The Ethics of Social Information Retrieval

In this chapter we discuss some of the social and ethical issues associated with social information retrieval. Using the work of Habermas we argue that social networking is likely to exacerbate already disturbing trends towards the fragmentation of society and a corresponding decline reduction in social diversity. Such a situation is not conducive to developing a healthy, democratic society. Following the tradition of critical theorists of technology, we conclude with a call for responsible and aware technological design with more attention paid to the values embedded in new technological systems.

Publication and Citation Analysis as a Tool for Information Retrieval

In this chapter an overview of citation analysis is presented, emphasizing its formal aspects as applied social network theory. As such citation linking can be considered a tool for information retrieval based on social interaction. It is, indeed, well-known that following citation links is an efficient method of information retrieval. Relations with web linking are highlighted. Yet, also social aspects related to the act of citing, such as the occurrence of invisible colleges, are discussed. We present some recent developments and present our opinion on some future developments. In this way we hope that the reader will realize how the fields of citation analysis and webometrics can be helpful in building social information retrieval systems.

Relevant Intra-Actions in Networked Environments

This chapter uses a study of human assessments of relevance to demonstrate how individual relevance judgments and retrieval practices embody collaborative elements that contribute to the overall progress of that person’s individual work. After discussing key themes of the conceptual framework, the chapter will discuss two case studies that serve as powerful illustrations of these themes for researchers and practitioners alike. These case studies, outcomes of a two-year ethnographic exploration of research practices, illustrate the theoretical position presented in part one of the chapter, providing lessons for the ways that people work with information systems to generate knowledge and the conditions that will support these practices. The chapter shows that collaboration does not have to be explicit to influence searcher behavior. It seeks to present both a theoretical framework and case studies that can be applied to the design, development and evaluation of collaborative information retrieval systems.

Social Information Seeking in Digital Libraries

Information seeking is a complex task, and many models of the basic, individual seeking process have been proposed. Similarly, many tools now exist to support “sit-forward” information seeking by single users, where the solitary seeker interacts intensively with a search engine or classification scheme. However, in many situations, there is a clear interaction between social contexts beyond the immediate interaction between the user and the retrieval system.

Multi-Agent Tourism System (MATS)

This chapter proposes the architecture of the Multi-Agent Tourism System (MATS). Tourism information on the World Wide Web is dynamic and constantly changing. It is not easy to obtain relevant and updated information for individual user’s needs. A multi-agent system is defined as a collection of agents that work in conjunction with each other. The objective of MATS is to provide the most relevant and updated information according to the user’s interests. It consists of multiple agents with three main tiers such as the Interface Module, Information Management Module, and Domain Related Module. We propose the Rule-based Personalization with Collaborative Filtering Technique for effective personalization in MATS which can address the limitations of pure Collaborative Filtering such as the scalability, sparsity and cold-start problems.

Hybrid Recommendation Systems

Recommendation systems have been used in e-commerce sites to make product recommendations and to provide customers with information that helps them decide which product to buy. They are based on different methods and techniques for suggesting products with the most well known being collaborative and content-based filtering. Recently, several recommendation systems adopted hybrid approaches by combining collaborative and content-based features as well as other techniques in order to avoid their limitations. In this chapter, we investigate hybrid recommendations systems and especially the way they support movie e-shops in their attempt to suggest movies to customers. Specifically, we introduce an approach where the knowledge about customers and movies is extracted from usage mining and ontological data in conjunction with customer-movie ratings and matching techniques between customers. This integration provides additional knowledge about customers’ preferences and allows the production of successful recommendations. Even in the case of the cold-start problem where no initial behavioural information is available, the approach can provide logical and relevant recommendations to the customers. The provided recommendations are expected to have higher accuracy in matching customers’ preferences and thus higher acceptance by them. Finally, we describe future trends and challenges and discuss the open issues in the field.

Metadata for Social Recommendations

Social information retrieval systems, such as recommender systems, can benefit greatly from sharable and reusable evaluations of online resources. For example, in distributed repositories with rich collections of learning resources, users can benefit from evaluations, ratings, reviews, annotations, etc. that previous users have provided. Furthermore, sharing these evaluations and annotations can help attain the critical mass of data required for social information retrieval systems to be effective and efficient. This kind of interoperability requires a common framework that can be used to describe in a reusable manner the evaluation approach, as well as the results of the evaluation. This chapter discusses this concept, focusing on the rationale for a reusable and interoperable framework, that can be used to facilitate the representation, management and reuse of results from the evaluation of learning resources. For this purpose, we review a variety of evaluation approaches for learning resources, and study ways in which evaluation results may be characterised, so as to draw requirements for sharable and reusable evaluation metadata. Usage scenarios illustrate how evaluation metadata can be useful in the context of recommender systems for learning resources.

Collaborating to Search Effectively in Different Searcher Modes Through Cues and Specialty Search

Searchers generally have difficulty searching into knowledge repositories because of the quantity of data involved and because searcher mechanisms are not tailored to their differing needs at different points in time. Also, every searcher generally searches alone without taking into account other users with similar search needs or experience. While the Internet may have contributed to information overload, the connectivity it has provides the potential to different searchers to collaborate when looking for information. In this chapter, we 1) review concepts related to social information retrieval and existing collaborative mechanisms 2) discuss two collaborative mechanisms – cues and specialty search and 3) see cues and specialty search in the context of the changing needs of a searcher in one of four modes. A case study of an online portal for the Singapore education community is used to show how collaboration could enhance learning and search efficacy.

Personalized Information Retrieval in a Semantic-based Learning Environment

Active learning is the ability of learners to carry out learning activities in such a way that they will be able to effectively and efficiently construct knowledge from information sources. Personalized and customizable access on digital materials collected from the Web according to one’s own personal requirements and interests is an example of active learning. Moreover, it is also necessary to provide techniques to locate suitable materials. In this paper, we introduce a personalized learning environment providing intelligent support to achieve the expectations of active learning. The system exploits collaborative and semantic approaches to extract concepts from documents and maintaining user and resources profiles based on domain ontologies. In such a way, the retrieval phase takes advantage from the common knowledge base used to extract useful knowledge and produces personalized views of the learning system.

Adaptive Peer-to-Peer Social Networks for Distributed Content-Based Web Search

This chapter proposed a collaborative peer network application called 6Search (6S) to address the scalability limitations of centralized search engines. Each peer crawls the Web in a focused way, guided by its user’s information context. Through this approach, better (distributed) coverage can be achieved. Each peer also acts as a search “servent” (server + client) by submitting and responding to queries to/from its neighbors. This search process has no centralized bottleneck. Peers depend on a local adaptive routing algorithm to dynamically change the topology of the peer network and search for the best neighbors to answer their queries. We present and evaluate learning techniques to improve local query routing. We validate prototypes of the 6S network via simulations with model users based on actual Web crawls. We find that the network topology rapidly converges from a random network to a small world network, with clusters emerging from user communities with shared interests. We finally compare the quality of the results with those obtained by centralized search engines such as Google.