Search

Document classification has become an indispensable technology to realize intelligent information services. This technique is often applied to the tasks such as document organization, analysis, and archiving or implemented as a submodule to support high-level applications. It has been shown that semantic analysis can improve the performance of document classification. Although this has been incorporated in previous automatic document classification methods, with an increase in the number of documents stored online, the use of semantic information for document classification has attracted greater attention as it can greatly reduce human effort. In this present paper, we propose two semantic document classification strategies for two types of semantic problems: (1) a novel semantic similarity computation (SSC) method to solve the polysemy problem and (2) a strong correlation analysis method (SCM) to solve the synonym problem. Experimental results indicate that compared with traditional machine learning, n-gram, and contextualized word embedding methods, the efficient semantic similarity and correlation analysis allow eliminating word ambiguity and extracting useful features to improve the accuracy of semantic document classification for texts in Chinese.

Virtual worlds have become global platforms connecting millions of people and containing various technologies. For example, No Man&rsquo, s Sky (nomanssky.com), a cross-platform virtual world, can dynamically and automatically generate content with the progress of user adventure. AltspaceVR (altvr.com) is a social virtual reality platform supporting motion capture through Microsoft&rsquo, s Kinect, eye tracking, and mixed reality extension. The changes in industrial investment, market revenue, user population, and consumption drive the evolution of virtual-world-related technologies (e.g., computing infrastructure and interaction devices), which turns into new design requirements and thus results in the requirement satisfaction problem in virtual world system architecture design. In this paper, we first study the new or evolving features of virtual worlds and emerging requirements of system development through market/industry trend analysis, including infrastructure mobility, content diversity, function interconnectivity, immersive environment, and intelligent agents. Based on the trend analysis, we propose a new design requirement space. We, then, discuss the requirement satisfaction of existing system architectures and highlight their limitations through a literature review. The feature-based requirement satisfaction comparison of existing system architectures sheds some light on the future virtual world system development to match the changing trends of the user market. At the end of this study, a new architecture from an ongoing research, called Virtual Net, is discussed, which can provide higher resource sufficiency, computing reliability, content persistency, and service credibility.

With the rise of social media, much attention has been focused on it to collect the data from it, which gives us a novel scientific way to investigate some classic questions about individual and social aspects of our life. This paper researches on such a study based on the previous studies. We demonstrate that there is no relationship between movie box office revenue and social media data. This paper applies the second hottest social media application: Twitter, to analyze the relationship between movie box office revenue and Tweets through Pearson correlation coefficient.

In global e-commerce, semantic document exchange ensures unambiguity and shares same meaning for documents sender and receiver cross different natural languages (e.g., English to Chinese), as the difference makes the translation between cross-language documents complex and inaccurate. This paper proposed a novel collaborative framework of semantic document exchange through a mediation approach which provides a sentence-based machine natural language (MNL). Here, the MNL constructs a grammatical case structure to compatible with all languages. Thus, the mediation framework enables the sentence computer-readable and understandable without ambiguity, simultaneously the MNL can improve accuracy and reduce the complexity of mapping in semantic document exchange.

Multi-agent collaboration in the agent oriented Collective Adaptive Systems could offset the failure of goal achievement by an independent agent. Commitments among agents to meld collaborative patterns typically defined in design time, which may cannot service the request of ACSs in response to changes in the system itself or in its environment. To address this problem, we propose a Goal-Capability-Commitment (GCC) based multi-agent collaboration mediation for ACSs at run-time. There are two issues with this state of the art approach: (1) the ability to represent the capability of agent under different contexts and diagnose the invalids of goals and agents leaded by the changing environments, and (2) the ability of mediation to select an appropriate capability or generate a new commitment in order to satisfy adaptive goal. We illustrate our approach through two experiments over the simulated scenario of automated hospital cart transportation system and discuss the results of experiments.

Question classification is an essential part of Question Answering system(QA). This paper introduces our research work on automatic question classification that depends on the sample set including questions from legal forum. We propose a taxonomy for law question, and divide questions into three main parts: civil, criminal and administrative according to Chinese legal system. We have experimented with four machine learning algorithms: Nearest Neighbors (NN), Naïve Bayes (NB), Logistic Regression (LR) and Support Vector Machines (SVM) using two kinds of features: TF-IDF and word2vec embeddings. Further, we used fastText and adjusted the parameters to get the better results. The research shows high accuracy in Chinese question classification in law domain. Moreover, to the best of our knowledge, our work is the first attempt in this promising domain.

Heterogeneous device services generated by various devices in different contexts prevent users from efficiently and correctly consuming device services. This seriously hinders the development of Internet of Things. This paper addresses the problems appearing in device discovery and device interaction. It devises a user interoperability framework (UIF) to enable device users to interoperate with heterogeneous devices of different contexts with consistent syntax and semantics. In this framework, a new separation strategy is provided; a device representation method for real, common, and virtual devices is devised; and a device transformability model is proposed to guarantee the proper transformation of device syntax and semantics. To demonstrate the correctness of UIF, a UIF prototype is implemented and several experiment methods are compared to determine which one should be adopted as semantic relatedness computing tools in device discovery for device users and in common device publishing for device providers.

This research is to show that functions are the indispensable elements for e-marketplace construction, and that basic functions in particular are able to meet the demand for highly interoperable and cost-effective e-marketplaces. Specifically, this research relies heavily on historical literature event methodology by studying existing electronic marketplaces through thousands of research papers, ranging among 1,221 articles published in journals and conferences over the period of 1986-2012. Based on the basic functions generated from the function published year and the function counted quantity, this research eventually shows that e-marketplace designers, facilitators, buyers, and sellers will be able to construct and select a suitable e-marketplace automatically for their diverse purposes.

The explosive growth of the World Wide Web leads to the fast advancing development of e-commerce techniques. Recommender systems, which use personalised information filtering techniques to generate a set of items suitable to a given user, have received considerable attention. User- and item-based algorithms are two popular techniques for the design of recommender systems. These two algorithms are known to have Cold-Start problems, i.e., they are unable to effectively handle Cold-Start users who have an extremely limited number of purchase records. In this paper, we develop TrustRank, a novel recommender system which handles the Cold-Start problem by leveraging the user-trust networks which are commonly available for e-commerce applications. A user-trust network is formed by friendships or trust relationships that users specify among them. While it is straightforward to conjecture that a user-trust network is helpful for improving the accuracy of recommendations, a key challenge for using user-trust networ...

Nowadays social network services have been popularly used in electronic commerce systems. Users on the social network can develop different relationships based on their common interests and activities. In order to promote the business, it is interesting to explore hidden relationships among users developed on the social network. Such knowledge can be used to locate target users for different advertisements and to provide effective product recommendations. In this paper, we define and study a novel community detection problem that is to discover the hidden community structure in large social networks based on their common interests. We observe that the users typically pay more attention to those users who share similar interests, which enable a way to partition the users into different communities according to their common interests. We propose two algorithms to detect influential communities using common interests in large social networks efficiently and effectively. We conduct our experimental evaluation using a data set from Epinions, which demonstrates that our method achieves 4–11.8% accuracy improvement over the state-of-the-art method.

In e-business, semantic document exchange is a methodology of providing exchangeable semantic documents, which ensures users and computers to share a same understanding in meaning on any exchanged document across heterogeneous contexts. Two kinds of Pinyin input method for word senses such as Word-based input method and Sentence-based input method are proposed. These two kind of word sense based Pinyin input method is based on the statistic language model of word sense representation and disambiguation. The prototype system shows both our Word-based and Sentence-based word sense Pinyin methods are promising in the semantic document editing system. These two kinds of Pinyin input methods of word senses are designed for our semantic document edit system for the semantic document exchange in e-business.

To support automatic document exchange, one essential issue is to maintain the consistency of semantic interpretation of the exchanged documents between any two autonomous communities, where the document sender and receiver have no misunderstanding in using the exchanged documents. However, different document systems often lead to heterogeneous documents in terms of syntax and semantics, which are difficult to make consistent interpretation and reasonable inference from one context to another. This paper proposes a novel tabular document exchange framework consisting of a tabular document model for semantic consistency maintenance of exchanged documents and a semantic inference scheme for automatic new document creation.

Virtual world has the potential to become a future global electronic market. It integrates many isolated markets in many areas. To achieve this goal, future virtual world is required to be persistent, which means that a virtual world together with its accumulated content shall exist forever regardless of dynamic changes of its virtual world users and virtual world owners. This paper addresses the persistence issue by proposing a decentralized redundancy model which is immune from the possible collapse of virtual world. The core work in this model is the selection of a redundancy level, which is based on cost optimization. The simulation results show that the proposed redundancy management approach is optimal compared with existing approaches.

An electronic marketplace (e-marketplace) is a common business information space populated with many entities of different system types. Each of them has its own context of how to process activities. This leads to heterogeneous e-marketplace activities, which are difficult to make interoperable and inferred from one entity to another. This study solves this problem by proposing a concept of separation strategy and implementing it through providing a semantic inference engine with a novel inference algorithm. The solution, called the RuleXPM approach, enables one to semantically infer a next e-marketplace activity across multiple contexts/domains. Experiments show that the cross-context/cross-domain semantic inference is achievable. This paper is an understanding of many aspects related to heterogeneous activity inference.

This article presents pioneering research on virtual money exchange (VMX) to protect the wealth generated in virtual worlds. This goal is realized by designing and implementing a VMX system through which virtual money exchange rates between virtual worlds are generated based on a redistribution strategy. Moreover, this strategy aims to re-value the total intrinsic value and the total exchangeable value of virtual currencies at a series of Pareto exchange points. We have designed, implemented, proved and extended a novel VMX exchange rate algorithm (VERA) algorithm, which implements the redistribution strategy. In order to observe the behavior of virtual money exchange rate generations, we built a VMX simulator to simulate various cases of virtual money exchange. Experiments on our VMX simulator show that minimum acceptable virtual exchange rates set by exchange requestors have a great impact on the success or failure of a virtual money exchange. This suggests the need for further research to reconcile the contradiction between presenting fair virtual currency exchange rates and achieving low fluctuations of virtual currency exchange rates. Finally, this research contributes to a better understanding of many aspects relating to virtual money, virtual currency exchange and virtual wealth protection. These are important for the future design and implementation of integrated virtual worlds.

This article presents pioneering research on measuring virtual wealth in an open virtual world for diagnosing the health of virtual worlds. It proved the existence of an open virtual world by proving the existence of a free choice of virtual currencies for virtual goods between distinct virtual worlds. By discussing the features of open virtual world in a circled networked organization, the article devised a virtual wealth measuring scheme, called Gross Virtual Product (GVP), for any virtual world. Based on this scheme, it suggested an accountability matrix to account for a changing virtual world regarding its total virtual wealth, profitability, user participation and happiness. To demonstrate the suitability of GVP scheme and accountability matrix, the article has conducted a case study on SecondLife.com, which showed the appropriateness of the proposed scheme and matrix. The research made in this article is very important. The proposed measuring scheme and matrix help virtual world participants perceive the possible risks of the participated virtual worlds in advance to make better decisions on virtual business.

The maintenance of semantic consistency between numerous heterogeneous electronic product catalogues (EPC) that are distributed, autonomous, interdependent and emergent on the Internet is an unsolved issue for the existing heterogeneous EPC integration approaches. This article attempts to solve this issue by conceptually designing an interoperable EPC (IEPC) system through a proposed novel collaborative conceptualisation approach. This approach introduces collaboration into the heterogeneous EPC integration. It implies much potential for future e-marketplace research. It theoretically answers why real-world EPCs are so complex, how these complex EPCs can be explained and articulated in a product map theory for heterogeneous EPC integration, how a semantic consistency maintenance model can be created to satisfy the three heterogeneous EPC integration conditions and implemented by adopting a collaborative integration strategy on a collaborative concept exchange model, and how this collaborative integration strategy can be realised on a collaboration mechanism. This approach has been validated through a theoretical justification and its applicability has been demonstrated in two prototypical e-business applications.

There is an increasing demand for doing business online, which calls for higher business interoperability on business-to-business (B2B) electronic market places (EMp). This drives the development of integration technologies for improving B2B electronic market (EM) functions on EMp. This paper argues that with the development of integration technologies companies will use more private, community and public EMp and select their proper type of EMp when comparing the function-cost ratios of business interoperability on different types of B2B EMp. This argument has been validated through the case studies against a method of historical event analysis. In this shift, four integration factors of standard flexibility, enterprise integration, service provision and semantic integration are constantly improving EMp functions, which lead to an overall reduction of interaction cost for business interoperation on all types of EMp. This will change business behaviour and corporate strategies of most firms, and have important implications for firms to make strategies of how to select EMp to increase business interoperability for higher competitiveness.

Exact document interpretation is very important to semantic document exchange. An essential issue for document interpretation is to maintain semantic consistency of the exchanged documents between any two autonomous business communities, where the document sender and receiver have no misunderstanding in using the exchanged documents. Existing approaches to resolving this issue adopt document standards or apply business ontologies. While these approaches are effective in certain degree, the issue of limited flexibility and evolvement in using standards and the lack of accuracy in using ontologies to mediate document elements must be explored and resolved. This paper proposes a multi-viewed tabular document (Tabdoc) approach to achieving consistent document interpretation between document writers and readers. In this approach, any document is a table, which is seen as a tree to represent document structure. Concepts, layout and grammatical relations of a same document are separated from the document structure and form different views in Tabdoc model.

An electronic marketplace (e-marketplace) is a common business information space populated with many entities of different system types. Each of them has its own context of how to build and process documents. This leads to heterogeneous e-marketplace documents in terms of syntax and semantics, which are difficult to make interoperation and inference from one entity to another. This paper proposes CCDR approach to make a semantic inference on received documents in a realistic e-business scenario and implements the reasoning procedure by developing SDR system which integrates with a novel inference algorithm.

Exact document interpretation is very important to semantic document exchange. An essential issue for document interpretation is to maintain syntactic and semantic consistency of the exchanged documents between any two autonomous business communities, where the document sender and receiver have no misunderstanding in using the exchanged documents. Existing approaches to resolving this issue mainly adopt document standards. While these approaches are effective in certain degree, the issue of limited flexibility and evolvement in using standards must be explored and resolved. This paper proposes a multi-viewed tabular document (Tabdoc) approach consisting of a Tabdoc model and a document processing procedure to achieving consistent document interpretation between document writers and readers. In this approach, any document is a table, which is seen as a tree to represent document structure. Concepts, layout and grammatical relations of a same document are separated from the document structure and form different views in Tabdoc model.

This paper investigates the context representation of ad hoc product data that distribute in different semantic communities especially in small and medium sized enterprises through the analysis of the problems in extracting, mediating and comparing product contexts. The problem analysis leads to a proposal for a novel context representation model that separates the representation process into two steps: transform irregular local product definitions into canonical local product representations and map canonical local product representations onto common product representations. This model serves as the foundation to further compare product contexts between different semantic communities.

Existing peer-to-peer systems focus on mono-type service provision, such as file sharing or file storage. If it is required to build more complex applications on peer-to-peer networks such as a virtual world application, they have to be extended to hosting diversified services. To achieve this, we propose a peer-to-peer platform on which peer computers can jointly host a file, a website, or a program. Users of our platform can utilize spare hardware resource on peer computers to host their own services. They pay the hosting cost to peers for hardware resources utilization. The problem is how to minimize hosting cost while maintain required service availability. This problem becomes difficult when peers are strategic. In this paper, we provide a procurement mechanism is provided to solve this problem by inducing peers reporting their true hosting cost and availability.

Brachydactyly type A-1 (BDA1) was, in 1903, the first recorded example of a human anomaly with Mendelian autosomal dominant inheritance. Two large families, the affected members of which were radiographed, were recruited in the study we describe here. Two-point linkage analysis for pedigree 1 (maximum LOD score [Zmax] 6.59 at recombination fraction [theta] 0.00) and for pedigree 2 (Zmax=5.53 at straight theta=0.00) mapped the locus for BDA1 in the two families to chromosome 2q. Haplotype analysis of pedigree 1 confined the locus for family 1 within an interval of8.1 cM flanked by markers D2S2248 and D2S360, which was mapped to chromosome 2q35-q36 on the cytogenetic map. Haplotype analysis of pedigree 2 confined the locus for family 2 within an interval of28. 8 cM flanked by markers GATA30E06 and D2S427, which was localized to chromosome 2q35-q37. The two families had no identical haplotype within the defined region, which suggests that the two families were not related.

Peer-to-peer network and application have boomed for the recent decade. However, Network Address Translation (NAT) devices obstruct its wide application by restricting the access to peers from private network. In this paper, we devise a peer strongly connected model to adapt Kademlia protocol to NAT-involved environment to minimize the impact on routine algorithm and meanwhile to make the target system reliable and scalable. Evaluation shows that our organization model highly outperforms existing model in delivery rate and scalability.

Resolving context differences between heterogeneous systems for global information interoperability is a challenging research issue in information technology. This paper solved the problem by suggesting a new concept of Open Information Platform (OIP) that builds on the two principles of naturalization and alienation. Following these two principles, an SCI methodology has been proposed to require standardization of information, collaborative creation of atomic signs and internalization of standardized information to hide complex standards behind final users. To implement the SCI method, an OIP technical infrastructure is implemented. The short history of information interoperability research signifies that OIP concept is important and is a natural outcome towards the future technology for information exchange and use.

In e-business, creating a common vocabulary for business integration, interoperation and interaction has to consider the heterogeneity reality of different interpretations from multiple term providers. Maintaining semantic consistency between multiple vocabulary providers is a difficult problem. To solve this problem, this paper proposes a novel cross-context collaborative vocabulary editing approach. This approach introduces a semantically consistent representation for terms, vocabularies and operations. It presents a cross-context semantic consistency maintenance model. To satisfy this model, it achieves context commonality by proposing a distributed, two-layered, role-based, and partially-replicated system architecture. It achieves concept equivalence by collaborative term mapping, multi-copy and arbitration. It satisfies structure mappability through a novel term identifier scheme. An integrated DO-scheme of ADD, MODIFY, DELETE and ARBITRATE has been devised to discuss an integrated solution to cross-context semantic consistency maintenance. The proposed vocabulary editing system has been implemented in a CHCES system.

Legal transfer of electronic title document across heterogeneous contexts is a challenging research problem in e-commerce and implies a wider e-commerce transaction scope. This kind of title transfer requires semantic consistency, confidentiality, integrity and legality between transferor and transferee. During the title transfer, cross-context semantic consistency must first be maintained between electronic title documents for legal title transfer while other requirements are considered. To solve the problem, this paper proposes a Cross-Context E-Title (CCET) approach, which satisfies the requirements for title transfer. Based on CCET approach, a CCET prototype is further implemented, on which some experiments are made to test the correctness and performance of the proposed approach.

Creating semantically consistent multilingual vocabulary is challenging to concept engineering, natural language process (NLP) and collaborative editing for cross-domain meaning understanding. This paper proposes a novel method of automatic concept mapping (My Lang Mapper) between multilingual dictionaries (same as bilingual dictionary, abbreviated as BD) and the Princeton’s WordNet (WN) to derive vocabulary for e-marketplace. It is heuristically developed following the analysis on the senses of words appeared in both WN and BD. By this approach, a word association categorization scheme is introduced to categorize words in WN and BD for achievement analysis, and proposed approach with two patterns of automatic words mapping are created to disambiguate the meaning of words being mapping. This approach’s implement and experiment result show that the proposed method is a good complement of the existing collaborative concept editing for vocabulary building method. It suggests that collaborative work for vocabulary building can be significantly reduced.

With the advance of the Internet, e-commerce systems have become extremely important and convenient to human being. More and more products are sold on the web, and more and more people are purchasing products online. As a result, an increasing number of customers post product reviews at merchant websites and express their opinions and experiences in any network space such as Internet forums, discussion groups, and blogs. So there is a large amount of data records related to products on the Web, which are useful for both manufacturers and customers. Mining product reviews becomes a hot research topic, and prior researches mostly base on product features to analyze the opinions. So mining product features is the first step to further reviews processing. In this paper, we present how to mine product features. The proposed extraction approach is different from the previous methods because we only mine the features of the product in opinion sentences which the customers have expressed their positive or negative experiences on. In order to find opinion sentence, a SentiWordNet-based algorithm is proposed. There are three steps to perform our task: (1) identifying opinion sentences in each review which is positive or negative via SentiWordNet; (2) mining product features that have been commented on by customers from opinion sentences; (3) pruning feature to remove those incorrect features. Compared to previous work, our experimental result achieves higher precision and recall.

In e-business development, semantics-oriented document exchange is becoming important, because it can support cross-domain user connection, business transaction and collaboration. To provide this support, this paper proposes a DOC Mechanism to exchange semantically interoperable business documents between heterogeneous enterprise information systems. This mechanism is designed on a layered-sign network, which enables any exchanged e-business document to be independently interpretable without losing semantic consistency.

In e-business, creating a common concept set for business integration, interoperation and interaction has to consider the heterogeneity reality of different interpretations from multiple concept providers. Maintaining semantic consistency between multiple concept providers is a difficult problem. To solve this problem, this paper first reviewed the existing technologies of collaborative editing systems and consistency maintenance in the areas of both CSCW and e-business. Based on the discussion of existing technologies, it then proposes a novel CHCES approach, which divides a collaborative editing system into two layers in topology and introduces four strategies to edit common concepts between the two layers. A set of operations is designed, which demonstrates the solution.

In this article, we propose a method for business information query expansions. In our approach, hypernym/hyponymy and synonym relations in WordNet are used as the basic expansion rules. Then we use WordNet Lexical Chains and WordNet semantic similarity to assign terms in the same query into different groups with respect to their semantic similarities. For each group, we expand the highest terms in the WordNet hierarchies with hypernym and synonym, the lowest terms with hyponym and synonym and all other terms with only synonym. In this way, the contradictory caused by full expansion can be well controlled. Furthermore, we use collection-related term semantic network to further improve the expansion performance. And our experiment reveals that our solution for query expansion can improve the query performance dramatically.

A meaningful e-marketplace (MEMP) is a common business information space where computer agents can faithfully deliver the true meanings of e-trade with each other on behalf of their human masters. Partial understanding of any received e-trade information is forbidden since it hides unfavorable legal consequences. MEMP is a new concept. This paper discusses it by putting forward a framework, which consists of four important procedures of design, reification, transformation and inference. The important features of MEMP are representation personalization and localization, accurate cross-domain message exchange, true result reasoning, context-based reification, and model-free template design and use. In future, a successful realization of MEMP in design will drastically change our existing e-trade modes, lift the quality of e-business, and lead to a more efficient e-marketplace brought by higher accuracy of meaning understanding, broader scope of business interaction, and richer e-trade functions.

E-marketplace activities initiated by users in general require representing the user requirements and preferences matched with a set of offerings. One issue of these activities is the heterogeneity among them, which asks for semantic consistency maintenance. This paper solves this problem by applying collaborative concept exchange technology and developing a novel RuleXPM approach. This approach transforms XPM reified documents into rule-based RuleXPM documents that are suitable for making cross-domain inference on heterogeneous e-marketplace activities, using defeasible reasoning on a newly designed RuleXPM Inference Engine made from a RuleXPM Inference Algorithm.

As World Wide Web is becoming the most important information repository, increasing amount of information is available. Currently, web search engines can only provide document oriented searches. In order to fully make use of information from the web, some effective and efficient extraction algorithms are definitely desirable. In this paper, some existing achievements are investigated firstly. Then our current technique on web information extraction is discussed in detail. In our approach, rules and patterns are extracted from sample pages through training process, with human involvements. We use both keywords and regular expressions to represent rules and patterns in our system. The keywords work as anchors to locate the positions of the potential information and regular expressions work as validations of the values. In our system, all the extracted information is represented in XML format.

In this paper, we provide a novel image annotation model by mining the Web. In our approach, the concepts or words appearing in the associated text are extracted and filtered as the semantic annotations for the corresponding Web images. In order to alleviate the influence caused by the noise images, for each semantic concept, we improve Web image-word relationships using Mixture Gaussian Distribution Model. By doing so, the concepts or words relevant to any image are re-weighed by both considering their relevance to the image in term of text and in term of visual feature. In fact, all the words associated to an image are not semantically independent. We use co-occurrences between two words to describe their semantic relevance. Thus, we further use a method, called Word Promotion, to co-enhance the weights of all the words associated to a given image based on their co-occurrences. Our experiments are conducted in several ways and the results show that our annotation method can achieve a satisfactory performance.

Establishing an open virtual money exchange regime is a novel idea but rarely discussed. This paper provides a pioneer research on virtual money exchange (VONEX) approach, aiming to facilitate the exchange of virtual currencies among a variety of heterogeneous virtual communities. It has defined the intrinsic value and exchangeable value of virtual currencies and suggested a redistribution strategy, constituting the theoretical foundation of the virtual exchange rate system, by which a novel VONEX exchange rate algorithm is derived. Further to the introduction of the algorithm, a proof is given to ensure its correctness.

The explosive web make it hard to organize and manage web information automatically. Therefore, online learning method such as incremental learning is gradually become effective instrument in practical applications. From our experiments, traditional incremental learning shows some flaws in the iterative process. To overcome the drawback caused by using only support vector to represent the whole former dataset, we embedded some additional information to enhance the effect of support vectors to solve the problem. Our experiment results reveal the proposed algorithm could obtain better results.

In this paper, we studied the semantic consistency maintenance issue between heterogeneous contexts, that is, how a firm' business process of one e-marketplace can be transformed to another firm's business process of another e-marketplace in a semantically consistent way. The proposed solution of this paper uses XML Product Map (XPM) of collaborative concept to represent semantically consistent business processes, and adopts common action concept pool and XPM documents to design heterogeneous business processes that are suitable for heterogeneous business process transformation. We motivated the approach with a real-world PVC poncho trade problem and explained it in architecture of collaborative process design and automatic service provision. We reported the implementation specification within a hybrid human-agent framework, where four layers of system modules are specified. The approach is evaluated based on a new semantic impact chain method particularly for evaluating concept consistency in meaning representation between heterogeneous contexts of business processes.

In this paper we study the semantic consistency maintenance issue between heterogeneous contexts, that is, how an inquiry from an unknown user of an e-marketplace can be received and answered in a semantically consistent way by a firm that is not in the context of the userpsilas e-marketplace. The proposed solution uses XPM to represent semantically consistent business concepts and adopts defeasible logic to reason with XPM document-oriented business rules for inquiring and offering. We motivate the approach with a real-world apartment rental problem, and explain it in architecture of collaborative business process design and automatic service provision. Finally, we report on an implementation specification within a hybrid human-agent framework.

EM2I’07 is a new venue for presenting state-of-the-art research and development achievements in the design, introduction, and use of integration technology for electronic marketplaces that affect business interoperability between firms and within supply chains. Although traditional forms of e-marketplaces such as intermediaries, supplier portals, and content hubs are an important area of focus, integration technology is increasingly supporting a much wider range of business interoperability that enables contextually heterogeneous enterprises to semantically work together beyond operational transactions. As more and more firms in all regions of the globe are able to interact online, we are rapidly moving toward an integrated global e-marketplace consisting of loosely coupled vertical, horizontal, and regional e-marketplaces.

When developing hotel information platform, the service providers face an important issue, how to attract more hotels to join in their platform without significantly increasing integration cost but maintaining effective information integration? This paper considers the issue in two aspects of business integration policy and technology support, which bring up a novel hotel power policy approach for service providers to define different hotel partners and integrate heterogeneous hotel information. With this approach, a hotel information collaboration platform is proposed to implement the hotel power policy for integrating the complex real-world hotel information.

The heterogeneous concept mapping (HCM) approach of collaborative concept exchange (CONEX) supports the multilingual business information exchange between heterogeneous e-business systems, but it unexplored the issue of semantic consistency maintenance in the constant value translation. This paper discusses this issue with a proposal of contextual value translation (CAT) approach to complementing the previous HCM research. This approach provides the solution to facilitate the multilingual translation of business concept values with semantic consensus.