Search

Negotiations continue to play an important part of our lives and in particular influences can be seen in the growth in electronic commerce through various auction and online stores. Estimates of up to 7bn were predicted for Christmas 2006, a rise of about 35%-40% on the previous year [1]. This growth can only enhance the demand for electronic negotiation systems or at least highlight the lack of commercial e-negotiation systems. Such systems, though available in mostly academic circles will need to be enhanced before they can replace traditional face-to-face negotiations. As e-commerce continues to grow, we anticipate a faster uptake of negotiation systems if their design can mimic traditional systems. Our work proposes to draw the key attributes that need to be present for a successful negotiation system by examining the current state of the art in electronic negotiation frameworks. The rest of this paper is structured as follows: Section 2 elaborates on the need for electronic negotiation systems, with Section 3 examining the current literature in negotiation frameworks, whilst Section 4 presents the attributes which we found required in negotiation frameworks. Conclusions are drawn in Section 5. [ABSTRACT FROM AUTHOR]

Several Web-based learning systems are currently available. Nevertheless, most existing e-learning platforms lack efficient adaptivity to learner needs. Moreover, adaptive system development is quite costly. Evaluation of these systems and assessment of adaptation components may enable identifying failures and improving them, in one hand, and exchanging successful adaptive components, in the other hand. Adaptive behaviour is strongly determined by functional requirements available to the application domain. In Web-based system, granular functions are increasingly provided by Web services. First, in this paper we focus on measurement criteria related to both adaptive functions and related Web services. Second, Case-Based Reasoning are adopted in order to capitalize evaluation results, learn from past experiences and reuse successful patterns. [ABSTRACT FROM AUTHOR]

Geographic information sharing and service plays an important role in the implement of Digital City. The traditional development model that is based on common geographic information system can not accommodate for the geographic information sharing and service in distributed web environment. In this article, we firstly introduce the requirement of the distributed geographic information sharing and service and the character of service-oriented software architecture. Then the principle of the service-oriented architecture and the service-oriented geographic information sharing and service software architecture for digital city is put forward which includes GIS service, called VGS (Virtual GIS Services) and AGS(Application GIS Services) which reflects the operation service upper the VGS. At last, the web service based model integration in SOA is introduced. And an application example is stated to demonstrate the advantage and application model of the service-oriented geographic information sharing and service software architecture, which is the ocean current numerical simulation model call based on web service. The development and deployment of the model services example was used in Xiamen City, China. [ABSTRACT FROM AUTHOR]

In the present paper we deal with graded reasoning in n-valued Łukasiewicz propositional logic Łn. Firstly we propose an approach to measure the extent to which a theory over Łn is consistent. Secondly, with the concept of consistency degrees of theories, we give several methods of graded reasoning in n-valued Łukasiewicz propositional logic Łn. [ABSTRACT FROM AUTHOR]

With the emergence and development of semantic web, traditional archive service meets a new challenge to provide more intelligent and interactive services for web users. To take good advantage of semantic web technologies, in particular ontology and semantic inference, this paper proposes a semantic search portal for cross-media cultural archives involving document, image, audio and video. With such semanticallyenhanced search portal, implicit multimedia archives can be retrieved under the support of ontology modeling and semantic reasoning. Furthermore, the retrieved crossmedia archives can be semantically navigated and repacked in a more meaningful and integrated way. [ABSTRACT FROM AUTHOR]

With more Web services emerging on Internet, it becomes a challenge for Web Service community to integrate existing Web services to meet the complex requirement of users with little intervention of human. Although semantics added into Web service promises us more powerful measures to automate the service discovering, matching, and integrating, how to realize the process of automatic Service Composition with semantics is still an urgent problem. In virtue of the fruits of the study of behaviorism, this paper analyzes and models the complex services. And through the behavior analysis and behavior partition, this paper reaches a better combination of services, reasoning algorithms with architecture-Service Agent Community(SAC), and makes Service Composition more automatically and intelligently. [ABSTRACT FROM AUTHOR]

Ontologies become more and more big, which is an important factor of low-efficient reasoning. In this paper, we propose an ontology segmentation method for alleviating the inference burden. The method is based on ontologies described by OWL DL. Unlike the traditional method, the optimized method will "chip off" a part of knowledge from the big ontology according to user's query and only uses this knowledge for reasoning. We implemented the algorithms by ontology editor and explain it is very useful in practice. [ABSTRACT FROM AUTHOR]

This paper presents an approach for distributed discovery of web services based on the match history. A service routing table (SRT) is introduced into each registry node to record the history of matches for selecting the repositories against incoming requests. The approach does not depend on the publishing mechanism of web service and the classification system for managing registries, and has not the constraint that all registries must conform to one shared ontology of concepts. [ABSTRACT FROM AUTHOR]

So far only rule-based knowledge has been taken into account in multiagent systems based on argumentation. Recent progress of the Semantic Web technology provides expressive ontology languages. In this paper, we present an integrated system of Semantic Web reasoning and argument-based reasoning, where the Logic of Multiple-valued Argumentation-based agent system (specialized to two values f, t) can inquire of the description logic reasoning system for ontologies that are lacking in agent's knowledge bases. Our approach contributes to advanced argumentative reasoning system with capabilities such as semantic web-based reasoning, which is shown by illustrating an interesting example of argumentation handling both rules and and ontologies. [ABSTRACT FROM AUTHOR]

In this paper, we present a method based on Expert Profiles (EP) for recommend system in ontological knowledge community in order to improve the efficiency of obtaining accurate knowledge in current Web. At first we improve Computable Context-Awareness Approach (CCAA) to fit a recommend system. Secondly, we design an indexing method to store links between keywords, which a domain expert often uses, and URLs in Search Profile (SP). Through computing semantic similarity between keywords, which a regular user inputs, and ones stored in SP, Search Engine (SE) can recommend pages, which are experts' searching history. Finally, we give an instance running on Nutch Search Engine. [ABSTRACT FROM AUTHOR]

In this paper we review two well-known citation methods to find relatedness between scientific papers: co-citation and bibliographic coupling. We propose a practical method to estimate the co-citation relatedness using the Google search engine. We call this method Web co-citation. We conducted experiments on a collection of scientific papers to compare the performances of different methods. The experimental results show that our approach, despite its simplicity, is efficient in discovering the relatedness between scientific papers. [ABSTRACT FROM AUTHOR]

In this paper, the web pages concerning products sale are analyzed with the aim to create clusters of similar web pages and characterize these by GUI patterns. We applied GD-CLS (gradient descent - constrained least squares) method which combines some of the best features of other methods. Both traditional methods for searching clusters and nonnegative matrix factorization are used. [ABSTRACT FROM AUTHOR]

As more information becomes available electronically, tools for finding information of interest to users become increasingly important. In this research, a personalized document filtering system with learning ability is designed and implemented. Each user puts one query in the system and five intelligent software agents rank each new document from their points of view. Three of these agents rank the document according to user's query, user's documents of interest in the profile, and user's group. The forth agent merges these scores and provides another score. Finally, the last agent corrects the obtained score by using previous estimated ranks and the judged ranks by the user. Using this agent that learns the users' behavior and adjusts the combination of the outputs of the other agents to estimate a rank for a document, results in a more accurate score than using each one (query, profile, or group) alone. We used LSI (Latent Semantic Indexing) method for documents and queries. [ABSTRACT FROM AUTHOR]

The problem of Authentication and Authorization is studied with an aim to trust the customer's transactions and to authorize the payment. Considering the limitation of the available methods and procedures, an improved trust metrics and variance based authorization model in e-commerce is proposed. The solutions proposed assess the deviation of the customers' transactions to calculate the Standard Deviation and employs normal distribution to assess the transaction to authorize. The model was applied on the customers' transactions and the results were studied that are promising to employ in e-commerce systems. [ABSTRACT FROM AUTHOR]

The Web is part of today's life and offers all kind of content. We present a system that can help the user to extract information from web documents and to find the answer for simple questions in natural language. This work is focused on newspaper articles and it is based on an ontology knowledge representation, natural language processment and a logic-programming framework. [ABSTRACT FROM AUTHOR]

Summary The analysis of query logs over a search engine provides valuable information on the user needs. Query clustering allows for the identification of similar queries and forms the basis for recommendations and query personalization. In this study, we propose constraint-based query clustering to enhance the query grouping process: Prior knowledge about the similarity of given queries is used to guide the formation of clusters, thus resulting in more homogeneous and reliable groups. We apply the constraint-based clustering algorithm C-DBSCAN [10] on query logs and show that constraints improve cluster quality. [ABSTRACT FROM AUTHOR]

The paper introduces several aspects of electronic content characteristics with their emphasis into Distance Learning technologies. They all have to be taken under consideration before the application development process starts. They also have to be defined in case the developer wants to run the on-line mode, of distance learning environment. To fulfil the given goals several items of management shell were introduced. The elaborated platform (Multimedia Applications Management Shell - MAMS), for applications development was introduced as well. Both platforms are simplifying the application structure and the unit control processes. The MAMS is supported by Quality Repetitions Unit (QRU) controlling the application progress and application repetition; working in accordance with Kay's [1], [2] interactive model. Finally they both produce the application status, transmitted into the user's personal data record. [ABSTRACT FROM AUTHOR]

It is widely recognized that online product reviews by users in sites such as amazon.com are biased in several dimensions including those due to the sequence in which the reviews are written as well as the benefit (monetary or otherwise) that the reviewer gains from writing a review. Although the latter is obvious and is often practiced by stakeholders wanting to promote their products (e.g., [2], [3], [4], [7]), the former is not entirely innocuous since subsequent reviews are not completely independent of preceding reviews by others. [ABSTRACT FROM AUTHOR]

Emerging Web services standards enable the development of large-scale applications in open environments. In particular, they enable services to be dynamically discovered and invoked. Our research objective is to propose new paradigms for interactions among semantic web services and software agents for problem solving. Agents are autonomous entities capable of acting on behalf of their user while Semantic Web services offer a new potential of automation in e-Work and e-Commerce, where fully open and flexible cooperation can be achieved on-the-fly. We believe that real goal of semantic web can only be realized if the semantic content associated with it can be read and interpreted. Since agent infrastructure has well-established reasoning, decision making and interaction mechanisms, it can contribute exceptionally in this regard. In this paper, we discuss the issue of negotiation between agents and semantic web services and propose architecture that enables negotiation between these heterogeneous entities. [ABSTRACT FROM AUTHOR]

In this paper we present an overview of the architectural design of the BiTutor which is a Bayesian Intelligent Tutoring System. This is an on-going research whose final goal is to build an open Intelligent Tutoring System (ITS). Every component of the architecture has its own strategies and tools that makes it intelligent. This makes the entire system posses adaptive capabilities. The design includes web-based distributed architecture, AI techniques used and programmer-optimized user interface. It is hypothesized that the completed prototype will be sufficient to prove the concept. A fully developed BiTutor will provide an interactively-rich learning environment for students that will result in increased achievement. [ABSTRACT FROM AUTHOR]

Recently, mobile RFID (Radio Frequency Identification) services such as in smart poster or supply chain are rapidly growing up as a newly generating industry. Here, mobile RFID service is defined as a special type of mobile service using RFID tag packaging object and RFID reader attached mobile RFID terminal. This paper is to provide an approach for ensuring RFID net-work security based on security engineering method. To ensure secure mobile RFID service network, we describes an approach which includes security state and security flow. We propose an efficient phone-based middleware platform architecture which is constructed by mobile RFID security mechanism based on WIPI (Wireless Internet Platform for Interoperability). WIPI-based light-weight mobile RFID security platform can be applied to various mobile RFID services that need secure business in mobile environment. So, we will propose the way to protect the personal privacy effectively using privacy preference for secure mobile RFID systems in ubiquitous network on this paper. [ABSTRACT FROM AUTHOR]

In this paper, we propose a Web Decision Support System for Impacts Assessment of Urban Mobility (WDSS4IA) which is based on a new approach. The latter uses fuzzy set theory for modeling criteria, belief theory for evaluations fusion from various information sources and it is able to handle uncertainty and vagueness. In this paper, the WDSS4IA is presented, focusing on its conception, modules and functionalities. [ABSTRACT FROM AUTHOR]

Ontology evaluation is as important as its designing and application. Researchers have identified different errors which should be catered in ontology evaluation process and classified them in error's taxonomy. We have found that some important errors are missing in the error's taxonomy. We have identified and defined new errors i.e. sufficient knowledge omis-sion error (SKO) and redundancy disjoint relation error (RDR) and catego-rized them in appropriate category of error's taxonomy. [ABSTRACT FROM AUTHOR]

The paper presents a new formalization for firewall systems, called the Unified Firewall Model (UFM). It offers an abstraction over firewall implementations, and uses formal concepts of Rule-Based Systems to describe firewall syntax and semantics. It is backed by the XTT/ARD design methods. It allows for improving system quality, by introducing a formal verification during the design stage. [ABSTRACT FROM AUTHOR]

The study introduces six new quality measures for linguistic summaries of databases. The basic Yager approach [6], with further improvements [1, 2], based on fuzzy logic, is considered. The informativeness of summaries is discussed, and the new measures are applied in the extended version of the algorithm (introduced in [3]) which enables automated generating of textual descriptions of databases, possibly applied in WWW or RSS news, press comments, etc. [ABSTRACT FROM AUTHOR]

This paper presents some issues inherent to the semantic indexing of resources in decentralized peer to peer networks. We first present a scenario that fixes the objectives of the indexing. We also explain the way to construct indexing keys in relation with ontologies. We also describe the way to distribute the global index through the nodes of the network and the way to retrieve resources. Then, we discuss some problems relative to the semantic indexing of personal resources respecting the previous requirements. [ABSTRACT FROM AUTHOR]

Content-based [6] and collaborative-based methods [7] [8] [9] are two main underlying techniques used in recommendation system. Some researchers proposed hybrid recommendation method to compromise the advantages and disadvantages of content-based and collaborative recommendation approaches [4] [10]. These three approaches share the common goal of assisting in the user's search for items of interest not recommending themselves to other users. For friend recommendation, we proposed a graph-based method, in this research, named Weighted Information Ratio (WIR) borrowed idea from information theory [1] [2]. We compare the method WIR with our prior algorithm in friend recommendation named Minimum-message Ratio (WMR) [3]. The precision and recall of WMR method are 15% and 8% for a target member with 15 recommendations in the testing prediction, respectively. This result is acceptable compared to a hybrid recommender system for digital library [4], where the testing precision and recall are 3% and 14% for 100 customers. Both recommendation algorithms generate a limited, ordered and personalized friend lists by the real communication number among web users. Communication number is more representative than most of the population variables because they are lack of diversity [5]. [ABSTRACT FROM AUTHOR]

In the Web service community, services may be exchanged among distributed environments. Actually, web services are described in terms of ontologies. When ontologies are distributed, arises the problem of achieving sematic interoperability. This problem is undertaken by a process which defines rules to relate relevant parts of different ontologies, called "Ontology Mapping". The present paper describes a methodology for automatic and semantic mapping of ontologies, basing our approach on a mathematical model called Information FlowModel and denoted IF Model. [ABSTRACT FROM AUTHOR]

Ontology-driven Web Services composition represents a novel approach to provide value added services or to improve services availability. Here we describe how ontology can be exploited to express the composition criteria, which can be automatically processed to obtain different workflows with the same semantic. Each workflow can be used to generate an orchestrated or a chorographical execution plan, whose actor contributes to provide the final service. We present a simple implementation as proof of concept using an OWL description of the composition criteria and the JENA APIs to process it. [ABSTRACT FROM AUTHOR]

Clustering of text documents is an important data mining issue and has wide application fields. However, many clustering approaches fail to yield high clustering quality because of the complex document semantics. Recently, semantic smoothing, which has been widely studied in the field of Information Retrieval, is proposed as an efficient solution. However, the existing semantic smoothing methods are not effective for partitional clustering. In this paper, based on the principle of TF*IDF schema, we propose an improved semantic smoothing method which is suitable for both agglomerative and partitional clustering. The experimental results show our method is more effective than the previous methods in terms of cluster quality. [ABSTRACT FROM AUTHOR]

We have shown that nondeterministic fuzzy finite automata (or NFFAs, for short) and deterministic fuzzy finite automata (or DFFAs, for short) are not necessary to be equivalent in the previous work. We continue to study the approximation of fuzzy finite automata in this paper. In particular, we show that we can approximate an NFFA by some DFFA with any given accuracy even the NFFA is not equivalent to any DFFA, related construction is also presented. Some characterizations of NFFA and DFFA are given. [ABSTRACT FROM AUTHOR]

With the rapid development of ubiquitous computing technology in the home and community, users can access information anytime and anywhere via personal devices such as PDA and internet mobile device. Ubiquitous application will need flexible access control mechanisms and more suitable access control decisions. Also context awareness throughout intelligent system is emphasized in order to provide automatic services in future home system. In this paper, we use a variety of device for collecting data from events for users in the home. This data is stored in the form of cases. This case form of data is used as training data for learning with a neural network algorithm, and the result is applied to an intelligent context aware system for future home automation. This system provides the intelligence required to "right situations do right things" for users. Consequently, the proposed system is an intelligent one. [ABSTRACT FROM AUTHOR]

In order to provide diverse users an integrated, scalable and easy-to-use interface to manage and exploit the dynamically growing learning resources on the Web, this paper proposes a semantic resource management framework to support the effective organizing and accessing of learning re-sources in an open environment. By exploiting the semantic relationships that characterize learning resources and user profile, the framework supports both semantic querying and conceptual navigation of learning resources pertaining to specific topics. A system has been developed and deployed within an academic setting to improve the resource management and exploitation for cooperative research. [ABSTRACT FROM AUTHOR]

The proper balance between a symmetric and asymmetric cell division is crucial for the neural stem cell maintenance both in vitro and in vivo. These conditions are provided by specific regions of the brain called neural stem cell niches and in vitro occur in neurospheres or adherent clones. A method and a tool for cell culture growth monitoring applied in the investigation of the clonally growth of HUCB-NSC (Human Umbilical Cord Blood derived Neural Stem Cells) line, as an in vitro model of the neural stem cell niche, is proposed. [ABSTRACT FROM AUTHOR]

The problem of knowledge sharing is eminent in the P2P area. In this paper, we propose a general framework, called semantic community, which is conceived for supporting dynamic ontology-based knowledge sharing and evolution in P2P systems. The knowledge sharing and evolution processes in semantic community are based on peer ontologies which are describing the knowledge of each peer, and on interactions among peers. This paper exploits an ontology matching algorithm to identify semantic affinity of two concepts. According to the semantic affinity threshold, the founder has to evaluate which peers are admitted in the community. [ABSTRACT FROM AUTHOR]

For most of us the term Web user profile should contain user's URL address, sometimes user's name and e-mail address, and some other components such as employeeŠs region and home organization if the user belongs to some company. However, when we think on a Web-based patient education that allows for the delivery of educational content to the patient, or on e-learning communities and on a system that serves each individual of the community, this information may not be sufficient. In the latter case the user profile should contain personal preferences of the individual, goals and needs, as well as the history of activity in the community, while in the former - patient parameters describing user's history, results of recent examinations, type of disease and so on. If mobile communicators are used (i.e. WAP) the CC/PP profile appears which is a more complex collection of capabilities and preferences associated with the user such as the user's position (which can change with time), and the characteristic of the user's hardware (e.g.phone). [ABSTRACT FROM AUTHOR]

This paper addresses the issue of how to define clusters of web visitors with respect to their behavior and supposed interests. We will use the non-obvious user profiles (NOPs) approach defined in [10], and present a new clustering algorithm which is a combination of hierarchical clustering together with a centroid based method with priority, which allows to cluster web users by similar interest in several topics. [ABSTRACT FROM AUTHOR]

In this paper we present a novel method for qualitative assessment of educational resources, specifically 'test problems'. For test problems, the basic elements of design are in the form of concepts arranged in a hierarchy. Course concept knowledge can be represented in the form of prerequisite relation based ontology using which, assessment and information extraction from test problems is possible. Using a schema based on Web Ontology Language (OWL), course ontologies can be represented in a standard and sharable way. Some synthetic parameters for the assessment of a test problem in its concept space are introduced. The assessment system can be further extended to analyze any type educational resource. [ABSTRACT FROM AUTHOR]

Today's CF systems fail to protect users' privacy. Without privacy protection, it becomes a challenge to collect sufficient and high quality data for CF. With privacy protection, users feel comfortable to provide more truthful and dependable data. In this paper, we propose to employ randomized response techniques (RRT) to protect users' privacy while producing accurate referrals using naïve Bayesian classifier (NBC), which is one of the most successful learning algorithms. We perform various experiments using real data sets to evaluate our privacy-preserving schemes. [ABSTRACT FROM AUTHOR]

A major difficulty of supervised approaches for text classification is that they require a great number of training instances in order to construct an accurate classifier. This paper proposes a semi-supervised method that is specially suited to work with very few training examples. It considers the automatic extraction of unlabeled examples from the Web as well as an iterative integration of unlabeled examples into the training process. Preliminary results indicate that our proposal can significantly improve the classification accuracy in scenarios where there are less than ten training examples available per class. [ABSTRACT FROM AUTHOR]

An important challenge regarding resource selection in Grid is how to cope with the wide range of selection and the high degree of strangeness. In this paper, reputation evaluation mechanism, as a fundamental building block technique, is introduced to leverage the guarantee of trustworthiness and reliability. Guided by the reputation evaluation ideas and fuzzy logic, the proposed approach can better handle uncertainty, fuzziness, and incomplete information, so the security of information service is highly strengthened. By applying the approach using eBay transaction statistical data, the paper demonstrate the final integrative decision order in various conditions. Compared with other methods, this approach has better overall consideration, accord with human selection psychology naturally. [ABSTRACT FROM AUTHOR]

Conventional web-based systems for knowledge sharing cannot help users determine the reliability of an unknown knowledge source on the web. This paper introduces an approach for using the concepts of trust and recommendation from social networks in web-based knowledge sharing systems. A simulation study of three algorithms for calculating trust inferred from recommendations on a social network is presented. The results show that our proposed algorithms can calculate inferred trust values for over 99% of the entities in the network with a high degree of accuracy. Finally, a prototype MAS system that uses trust and recommendation in knowledge sharing is described1. [ABSTRACT FROM AUTHOR]

The new method, based on automatic understanding is proposed for fighting spam in web information exchange (especially email correspondence). The web cancer term is used to reflect the variety and sophistication of web contaminations. The notable oncology achievements in medicine could inspire more research towards finding solutions to what can easily turn into an analogous civilization crisis. Automatic understanding is appropriate for the semantic-level content analysis and is expected to substantially reduce the wasted user time for semi-automatic analysis needed for the massive processing as most filters are too tight or too loose. [ABSTRACT FROM AUTHOR]

In this paper, we present a fast and scalable Bayesian model for improving weakly annotated data — which is typically generated by a (semi) automated information extraction (IE) system from Web documents. Weakly annotated data suffers from incorrect ontological role assignments. Our experimental evaluations with the TAP and a collection of 20,000 home pages from university, shopping and sports Web sites, indicate that the model described here can improve the accuracy of role assignments from 40% to 85% for template driven sites, from 68% to 87% for non-template driven sites. [ABSTRACT FROM AUTHOR]

Semantic Web technologies in general and ontology-based approaches in particular are considered the foundation for the next generation of information services. While ontologies enable software agents to exchange knowledge and information in a standardized, intelligent manner, describing todayŠs vast amount of information in terms of ontological knowledge remains a challenge. In this paper we describe the research project AVALON - Acquisition and VAL-idation of ONtologies, which aims at reducing the knowledge acquisition bottleneck by using methods from ontology learning in the context of a cybernetic control system. We will present techniques allowing us to automatically extract knowledge from textual data and formulating hypothesis based upon the extracted knowledge. Based on real world indicators, like for example business numbers, hypotheses are validated and the result is fed back into the system, thereby closing the cybernetic control system's feedback loop. While AVALON is currently under development, we will present intermediate results and the basic idea behind the system. [ABSTRACT FROM AUTHOR]

The use of online collaboration environments has become exceptionally widespread over the past decade. One of the most popular styles of collaboration are the "wiki" web sites. They have attracted attention because of their policy of letting anyone become an editor. This paper presents the technique for the analysis and visualization of Wikipedia - the largest wiki in existence. Specifically, it concentrates on some activity patterns of its contributors. First, a new visualization and analysis tool named JWikiVis is presented. Second, with the use of this software, some interesting user behaviors are described. Finally, text classification algorithms are applied in order to determine some patterns observed in individual wiki pages as well as in the entire service. [ABSTRACT FROM AUTHOR]

In this paper we introduce the IdentityRank algorithm developed to address the problem of named entity disambiguation. It is used for semantic annotation of Web resources taking Wikipedia as knowledge source. [ABSTRACT FROM AUTHOR]

In this note we consider design of a learning provisioning subsystem for an agentbased virtual organization. Flexible delivery of learning content is based on matching of ontologically demarcated user profiles, domain specific knowledge and learning modules. [ABSTRACT FROM AUTHOR]

In this paper we would like to propose a new hybrid scheme for learning approximate concepts and causal relations among them using information available from the Web. For this purpose we are applying fuzzy cognitive maps (FCMs) as a knowledge representation method and an analytical tool. Fuzzy cognitive maps are a decision-support tool, analytical technique, and a qualitative knowledge representation method with large potential for real world applications. FCMs are able to express the behavior of a system through the description of cause and effect relationships among concepts. FCMs can be represented as directed graphs consisting of concepts (nodes) and cause and effect relationships (branches) among them. The concepts represent states that are observable within the domain. The directions of branches indicate the causal dependency between source and target concepts. In spite of a quite simple construction and relatively easy interpretation, which can play a key role while constructing decision support systems, it's expected that FCMs can express complex behaviors of dynamic systems. The basic formalism of FCMs is presented in section 2. Obviously, there are also drawbacks of FCMs, that have been mentioned, e.g., in [4]. Also, it can be mentioned that, among the many extensions to FCMs, there is still lack of common formalism, which causes some difficulties when comparing one with another. [ABSTRACT FROM AUTHOR]