardize its results, in order to facilitate future examination and reuse. We describe ongoing research on the use of case-based reasoning methods to support the knowledge modeling process through proactive retrieval of relevant prior concept maps, in order to provide suggestions to aid the concept map generation process. The selection of relevant concept maps relies on an algorithm that combines textual and topological analysis. We describe the algorithm and present an example that illustrates concept suggestion procedures in the Mars exploration domain.

Concept maps and expert systems are both in the soft toolbar of knowledge modelling. We have spent nearly two decades developing our expert system shell "Doctus". Several years ago we have seen the first concept mapping solutions and started using them very soon. Frequently we have found ourselves using both tools in a particular research or consultancy project and started to wander how the two could be combined to achieve synergies. We came up with several ideas, typically when we have faced a situation which called for one of the potential synergies. In this paper we present the first of these ideas in elaborated form of a conceptual model and we also mention few additional ideas as our plans for future research. In this first idea we combine different kinds of concept maps and our expert system in order to map organisational knowledge. The expert system here is used in machine learning mode, i.e. the resulting concept map will be capable of learning -this is our intelligent concept map.

2015

Concept maps are useful in many disciplines for the representation and communication of structured knowledge. This article contains a description of concept mapping and knowledge modeling based upon concept maps that are used for a variety of purposes. It describes applications of concept mapping and knowledge modeling for education, for knowledge preservation and sharing, for knowledge creation, as an efficient means of creating documentation, and for the creation of knowledge formalisms from informal knowledge representations. Examples are drawn from several different knowledge domains.

KPI Science News, 2020

Background. The hypermedia environment, which has received a powerful technical infrastructure thanks to the WWW, has led to the study and emergence of new forms and tools of information and educational content presentation. Various methods and means of visualization of educational information increase clarity and facilitate the process of new knowledge perception. Such tools include a wide range of concept maps that have become widespread in many areas related to information technology and education. The challenge here is to find comprehensive solutions that will reduce computing and labor costs for the multifunctional use of concept maps in information and learning systems. Objective. The work is focused on the review of concept maps, research of preconditions for their origin, analysis of their types and purposes of application in the educational process and learning systems. The main task is to analyze the requirements for interactive concept maps in ontology-oriented information systems to support lifelong learning. Methods. The use of concept maps in educational systems is based on knowledge modeling, graph theory, ontological modeling of educational content and methods of adaptive e-learning systems. The paper reviews and analyzes the application of concept maps and requirements for them within the information and learning systems. Results. Concept maps have significant foundation in cognitive and educational psychology, computational linguistics, knowledge engineering and have widespread application in computer supported learning. Concept maps are used as a means of meaningful learning when constructed by students, used to assess knowledge, as well as a means of navigating information resources. Concept maps in educational systems are used to present knowledge to users and serve as interfaces in the process of exploratory search and review of study areas. Information systems provide enrichment of concept maps by means of interactivity, which allows diversifying and expanding its use. Conclusions. The key requirements for interactive concept maps in information and learning systems are formed, including automation of interactive concept map construction, availability of wide navigation capabilities together with cognitive load control, implementation of interdisciplinary links, media annotation of map elements, complex application of graph interfaces for different parts of the system and adaptation to mobile devices.