A blogosphere is a representative example of online social networks. In this paper, we address spectral analysis of a blogosphere. We model a real-world blogosphere as a matrix and a tensor, and then analyze it by using the SVD and PARAFAC decomposition. According to the results, the SVD successfully identified communities, each of which focuses on a specific topic, and also found hub blogs and authoritative posts within each community. The PARAFAC decomposition also succeeded in extracting more communities of finer granules than the SVD. Also, the PARAFAC decomposition could identify the dominant keywords in addition to the hub blogs and authoritative posts honored in each community.

In a blog network, there are special users who induce other users to actively utilize blogs. Identifying such influential users is important when establishing business policy and business models for the blog network. This paper defines the users whose contents exhibit significant influence over other users as content power users (CPUs) and proposes a method of identifying them. We analyze the performance of the proposed method by applying it to an actual blog network and comparing its results with those of preexisting methods for determining power users. The experimental results demonstrate that the definition of CPUs is adequate to address the dynamic nature of the blogosphere and the main concerns of the blog industry. We also discuss the business models based on CPUs that could be used to stimulate user activities in a blog network.

New types of document collections are being developed by various web services. The service providers keep track of non-textual features such as click counts. In this paper, we present a framework to use non-textual features to predict the quality of documents. We also show our quality measure can be successfully incorporated into the language modeling-based retrieval model. We test our approach on a collection of question and answer pairs gathered from a community based question answering service where people ask and answer questions. Experimental results using our quality measure show a significant improvement over our baseline.

There has recently been a significant increase in the number of community-based question and answer services on the Web where people answer other peoples' questions. These services rapidly build up large archives of questions and answers, and these archives are a valuable linguistic resource. One of the major tasks in a question and answer service is to find questions in the archive that a semantically similar to a user's question. This enables high quality answers from the archive to be retrieved and removes the time lag associated with a community-based system. In this paper, we discuss methods for question retrieval that are based on using the similarity between answers in the archive to estimate probabilities for a translation-based retrieval model. We show that with this model it is possible to find semantically similar questions with relatively little word overlap.

A large number of question and answer pairs can be collected from question and answer boards and FAQ pages on the Web. This paper proposes an automatic method of finding the questions that have the same meaning. The method can detect semantically similar questions that have little word overlap because it calculates question-question similarities by using the corresponding answers as well as the questions. We develop two different similarity measures based on language modeling and compare them with the traditional similarity measures. Experimental results show that semantically similar questions pairs can be effectively found with the proposed similarity measures.

It has been known that using different representations of either queries or documents, or different retrieval techniques retrieves different sets of documents. Recent work suggests that significant improvements in retrieval performance can be achieved by combining multiple representations or multiple retrieval techniques. In this paper we propose a simple method for retrieving different documents within a single query representation, a single document representation and a single retrieval technique. We classify the types of documents, and describe the properties of weighting schemes. Then, we explain that different properties of weighting schemes may retrieve different types of documents. Experimental results show that significant improvements can be obtained by combining the retrieval results from different properties of weighting schemes.

The retrieval models based on the extended boolean retrieval framework, e.g., the fuzzy set model and the extended boolean model have been proposed in the past to provide the conventional boolean retrieval system with the document ranking facility. However, due to undesirable properties of evaluation formulas for the AND and OR operations, the former generates incorrect ranked output in certain cases and the latter suffers from the complexity of computation. There have been a variety of fuzzy operators to replace the evaluation formulas. In this paper we first investigate the behavioral aspects of the fuzzy operators and address important issues to affect retrieval effectiveness. We then define an operator class called positively compensatory operators giving high retrieval effectiveness, and present a pair of positively compensatory operators providing high retrieval efficiency as well as high retrieval effectiveness. All the claims are justified through experiments.

In order to improve the two-level signature file method designed by Sacks-Davis et al. [20], we propose new multikey access methods based on term discrimination and signature clustering. By term discrimination, we create separate, efficient access methods for the terms frequently used in user queries. We in addition cluster similar signatures by means of these terms so that we may achieve good performance on retrieval. Meanwhile we provide the space-time analysis of the proposed methods and compare them with the two-level signature file method. We show that the proposed methods achieve 15-30% savings in retrieval time and require 3-9 % more storage overhead.