Determining Initial Starting Conditions for Documents Clustering

Clustering is an efficient technique that organizes a large quantity of unordered text documents into a small number of significant and coherent clusters, thereby providing a basis for intuitive and informative navigation and browsing mechanisms. It is studied by the researchers at broad level because of its broad application in several areas such as web mining, search engines, and information extraction. It clusters the documents based on various similarity measures. The existing K-means (document clustering algorithm) was based on random center generation and every time the clusters generated was different In this paper, an Improved Document Clustering algorithm is given which generates number of clusters for any text documents based on fixed center generation, collect only exclusive words from different documents in dataset and uses cosine similarity measures to place similar documents in proper clusters. Experimental results showed that accuracy of proposed algorithm is high compare to existing algorithm in terms of F-Measure, Recall, Precision and time complexity.

Data Mining and Knowledge Discovery, 2005

Fast and high-quality document clustering algorithms play an important role in providing intuitive navigation and browsing mechanisms by organizing large amounts of information into a small number of meaningful clusters. In particular, clustering algorithms that build meaningful hierarchies out of large document collections are ideal tools for their interactive visualization and exploration as they provide data-views that are consistent, predictable, and at different levels of granularity. This paper focuses on document clustering algorithms that build such hierarchical solutions and (i) presents a comprehensive study of partitional and agglomerative algorithms that use different criterion functions and merging schemes, and (ii) presents a new class of clustering algorithms called constrained agglomerative algorithms, which combine features from both partitional and agglomerative approaches that allows them to reduce the early-stage errors made by agglomerative methods and hence improve the quality of clustering solutions. The experimental evaluation shows that, contrary to the common belief, partitional algorithms always lead to better solutions than agglomerative algorithms; making them ideal for clustering large document collections due to not only their relatively low computational requirements, but also higher clustering quality. Furthermore, the constrained agglomerative methods consistently lead to better solutions than agglomerative methods alone and for many cases they outperform partitional methods, as well.

2017 13th International Computer Engineering Conference (ICENCO), 2017

K-means algorithm is a well-known clustering algorithm due to its simplicity. Unfortunately, the output of k-means depends on the initialization of cluster centroids. In this paper, we propose a new hybrid approach for document clustering which uses the outputs of single pass clustering (SPC) as an initialization for k-means algorithm. We aim to get the advantages of careful seeding with single pass clustering and the benefits of k-means algorithm. The experimental results state that the proposed approach outperforms traditional k-means algorithm in both unsupervised and supervised evaluation measures especially when the number of required clusters is increased.

… conference on Knowledge discovery and data mining

Clustering is a powerful technique for large-scale topic discovery from text. It involves two phases: first, feature extraction maps each document or record to a point in high-dimensional space, then clustering algorithms automatically group the points into a hierarchy of clusters. We describe an unsupervised, near-linear time text clustering system that offers a number of algorithm choices for each phase. We introduce a methodology for measuring the quality of a cluster hierarchy in terms of F-Measure, and present the results of experiments comparing different algorithms. The evaluation considers some feature selection parameters (tfidfand feature vector length) but focuses on the clustering algorithms, namely techniques from Scatter/Gather (buckshot, fractionation, and split/join) and kmeans. Our experiments suggest that continuous center adjustment contributes more to cluster quality than seed selection does. It follows that using a simpler seed selection algorithm gives a better time/quality tradeoff. We describe a refinement to center adjustment, "vector average damping," that further improves cluster quality. We also compare the near-linear time algorithms to a group average greedy agglomerative clustering algorithm to demonstrate the time/quality tradeoff quantitatively.

2019

2006

The steady increase of information on WWW, digital library, portal, database and local intranet, gave rise to the development of several methods to help user in Information Retrieval, information organization and browsing. Clustering algorithms are of crucial importance when there are no labels associated to textual information or documents. The aim of clustering algorithms, in the text mining domain, is to group documents concerning with the same topic into the same cluster, producing a flat or hierarchical structure of clusters. In this paper we present a Knowledge Discovery System for document processing and clustering. The clustering algorithm implemented in this system, called Induced Bisecting k-Means, outperforms the Standard Bisecting k-Means and is particularly suitable for on line applications when computational efficiency is a crucial aspect.

2014

Clustering is an automatic learning technique aimed at grouping a set of objects into subsets or clusters. Objects in the same cluster should be as similar as possible, whereas objects in one cluster should be as dissimilar as possible from objects in the other clusters. Document clustering has become an increasingly important task in analysing huge documents. The challenging aspect to analyse the enormous documents is to organise them in such a way that facilitates better search and knowledge extraction without introducing extra cost and complexity. Document clustering has played an important role in many fields like information retrieval and data mining. In this paper, first Document Clustering has been proposed using Hierarchical Agglomerative Clustering and K-Means Clustering Algorithm.Here, the approach is purely based on the frequency count of the terms present in the documents where context of the documents are totally ignored. Therefore, the method is modified by incorporati...

2016

As the number of electronic documents generated<br> from worldwide source increases, it is hard to manually<br> organize, analyze and present these documents efficiently.<br> Document clustering is one of the traditionally data mining<br> techniques and an unsupervised learning paradigm. Fast and<br> high quality document clustering algorithms play an<br> important role in helping users to effectively navigate,<br> summarize and organize the information. K-Means algorithm<br> is the most commonly used partitioned clustering algorithm<br> because it can be easily implemented and is the most efficient<br> one in terms of execution times. However, the major problem<br> with this algorithm is that it is sensitive to the selection of<br> initial centroid and may converge to local optima. The<br> algorithm takes the initial cluster centre arbitrarily so it does<br> not always guarantee good clustering resu...

Automatic document clustering has played an important role in the field of information retrieval. The aim of the developed this system is to store documents in clusters and to improve its retrieval efficiently. Clustering is a technique aimed at grouping a set of objects into clusters. Document clustering is the task of combining a set of documents into clusters so that similar type of documents will be store in one cluster. We applied non overlapping method to store document into cluster. In this project, we write an algorithm which will calculate similarity of document’s keywords and according to its similarity points it will either put into existing cluster or new cluster is created and stored into that cluster. To find keywords from document various techniques are used like tokenization, stop word removal, stemmer, TF*IDF calculation

2016

In today's era of World Wide Web, there is a<br> tremendous proliferation in the amount of digitized text<br> documents. As there is huge collection of documents on the web,<br> there is a need of grouping the set of documents into clusters.<br> Document clustering plays an important role in effectively<br> navigating and organizing the documents. K-Means clustering<br> algorithm is the most commonly document clustering algorithm<br> because it can be easily implemented and is the most efficient one<br> in terms of execution times. The major problem with this<br> algorithm is that it is quite sensitive to selection of initial cluster<br> centroids. The algorithm takes the initial cluster center arbitrarily<br> so it does not always promise good clustering results. If the initial<br> centroids are incorrectly determined, the remaining data points<br> with the same similarity scores may fall into the dif...

Data & Knowledge Engineering, 2010

The use of centroids as prototypes for clustering text documents with the k-means family of methods is not always the best choice for representing text clusters due to the high dimensionality, sparsity, and low quality of text data. Especially for the cases where we seek clusters with small number of objects, the use of centroids may lead to poor solutions near the bad initial conditions. To overcome this problem, we propose the idea of synthetic cluster prototype that is computed by first selecting a subset of cluster objects (instances), then computing the representative of these objects and finally selecting important features. In this spirit, we introduce the MedoidKNN synthetic prototype that favors the representation of the dominant class in a cluster. These synthetic cluster prototypes are incorporated into the generic spherical k-means procedure leading to a robust clustering method called k-synthetic prototypes (k-sp). Comparative experimental evaluation demonstrates the robustness of the approach especially for small datasets and clusters overlapping in many dimensions and its superior performance against traditional and subspace clustering methods.

Document Clustering is the collection of similar documents into classes and the similarity is some function on the document. Document Clustering need not require any separate training process and manual tagging group in advance. The documents used in the same clusters are more similar, while the documents used in different clusters are more dissimilar. It is one of the familiar technique used in data analysis and is used in many areas including data mining, statistics and image analysis. The traditional clustering approaches lose its algorithmic approach when handling high dimensional data. For this, a new K-Means Clustering technique is proposed in this work. Here Cosine Similarity of Vector Space Model is used as the centroid for clustering. Using this approach, the documents can be clustered efficiently even when the dimension is high because it uses vector space representation for documents which is suitable for high dimensions.

Over the past few decades, the volume of existing text data increased exponentially. Automatic tools to organize these huge collections of documents are becoming unprecedentedly important. Document clustering is important for organizing automatically documents into clusters. Most of the clustering algorithms process document collections as a whole; however, it is important to process these documents dynamically. This research aims to develop an incremental algorithm of hierarchical document clustering where each document is processed as soon as it is available. The algorithm is based on two well-known data clustering algorithms (COBWEB and CLASSIT), which create hierarchies of probabilistic concepts, and seldom have been applied to text data. The main contribution of this research is a new framework for incremental document clustering, based on extended versions of these algorithms in conjunction with a set of traditional techniques, modified to work in incremental environments.

Künstliche Intelligenz (KI, 2001

Text clustering typically involves clustering in a high dimensional space, which appears difficult with regard to virtually all practical settings. In addition, given a particular clustering result it is typically very hard to come up with a good explanation of why the text clusters have been constructed the way they are. In this paper, we propose a new approach for applying background knowledge during preprocessing in order to improve clustering results and allow for selection between results. We preprocess our input data applying an ontology-based heuristics for feature selection and feature aggregation. Thus, we construct a number of alternative text representations. Based on these representations, we compute multiple clustering results using K-Means. The results may be distinguished and explained by the corresponding selection of concepts in the ontology. Our results compare favourably with a sophisticated baseline preprocessing strategy.

KDD workshop on text mining, 2000

This paper presents the results of an experimental study of some common document clustering techniques. In particular, we compare the two main approaches to document clustering, agglomerative hierarchical clustering and K-means. (For K-means we used a "standard" K-means algorithm and a variant of K-means, "bisecting" K-means.) Hierarchical clustering is often portrayed as the better quality clustering approach, but is limited because of its quadratic time complexity. In contrast, K-means and its variants have a time complexity which is linear in the number of documents, but are thought to produce inferior clusters. Sometimes K-means and agglomerative hierarchical approaches are combined so as to "get the best of both worlds." However, our results indicate that the bisecting K-means technique is better than the standard K-means approach and as good or better than the hierarchical approaches that we tested for a variety of cluster evaluation metrics. We propose an explanation for these results that is based on an analysis of the specifics of the clustering algorithms and the nature of document data. 1 Background and Motivation Document clustering has been investigated for use in a number of different areas of text mining and information retrieval. Initially, document clustering was investigated for improving the precision or recall in information retrieval systems [Rij79, Kow97] and as an efficient way of finding the nearest neighbors of a document [BL85]. More recently, clustering has been proposed for use in browsing a collection of documents [CKPT92] or in organizing the results returned by a search engine in response to a user's query [ZEMK97]. Document clustering has also been used to automatically generate hierarchical clusters of documents [KS97]. (The automatic generation of a taxonomy of Web documents like that provided by Yahoo!