Ontology Development Through Concept Maps Using Text Indices

Abstract- Ontology acts as a platform for knowledge sharing and description to represent a particular domain in the form of customized web information gathering. While developing those ontologies for a particular domain, it emphasizes the knowledge base across the global information than the local in information. In this project represent a customized ontology system for a particular domain. Data mining is chosen as a domain to represent its concepts and scope globally. This system is developed by comparing the pre-existing ontologies on Data Mining and merging the essential features associated with it. Finally the ontological model developed for the domain Data Mining is represented as conceptual map using protégé. The conceptual map helps in identifying the relationships between the concepts based on the semantics of the terms. Concept map can be in various different forms. Among that we represent the concept map for data mining in Onto-Graph.

Index Terms- Concept Map Mining, Concept Map generation, Text Mining.

1. INTRODUCTION

Various tools and techniques are used in the progress of the education field to attain the higher results and quality. Data Exploration is the practice of using visualization techniques to find unforeseen relationships between data points or sets of points in a large databases. Visualization techniques can also be applied to information that is already known. The purpose of any visualization to be used in an educational context is to facilitate the learning of some knowledge (idea, concept, fact, algorithm, relationship). In order to accomplish visualization it must make connections between the knowledge learner and the knowledge being taught. Conceptual

structures such as concept maps, topic maps and conceptual graphs deal with organizing, processing and visualizing the domain knowledge in Web based educational systems (WBES)[1].

Concept maps are anticipated in order to overcome the shortcomings of mind map. Concept Maps are graphical representation of knowledge that are comprised of concepts and the relationships between them. Usually concepts are encapsulated in circle or boxes. The relationship between concepts is articulated in linking phrases, e.g., “gives rise to”, “results in”, “is required by,” or “contributes to”. Concept map uses the triple form concept-link-concept. Concept mapping is a tested, intuitive, low entry-cost technique for knowledge capture and composition. In Concept map concepts are represented in a hierarchical fashion with the most inclusive, most general concepts at the top of the map and the more specific, less general concepts arranged at the bottom level.

Concept and web ontology language represent the same domain knowledge. Concept map comprises the nodes and labels and Web Ontology Language (OWL) have the classes, instances and properties.

Figure 1.1 Correspondence of Main Ontology Elements To Concept Map

The article is further organized as follows. In section 2 related works on conceptual map are narrated in a nutshell. In section 3 the keyword extraction and concept map generation is presented. In Section 4 the evaluation and implementation methods are described. The results and discussions and the conclusion are briefly discussed in section 5.

2. RELATED WORKS

The main aim of this chapter is to describe the theoretical foundations and relevant background of concept map creation. It also brings out the different definitions of ontology an overview of keyword extraction, ontology creation, and concept maps the main aim of the project is to develop the domain ontology for Data Mining in order to provide the knowledge base in that domain. At this stage it is essential to have a glance about the pre-existing similar kind of ontology and grasp the knowledge base on that ontologies. There are various researches done on the concept of domain ontology especially on Data Mining.

Ontology

Ontology is a “formal, explicit specification of a shared conceptualization”[2]. It is formally represents knowledge as a set of concepts within a domain, and the relationships between pairs of concepts. It can be used to model a domain and support reasoning about concepts. It provides a shared vocabulary, which can be used to model a domain, that is, the type of objects and/or concepts that exist, and their properties and relations.

Visualization

A good visualization certainly has to do more, but these criteria are useful to draw the line between a lot of things that are often called visualization and what we consider visualization in this field[3].

1. Based on (non-visual) data. A visualization’s purpose is the communication of data. That means that the data must come from something that is abstract or at least not immediately visible (like the inside of the human body). This rules out photography and image processing. Visualization transforms from the invisible to the visible[4].
2. Produce an image. It may seem obvious that a visualization has to produce an image, but that is not always so clear. Also, the visual must be the primary means of communication, other modalities can only provide additional information. If the image is only a small part of the process, it is not visualization[5].

Concept Map

concept map is a diagram that depicts suggested relationships between concepts. A concept map typically represents ideas and information as boxes or circles, which it connects with labeled arrows in a downward-branching hierarchical structure. Concept maps are a way to develop logical thinking and study skills by revealing connections and helping students see how individual ideas form a larger whole. Concept maps were developed to enhance meaningful learning in the sciences. A well-made concept map grows within a context frame defined by an explicit “focus question”, while a mind map often has only branches radiating out from a central picture[6].

Concept Map History

Concept Maps (CM) were introduced by Joseph Novak as a way to assess children’s understanding of science with graphical tools to organize and represent knowledge (Novak & Gowin, 1984)[7]. In a CM, concepts are represented in boxes that are linked by labeled relationships; two related concepts (including their link) form a proposition or semantic unit. Concepts are also arranged hierarchically such that more general concepts are located higher on the map and specific concepts such as examples are located lower. Novak defines a concept as “a perceived regularity in events or objects”, or “records of events or objects” designated by a label. A concept by itself does not provide meaning, but when two concepts are connected using linking words or phrases, they form a meaningful proposition.

Figure 2.1 Concept Map Using Tools

Kuo-En Chang et.al.,[8] have developed the Effect of Concept Mapping to Enhance Text Comprehension and Summarization. Graphic strategies, such as graphic organizers and knowledge maps, have proved helpful for text learning, certain important application issues such as surface processing and cognitive overload have yet to be resolved. The authors tested the learning effects of a concept-mapping strategy. They designed three concept-mapping approaches—map correction, scaffold fading, and map generation—to determine their effects on students’ text comprehension and summarization abilities. The experimental results showed that the map-correction method enhanced text comprehension and summarization abilities and that the scaffold-fading method facilitated summarization ability.

Find Out How UKEssays.com Can Help You!

Our academic experts are ready and waiting to assist with any writing project you may have. From simple essay plans, through to full dissertations, you can guarantee we have a service perfectly matched to your needs.

View our academic writing services

Nian-Shing et. al.,[9]. Chan have developed the Mining e-Learning domain concept map. Recent researches have demonstrated the importance of concept map and its versatile applications especially in e-Learning. For example, while designing adaptive learning materials, designers need to refer to the concept map of a subject domain. Moreover, concept maps can show the whole picture and core knowledge about a subject domain. Research from literature also suggests that graphical representation of domain knowledge can reduce the problems of information overload and learning disorientation for learners. However, construction of concept maps typically relied upon domain experts in the past; it is a time consuming and high cost task. Concept maps creation for emerging new domains such as e-Learning is even more challenging due to its ongoing development nature. The aim of this paper is to construct e-Learning domain concept maps from academic articles. The authors have adopted some relevant journal articles and conference papers in e-Learning domain as data sources, and applied text-mining techniques to automatically construct concept maps for e-Learning domain. The constructed concept maps can provide a useful reference for researchers, who are new to the e-Leaning field, to study related issues, for teachers to design adaptive learning materials, and for learners to understand the whole picture of e-Learning domain knowledge.

A system is developed to realize the whole process of automatic concept map construction for e-Learning domain. These processes are needed only once for constructing concept map database.

Clariana .B et, al.,[9] have developed A Computer-Based Approach For Translating Text into Concept Map-Like Representations . Essays, concept maps provide a visual and holistic way to describe declarative knowledge relationships, often providing a clear measure of student understanding and most strikingly, highlighting student misconceptions. This article presents a computer-based approach that uses concept-map like Pathfinder network representations to make visual students’ written text summaries of biological content. A software utility called ALA-Reader was used to translate students’ written text summaries of the heart and circulatory system into raw proximity data, and then Pathfinder PCKNOT software was used to convert the proximity data into visual PFNets. The validity of the resulting PFNets as adequate representations of the students’ written text was considered by simply asking the students and also by comparing the correlation of human rater scores to the PFNet agreement-with-an-expert scores. The concept-map like PFNet representations of texts provided students (and their instructor) with another way of thinking about their written text, especially by highlighting correct, incorrect, and missing propositions in their text. This paper provides an overview of the approach and the pilot experimental results. The actual poster session will in addition demonstration the free ALA-Reader software and will also how to procure and use PCKNOT software.

Method and Tools

Twenty-four graduate students who are experienced practicing teachers enrolled in an educational assessment course used Inspiration software to create concept maps on the structure and function of the human heart while researching the topic online. Later outside of class, using their concept map they wrote text summaries as a precursor for the in-class activities of scoring the concept maps and text summaries (essays). In class, students discussed multiple scoring approaches and then working in pairs, scored all of the text summaries using a 5-point rubric that focused on three areas, content, style, mechanics, and overall.

Tools:

1. ALA-Reader software
2. PCKNOT software
3. Comparing text scores (from human raters)to the ALA-Reader/PFNet text scores.

In this pilot study, graduate students used Inspiration software to create concept maps while researching the structure and function of the human heart online, these concept maps were used to write text summaries, and then the text summaries were translated into concept map-like representations using computer-based software tools. The findings suggest that this approach captures some aspects of science content and/or process knowledge contained in the students’ text summaries. The concept-map like PFNet representations of texts provides students (and their instructor) with another way of thinking about their written text and their science content knowledge, especially by highlighting correct, incorrect, and missing propositions. Given a little thought, there are multiple ways that this approach can be used instructionally. For example, one of our near term goals is to embed the text-to-map system into writing software and also to use the approach for answer judging (relative to an expert) of extended constructed response items in online instruction[10].

3. KEYWORD EXTRACTION AND CONCEPT MAP GENERATION

A good concept map contains only relevant concepts (a perceived regularity in events or objects, or records of events or objects, designated by a label), connected by linking words into coherent propositions. On deciding what concepts to include in a concept map, and on linking them properly the author’s reflection is required . Concept maps have been used to support reading and writing activities, what is known as Text Concept Mapping (TCM) . The activities usually consist on summarizing the key ideas in a piece of text, and there are three ways of doing it: Building a concept map from scratch, fixing a previously built concept map and studying a concept map. In the first activity the students build a concept map without any support, in the second activity the teacher builds a map that has some errors and/or missing information that the students have to fix, and in the final activity the students study a concept map built by the teacher which summarizes the text. All activities have been shown to improve the students’ understanding on the readings’ topics . Concept Map Mining:

Figure 3.1 CMM Process

Concept Map Mining is defined as the extraction of concept maps from text that are useful in educational context. Its aim is to provide new ways to visualize the knowledge expressed in the text for human consumption. The CMM process consist on identifying the concept in a piece of text and the linking words that connect them. It has three sub-task which are: Concept Extraction, Relationship Extraction and summarization. The first task aims to identify every possible concept in the second aims to find all possible connections between the previous concepts and the third step consists on creating a reduced version of the map that summarizes the content, avoiding redundancy and maximizing coverage.

This Concept Map Mining (CMM) is: The automatic extraction of concept maps from essays for educational purposes, and presented the analysis of a gold standard constructed for the purpose of evaluating the algorithms that will implement the task. The main goal of the analysis is to gain an understanding on the characteristics of the concept maps produced by human annotators when asked to create a summary of a piece of text. Such patterns will inform the design of the automatic algorithms that will implement CMM.

4. IMPLEMENTATION AND EVALUATION

The main intention of the paper is generating the concept map from the Web Ontology Language (OWL) ontologies. Existing ontologies which are already available on the web pages are used as the input. Web ontology Language (OWL) has the classes and properties, data type properties and object properties.

The importance of automatic methods to enrich knowledge bases from free text is acknowledged by the knowledge management and ontology communities. Developing a domain knowledge base is an expensive and time consuming task, and static knowledge bases are difficult to maintain. This is especially true in the domain of online training. Domain ontology is central of the knowledge base. This research focuses mainly on the domain model and describes a semiautomatic methodology and tool, to build domain ontologies from English text.

Concept maps are tends to make the structure of a body of knowledge much more significant for human users than other forms of knowledge representation. Hence, easily validated and enriched by a domain expert. Concept maps also foster meaningful learning and index sentences at a fine-grained level, which is required for efficient indexing and retrieval. In order to promote interoperability and reuse, concept maps pass through an export process that outputs lightweight domain ontology.

The objectives of the research work are:

• To present a overview of keyword extraction and ontology creation.
• To extracting the keywords automatically from given text using java coding in eclips.
• To analyzing the extracted keywords and build ontology manually.
• To propose a automatic concept map for ontology creation from text.
• To view the concept map using OWL API 3.4.2 (Protege).

Figure 4.1 Overview of Keyword Extraction

Figure 4.2 Using Keyword Generating the Concept Map in OntoGraf Tool

5. CONCLUSION

A number of enhancements and extensions are possible. We would like to enrich the keyword extraction with new structures and explore other ways of expressing patterns. Moreover, further thorough ontology and concept map are need to develop automatically. Additionally, the different types or structure documents are not only converting text document into ontology in future other structure documents also convert into ontology automatically

The proposed framework for generating the concept map from the OWL ontologies having the ability to generate the concept map in the very effective manner. This is the main advantage of this proposed framework. This framework is suitable to generate the concept map at the minimum number nodes upto the maximum of fifty nodes. The number of nodes has to be increased and make the possible to view the more contents and the relationship between the concepts. In future, more refinement and enhancement will be added in the concept map generating software. OWL file could be transformed independently from their construction tool. The visualization of the concept map has to be increased to improve the clear visual presentation of the concepts and relationship.