Mining Sentiment Using Conversation Ontology

The research in the field of opinion mining has been ongoing for several years, and many models and techniques have been proposed. One of the techniques that can address the need for automated information monitoring to help to identify the trends and patterns that matter is sentiment mining. Existing approaches enable the analysis of a large number of text documents, mainly based on their statistical properties and possibly combined with numeric data. Most approaches are limited to simple word counts and largely ignore semantic and structural aspects of content. Conversation plays a vital role in expressing and promoting an opinion. In this chapter, the authors discuss the concept of ontology and propose a framework that allows the incorporation of information on conversation structure in the models for sentiment discovery in text.

An Ontology-Based Search Tool in the Semantic Web

The chapter presents a meta-search tool developed in order to deliver search results structured according to the specific interests of users. Meta-search means that for a specific query, several search mechanisms could be simultaneously applied. Using the clustering process, thematically homogenous groups are built up from the initial list provided by the standard search mechanisms. The results are more user-oriented, thanks to the ontological approach of the clustering process. After the initial search made on multiple search engines, the results are pre-processed and transformed into vectors of words. These vectors are mapped into vectors of concepts, by calling an educational ontology and using the WordNet lexical database. The vectors of concepts are refined through concept space graphs and projection mechanisms, before applying the clustering procedure. The chapter describes the proposed solution in the framework of other existent clustering search solutions. Implementation details and early experimentation results are also provided.

Emergent Ontologies by Collaborative Tagging for Knowledge Management

The massive use of Internet and social networks leads us to a new dynamic environment with huge amounts of unstructured and unclassified information resources in continuous evolution. New classification, compilation, and recommendation systems based on the use of folksonomies and ontologies have appeared to deal with the requirements of data management in this environment. Nevertheless, using ontologies alone has some weaknesses due to the need of being statically modeled by a set of experts in a specific domain. On the other hand, folksonomies show a lack of formality because of their implicit ambiguity and flexibility by definition. The main objective of this chapter is to outline and evaluate a new way to exploit Web information resources and tags for bridging the gap between ontology modeling and folksonomies.

Intermediary Design for Collaborative Ontology-Based Innovation Monitoring

This chapter presents the architecture of an intermediary platform for networked open innovation management, as well as a surrounding sustainable business ecosystem. The instantiation presented here is tailored towards SMEs, both as stakeholders in the platform and as contributors in the modular ecosystem. It enables SMEs to work together in creating innovative products, increasing both reach and agility of their innovation processes. The chapter also describes to some detail the technical realization of the system, including the representation and automatic acquisition of relevant information. Selected business aspects are also addressed. It specifically focuses on the role of ontologies and how they contribute to the overall business value of the system.

Ontology-Based Opinion Mining

In this chapter, the authors discuss an ontology-based approach to opinion mining exploiting the possibility to represent commonly shared meaning of linguistic relations by ontologies. The ontology definitions are used as a standard to which sentences extracted from texts are compared. Unlike conventional text mining, which is based on objective topics aiming to discover common patterns of user opinions from their textual statements automatically or semi-automatically, it will extract opinion from subjective locations.

Identifying Polarized Wikipedia Articles

Wikipedia is one of the most successful worldwide collaborative efforts to put together user-generated content in a meaningfully organized and intuitive manner. Currently, Wikipedia hosts millions of articles on a variety of topics, supplied by thousands of contributors. A critical factor in Wikipedia’s success is its open nature, which enables everyone to edit, revise, and/or question (via talk pages) the article contents. Considering the phenomenal growth of Wikipedia and the lack of a peer review process for its contents, it becomes evident that both editors and administrators have difficulty in validating its quality on a systematic and coordinated basis. This difficulty has motivated several research works on how to assess the quality of Wikipedia articles. In this chapter, the authors propose the exploitation of a novel indicator for the Wikipedia articles’ quality, namely information credibility. In this respect, the authors describe a method that captures the polarized (i.e., biased) information across the article contents in an attempt to infer the amount of credible (i.e., objective) information every article communicates. This approach relies on the intuition that an article offering non-polarized information about its topic is more credible and of better quality compared to an article that discusses the editors’ (subjective) opinions on that topic.

Enterprise Tomography

Cloud Computing is finding its way into the architecture of current IT landscapes. The present chapter depicts an algorithm-based methodology supporting the Root-Cause-Analysis in the context of malfunctioning Federated ERP (FERP) software in Enterprise Clouds. The challenge is to standardize the error-finding procedure and increase the efficiency. For a given error symptom it is shown that the error location is approximated iteratively with help of generic operators in a semiautomatic manner. This approach of Semantic Debugging outperforms classical methods of Technical Debugging in efficiency regarding prerequisite knowledge and time consumption. Semantic integration and maintainability correlate strongly. The Delta-Operator enables the reconstruction of semantic FERP integration in the course of the error reproduction session. In combination with the Join-Operator, the defect approximation can be performed along the dependencies of semantic artifacts.

Ethical Tensions Emerging from the Application of the Collective Intelligence Concept in Academic Social Networking

This chapter examines the ethical questions and actions emerging from academic social networking. Academics have always been involved in rigorous discourse across multiple contexts, involving generation, exploration, analysis, evaluation, and application of ideas through a process of thought, research, peer validation, and publication. The argument is that the concept of collective intelligence is changing the traditional hierarchical “rules” associated with academic dialogue. Collective intelligence is defined as a mix of formal and informal conversational contexts, and the storing and sharing of ideas and information through multiple public online contexts. The meta-concept of collective intelligence presents a number of ethical dilemmas and questions related to privacy, and ownership and control of net-generated data, ideas, and information. The purpose of this chapter is to identify and describe these ethical issues and actions in relation to academic social networking.

Multimedia Systems Development

The multimedia information system represents a specific form of information system. This research area suffered many changes in direction due to technology shifts. The general problem is that few years back, multimedia technologies had been limited to relatively simple, stand-alone applications, but multimedia systems, particularly Web-based systems grew in complexity and intervened with many critical issues for development. In this chapter, a specific focus will be cast on existing methodology approaches, their upsides and downsides, and on the surveys and research done by distinguished authors in this area on what sort of methodologies are used in practice. Afterwards, the focus of this chapter will be on whether existing development methodologies can be applied to multimedia systems and if there is any need to adapt them for that specific purpose.

Ontology-Based Optimization in Search Engine

The major aim of the chapter is to propose and study the use of ontology-based optimization for positioning websites in search engines. In this sense, using heterogeneous inductive learning techniques and ontology for knowledge representation, a knowledge-based system which is capable of supporting the activity of SEO (Search Engine Optimization) has been designed and implemented. From its knowledge base, the system suggests the most appropriate optimization tasks for positioning a pair (keyword, website) on the first page of search engines and infers the positioning results to be obtained. The system evolution and learning capacity allows optimizing the productivity and effectiveness of the SEO process.