This paper presents the results of an experimental study of some common document clustering techniques: agglomerative hierarchical clustering and K-means. (We used both a “standard” K-means algorithm and a “bisecting ” K-means algorithm.) Our results indicate that the bisecting K-means technique is better than the standard K-means approach and (somewhat surprisingly) as good or better than the hierarchical approaches that we tested.

Previous research on cluster-based retrieval has been inconclusive as to whether it does bring improved retrieval effectiveness over document-based retrieval. Recent developments in the language modeling approach to IR have motivated us to re-examine this problem within this new retrieval framework. We propose two new models for cluster-based retrieval and evaluate them on several TREC collections. We show that cluster-based retrieval can perform consistently across collections of realistic size, and significant improvements over document-based retrieval can be obtained in a fully automatic manner and without relevance information provided by human.

A major challenge in document clustering is the extremely high dimensionality. For example, the vocabulary for a document set can easily be thousands of words. On the other hand, each document often contains a small fraction of words in the vocabulary. These features require special handlings. Another requirement is hierarchical clustering where clustered documents can be browsed according to the increasing specificity of topics. In this paper, we propose to use the notion of frequent itemsets, which comes from association rule mining, for document clustering. The intuition of our clustering criterion is that each cluster is identified by some common words, called frequent itemsets, for the documents in the cluster. Frequent itemsets are also used to produce a hierarchical topic tree for clusters. By focusing on frequent items, the dimensionality of the document set is drastically reduced. We show that this method outperforms best existing methods in terms of both clustering accuracy and scalability.

Hierarchic document clustering has been widely applied to Information Retrieval (IR) on the grounds of its potential improved effectiveness over inverted file search. However, previous research has been inconclusive as to whether clustering does bring improvements. In this paper we take the view that if hierarchic clustering is applied to search results (query-specific clustering), then it has the potential to increase the retrieval effectiveness compared both to that of static clustering and of conventional inverted file search. We conducted a number of experiments using five document collections and four hierarchic clustering methods. Our results show that the effectiveness of query-specific clustering is indeed higher, and suggest that there is scope for its application to IR.

Current best-match ranking (BMR) systems perform well but cannot handle word mismatch between a query and a document. The best known alternative ranking method, hierarchical clustering-based ranking (HCR), seems to be more robust than BMR with respect to this problem, but it is hampered by theoretical and practical limitations. We present an approach to document ranking that explicitly addresses the word mismatch problem by exploiting interdocument similarity information in a novel way. Document ranking is seen as a querydocument transformation driven by a conceptual representation of the whole document collection, into which the query is merged. Our approach is based on the theory of concept (or Galois) lattices, which, we argue, provides a powerful, well-founded, and computationallytractable framework to model the space in which documents and query are represented and to compute such a transformation. We compared information retrieval using concept lattice-based ranking (CLR) to BMR and HCR. The results showed that HCR was outperformed by CLR as well as by BMR, and suggested that, of the two best methods, BMR achieved better performance than CLR on the whole document set while CLR compared more favorably when only the first retrieved documents were used for evaluation. We also evaluated the three methods' specific ability to rank documents that did not match the query, in which case the superiority of CLR over BMR and HCR (and that of HCR over BMR) was apparent.

Cluster analysis divides data into groups (clusters) for the purposes of summarization or improved understanding. For example, cluster analysis has been used to group related documents for browsing, to find genes and proteins that have similar functionality, or as a means of data compression. While clustering has a long history and a large number of clustering techniques have been developed in statistics, pattern recognition, data mining, and other fields, significant challenges still remain. In this chapter we provide a short introduction to cluster analysis, and then focus on the challenge of clustering high dimensional data. We present a brief overview of several recent techniques, including a more detailed description of recent work of our own which uses a concept-based clustering approach. 1

Abstract not found

Clustering of related or similar objects has long been regarded as a potentially useful contribution to helping users navigate an information space such as a document collection. When documents are related by virtue of being about the same or similar topics, then this is often a good indicator that they will be relevant to the same queries and this can be used during the retrieval operation. Many clustering algorithms and techniques have been developed and implemented since the earliest days of computational information retrieval but as the sizes of document collections have grown these techniques have not been scaled to large collections because of their computational overhead. In this paper we describe a technique for clustering a collection of documents such as a collection of online newspapers which uses a number of short-cuts to make the process computable for large collections. Furthermore, our design is extensible in that it caters for a dynamic collection of documents which would be periodically, perhaps nightly, updated, amended or have deletions. An implementation of the clustering on an archive of the Irish Times newspaper is reported here. 1.

Abstract--Recall and Precision have become the principle measures of the effectiveness of information retrieval systems. Inherent in these measures of performance is the idea of a relevant document, Although recall and precision are easily and unambiguously defined, selecting the documents relevant to a query has long been recognized as problematic. To compare performance of different systems, standard collections of documents, queries, and relevance judgments have been used. Unfortunately the standard collections, such as SMART and TREC, have locked in a particular approach to relevance that is suitable for assessing precision but not recall. The problem is demonstrated by comparing two information retrieval methods over several queries, and showing how a new method of forming relevance judgments that is suitable for assessing recall gives different results. Recall is an interesting and practical issue, but current test procedures are inadequate for measuring it. Copyright ©

Recall and Precision have become the principle measures of the effectiveness of information retrieval systems. Inherent in these measures of performance is the idea of a relevant document. Although recall and precision are easily and unambiguously defined, selecting the documents relevant to a query has long been recognised as problematic. To compare performance of different systems, standard collections of documents, queries, and relevance judgements have been used. Unfortunately the standard collections, such as SMART and TREC, have locked in a particular approach to relevance and this has affected subsequent research. Two styles of information need are distinguished, high precision and high recall, and a method of forming relevance judgements suitable for each is described. The issues are illustrated by comparing two retrieval systems, keyword retrieval and semantic signatures, on different sets of relevance judgements. 2 Introduction Four decades of testing informatio...