DOCSLIB.ORG

Document Clustering Using K-Means and K-Medoids Rakesh Chandra Balabantaray*, Chandrali Sarma**, Monica Jha***

Total Page：16

File Type：pdf, Size：1020Kb

Download full-text PDF Read full-text
Document Clustering Using K-Means and K-Medoids Rakesh Chandra Balabantaray*, Chandrali Sarma**, Monica Jha*** Article can be accessed online at http://www.publishingindia.com Document Clustering using K-Means and K-Medoids Rakesh Chandra Balabantaray*, Chandrali Sarma**, Monica Jha*** Abstract clustering are big volume, high dimensionality and complex semantics. Our motive in the present paper is to With the huge upsurge of information in day-to-day’s life, extract particular domain of work from a huge collection it has become difficult to assemble relevant information of documents using K-Means and K-Medoids clustering in nick of time. But people, always are in dearth of algorithm and to obtain best clusters which later on time, they need everything quick. Hence clustering can be used for document summarizations. Document was introduced to gather the relevant information in clustering is a more specific technique for document a cluster. There are several algorithms for clustering organization, automatic topic extraction and fast IR1, information out of which in this paper, we accomplish which has been carried out using K-means clustering K-means and K-Medoids clustering algorithm and a algorithm implemented on a tool named WEKA2(Waikato comparison is carried out to find which algorithm is best Environment for Knowledge Analysis) and K-Medoids for clustering. On the best clusters formed, document algorithm is executed on Java NetBeans IDE to obtain summarization is executed based on sentence weight clusters. This allows a collection of various documents to focus on key point of the whole document, which makes it easier for people to ascertain the information from different domains to be segregated into groups of they want and thus read only those documents which similar domain. The best cluster obtained, then undergoes is relevant in their point of view. summarization to retrieve highest weighed sentences to reveal gist of the whole document. Keywords: Clustering, K-Means, K-Medoids, WEKA3.9, Document Summarization 2. Reviews Throughout these years, there has been a lot of work 1. Introduction implemented on document clustering using k-means by various researchers employing different means. Initially, Achievement of better efficiency in retrieval of relevant the researchers worked using the simple k-means information from an explosive collection of data is algorithm and then in later years, various modifications challenging. In this context, a process called document were executed. Use of K-mean clustering and Vector clustering can be used for easier information access. Space model was employed by using the text data by The goal of document clustering is to discover the treating it as high dimensional. It was shown that the time natural grouping(s) of a set of patterns, points, objects or taken for entire clustering process was linear in the size of documents. Objects that are in the same cluster are similar document collection [Indrajit S. Dhillon et.al. 2001]. Some among themselves and dissimilar to the objects belonging researchers found an effective technique for K-means to other clusters. The purpose of document clustering is clustering which proves that principal components to meet human interests in information searching and are the continuous solutions to the discrete cluster understanding. The challenging problems of document membership [Chris Ding et.al.2004]. Recently, work on * IIIT Bhubaneswar, Bhubaneswar, Odisha, India. E-mail: [email protected] ** Department of Information and Technology, Gauhati University, Guwahati, India. E-mail: [email protected] *** Department of Information and Technology, Gauhati University, Guwahati, India. E-mail: [email protected] 8 International Journal of Knowledge Based Computer System Volume 1 Issue 1 June 2013 the performance of the partition clustering techniques Same input is provided to both the algorithms and later on in terms of complex data objects and comparative after the algorithm implementation is over, the best cluster study of the cluster algorithm for corresponding data obtained is then used for document summarization. and proximity measure for specific objective function based on K-means and EM Algorithms was executed. 3.1. Collection of Datasets Comparison and evaluation clustering algorithms with multiple data sets, like text, business, and stock market At the beginning hundred documents were collected data was performed. Comparative study of clustering which consisted twenty each of Entertainment (e1, e2…. algorithms identified one or more problematic factors e20), Literature (l1, l2….l20), Sport (s1, s2….s20), such as high dimensionality, efficiency, scalability with Political (p1, p2.… p20) and Zoology (z1,z2,….z20). data size, sensitivity to noise in the data. [Satheelaxmi.G These documents undergo refinement which is fed to the et.al.2012]. Work by integrating the constraints into the algorithm to obtain clusters containing documents from trace formulation of the sum of square Euclidean distance similar domains. function of K-means by combining criterion function transformation into trace maximization was optimized by eigen-decomposition [Guobiao Hu et.al.2008]. Plentiful 3.2. Convert Documents into Vectors times work on K-means algorithm on WEKA model had been implemented in the past which in turn has improved A document usually consists of huge number of words, it the WEKA tool set. [Sapna Jain et al.2010]. Previously, is not always necessary that each word is of importance. work based on several datasets, including synthetic and Due to which, a document has high dimensionality has to real data, show that the proposed algorithm may reduce the be reduced. Hence processing is carried on a document number of distance calculations by a factor of more than to reduce this dimensionality and get rid of extra words a thousand times when compared to existing algorithms and to obtain weight of each of the word to be used in while producing clusters of comparable quality was the algorithm. Conversion of documents into vectors is carried out[Maria Camila N. et.al.2006]. Proposal of a carried in various steps. new language model, to simultaneously cluster and sum up at the same time has been implemented in past. The 3.2.1. Tokenization method implies good document clustering method with more meaningful interpretation and a better document All processes in information retrieval require the words of summarization method taking the document context the data set. The main use of tokenization is identifying information into consideration [Wang, Shenghuo Zhu et the meaningful keywords called tokens. Tokenization al.2008]. splits sentences into individual tokens, typically words. 3. Methodology 3.2.2. Stop-Words Removal Execution of algorithm is based on the input provided Collected documents contain some unnecessary words by to the algorithm. In this paper, the input provided to which dimensionality of a document will be increased; we the algorithm had to undergo certain refinement. The should remove those words to get proper result. Pronoun, experiment generally comprises of four major steps. adverb, preposition etc. which are used constantly throughout in a document has to be removed. Convert Documents into Collection of Datasets Vectors 3.2.3. Weight Calculation This step involves calculating the weight of each word twice, once using frequency of words and then using term Multi-document Clustering based frequency-inverse document frequency (tf-idf). summarization algorithm Document Clustering using K-Means and K-Medoids 9 a. Weight calculated using frequency 3.3. Clustering Based Algorithms Ratio of each word occurred in the document to the total Among various clustering based algorithm, we number of words in that document gives us weight. have selected K-means and K-Medoids algorithm. Weight = (frequency) ∏ (total number of words in a document) Implementation of K-means algorithm was carried out via b. Weight calculated using tf-idf method WEKA tool and K-Medoids on java platform. Using the same input matrix both the algorithms is implemented and The other method which is often used in information the results obtained are compared to get the best cluster. retrieval and text mining known as tf-idf weight, where K-Mean Clustering using WEKA Tool tf is the “Term Frequency” and is denoted tft,d with the subscripts denoting the term and the document in order To cluster documents, after doing preprocessing tasks and idf is the “Inverse Term Frequency”. The term vector we have to form a flat file which is compatible with for a string is defined by its term frequencies. If count WEKA tool and then send that file through this tool to (t,cs) is the count of term t in character sequence cs, then form clusters for those documents. This section will give the term frequency (TF) is defined by, a brief mechanism with WEKA tool and use of K-means Tf (t,cs) = sqrt(count(t,cs)) algorithm on that tool. WEKA has four applications Explorer, Experiment, Knowledge Flow and Simple CLI If df(t,docs) be the document frequency of token t i.e. the but here only Explorer application and the two fields from number of documents in which the token t appears, then this application i.e. preprocess and cluster fields are used. the inverse term frequency (IDF) of t is defined by, idf(t,docs) = log(D/df(t,docs)) Therefore if term weight is denoted by Wi then typically, Wi = TF * IDF 3.2.4. Weighted Matrix Formation A matrix had to be formed where we stored weight of each word in rows and in the column we had stored documents name. This matrix serves as the input for both the algorithm. For formation of this matrix we employ the idea from Vector Space Model (VSM)3 which is an algebraic model for representing text documents (and any objects, in general) as vectors of identifiers, such as, for 3.3.1. WEKA Data File Format (input) example, index term. Tw1 Tw2 Tw3 Tw4 Tw5 As it is already mentioned that weighted matrix is the input for the implementation of the algorithm, so an .arff d1 Ê 05.
Load more

Recommended publications
  • Probabilistic Topic Modelling with Semantic Graph
    Probabilistic Topic Modelling with Semantic Graph B Long Chen( ), Joemon M. Jose, Haitao Yu, Fajie Yuan, and Huaizhi Zhang School of Computing Science, University of Glasgow, Sir Alwyns Building, Glasgow, UK [email protected] Abstract. In this paper we propose a novel framework, topic model with semantic graph (TMSG), which couples topic model with the rich knowledge from DBpedia. To begin with, we extract the disambiguated entities from the document collection using a document entity linking system, i.e., DBpedia Spotlight, from which two types of entity graphs are created from DBpedia to capture local and global contextual knowl- edge, respectively. Given the semantic graph representation of the docu- ments, we propagate the inherent topic-document distribution with the disambiguated entities of the semantic graphs. Experiments conducted on two real-world datasets show that TMSG can significantly outperform the state-of-the-art techniques, namely, author-topic Model (ATM) and topic model with biased propagation (TMBP). Keywords: Topic model · Semantic graph · DBpedia 1 Introduction Topic models, such as Probabilistic Latent Semantic Analysis (PLSA) [7]and Latent Dirichlet Analysis (LDA) [2], have been remarkably successful in ana- lyzing textual content. Specifically, each document in a document collection is represented as random mixtures over latent topics, where each topic is character- ized by a distribution over words. Such a paradigm is widely applied in various areas of text mining. In view of the fact that the information used by these mod- els are limited to document collection itself, some recent progress have been made on incorporating external resources, such as time [8], geographic location [12], and authorship [15], into topic models.
    [Show full text]
  • A Hierarchical Clustering Approach for Dbpedia Based Contextual Information of Tweets
    Journal of Computer Science Original Research Paper A Hierarchical Clustering Approach for DBpedia based Contextual Information of Tweets 1Venkatesha Maravanthe, 2Prasanth Ganesh Rao, 3Anita Kanavalli, 2Deepa Shenoy Punjalkatte and 4Venugopal Kuppanna Rajuk 1Department of Computer Science and Engineering, VTU Research Resource Centre, Belagavi, India 2Department of Computer Science and Engineering, University Visvesvaraya College of Engineering, Bengaluru, India 3Department of Computer Science and Engineering, Ramaiah Institute of Technology, Bengaluru, India 4Department of Computer Science and Engineering, Bangalore University, Bengaluru, India Article history Abstract: The past decade has seen a tremendous increase in the adoption of Received: 21-01-2020 Social Web leading to the generation of enormous amount of user data every Revised: 12-03-2020 day. The constant stream of tweets with an innate complex sentimental and Accepted: 21-03-2020 contextual nature makes searching for relevant information a herculean task. Multiple applications use Twitter for various domain sensitive and analytical Corresponding Authors: Venkatesha Maravanthe use-cases. This paper proposes a scalable context modeling framework for a Department of Computer set of tweets for finding two forms of metadata termed as primary and Science and Engineering, VTU extended contexts. Further, our work presents a hierarchical clustering Research Resource Centre, approach to find hidden patterns by using generated primary and extended Belagavi, India contexts. Ontologies from DBpedia are used for generating primary contexts Email: [email protected] and subsequently to find relevant extended contexts. DBpedia Spotlight in conjunction with DBpedia Ontology forms the backbone for this proposed model. We consider both twitter trend and stream data to demonstrate the application of these contextual parts of information appropriate in clustering.
    [Show full text]
  • Query-Based Multi-Document Summarization by Clustering of Documents
    Query-based Multi-Document Summarization by Clustering of Documents Naveen Gopal K R Prema Nedungadi Dept. of Computer Science and Engineering Amrita CREATE Amrita Vishwa Vidyapeetham Dept. of Computer Science and Engineering Amrita School of Engineering Amrita Vishwa Vidyapeetham Amritapuri, Kollam -690525 Amrita School of Engineering [email protected] Amritapuri, Kollam -690525 [email protected] ABSTRACT based Hierarchical Agglomerative clustering, k-means, Clus- Information Retrieval (IR) systems such as search engines tering Gain retrieve a large set of documents, images and videos in re- sponse to a user query. Computational methods such as Au- 1. INTRODUCTION tomatic Text Summarization (ATS) reduce this information Automatic Text Summarization [12] reduces the volume load enabling users to find information quickly without read- of information by creating a summary from one or more ing the original text. The challenges to ATS include both the text documents. The focus of the summary may be ei- time complexity and the accuracy of summarization. Our ther generic, which captures the important semantic con- proposed Information Retrieval system consists of three dif- cepts of the documents, or query-based, which captures the ferent phases: Retrieval phase, Clustering phase and Sum- sub-concepts of the user query and provides personalized marization phase. In the Clustering phase, we extend the and relevant abstracts based on the matching between input Potential-based Hierarchical Agglomerative (PHA) cluster- query and document collection. Currently, summarization ing method to a hybrid PHA-ClusteringGain-K-Means clus- has gained research interest due to the enormous information tering approach. Our studies using the DUC 2002 dataset load generated particularly on the web including large text, show an increase in both the efficiency and accuracy of clus- audio, and video files etc.
    [Show full text]
  • Wordnet-Based Metrics Do Not Seem to Help Document Clustering
    Wordnet-based metrics do not seem to help document clustering Alexandre Passos1 and Jacques Wainer1 Instituto de Computação (IC) Universidade Estadual de Campinas (UNICAMP) Campinas, SP, Brazil Abstract. In most document clustering systems documents are repre- sented as normalized bags of words and clustering is done maximizing cosine similarity between documents in the same cluster. While this representation was found to be very effective at many different types of clustering, it has some intuitive drawbacks. One such drawback is that documents containing words with similar meanings might be considered very different if they use different words to say the same thing. This happens because in a traditional bag of words, all words are assumed to be orthogonal. In this paper we examine many possible ways of using WordNet to mitigate this problem, and find that WordNet does not help clustering if used only as a means of finding word similarity. 1 Introduction Document clustering is now an established technique, being used to improve the performance of information retrieval systems [11], as an aide to machine translation [12], and as a building block of narrative event chain learning [1]. Toolkits such as Weka [3] and NLTK [10] make it easy for anyone to experiment with document clustering and incorporate it into an application. Nonetheless, the most commonly accepted model—a bag of words representation [17], bisecting k-means algorithm [19] maximizing cosine similarity [20], preprocessing the corpus with a stemmer [14], tf-idf weighting [17], and a possible list of stop words [2]—is complex, unintuitive and has some obvious negative consequences.
    [Show full text]
  • Evaluation of Text Clustering Algorithms with N-Gram-Based Document Fingerprints
    Evaluation of Text Clustering Algorithms with N-Gram-Based Document Fingerprints Javier Parapar and Alvaro´ Barreiro IRLab, Computer Science Department University of A Coru~na,Spain fjavierparapar,[email protected] Abstract. This paper presents a new approach designed to reduce the computational load of the existing clustering algorithms by trimming down the documents size using fingerprinting methods. Thorough eval- uation was performed over three different collections and considering four different metrics. The presented approach to document clustering achieved good values of effectiveness with considerable save in memory space and computation time. 1 Introduction and Motivation Document's fingerprint could be defined as an abstraction of the original docu- ment that usually implies a reduction in terms of size. In the other hand data clustering consists on the partition of the input data collection in sets that ideally share common properties. This paper studies the effect of using the documents fingerprints as input to the clustering algorithms to achieve a better computa- tional behaviour. Clustering has a long history in Information Retrieval (IR)[1], but only re- cently Liu and Croft in [2] have demonstrated that cluster-based retrieval can also significantly outperform traditional document-based retrieval effectiveness. Other successful applications of clustering algorithms are: document browsing, search results presentation or document summarisation. Our approach tries to be useful in operational systems where the computing time is a critical point and the use of clustering techniques can significantly improve the quality of the outputs of different tasks as the above exposed. Next, section 2 introduces the background in clustering and document repre- sentation.
    [Show full text]
  • Word Sense Disambiguation in Biomedical Ontologies with Term Co-Occurrence Analysis and Document Clustering
    Int. J. Data Mining and Bioinformatics, Vol. 2, No. 3, 2008 193 Word Sense Disambiguation in biomedical ontologies with term co-occurrence analysis and document clustering Bill Andreopoulos∗, Dimitra Alexopoulou and Michael Schroeder Biotechnological Centre, Technischen Universität Dresden, Germany E-mail: [email protected] E-mail: [email protected] E-mail: [email protected] ∗Corresponding author Abstract: With more and more genomes being sequenced, a lot of effort is devoted to their annotation with terms from controlled vocabularies such as the GeneOntology. Manual annotation based on relevant literature is tedious, but automation of this process is difficult. One particularly challenging problem is word sense disambiguation. Terms such as ‘development’ can refer to developmental biology or to the more general sense. Here, we present two approaches to address this problem by using term co-occurrences and document clustering. To evaluate our method we defined a corpus of 331 documents on development and developmental biology. Term co-occurrence analysis achieves an F -measure of 77%. Additionally, applying document clustering improves precision to 82%. We applied the same approach to disambiguate ‘nucleus’, ‘transport’, and ‘spindle’, and we achieved consistent results. Thus, our method is a viable approach towards the automation of literature-based genome annotation. Keywords: WSD; word sense disambiguation; ontologies; GeneOntology; text mining; annotation; Bayes; clustering; GoPubMed; data mining; bioinformatics. Reference to this paper should be made as follows: Andreopoulos, B., Alexopoulou, D. and Schroeder, M. (2008) ‘Word Sense Disambiguation in biomedical ontologies with term co-occurrence analysis and document clustering’, Int. J. Data Mining and Bioinformatics, Vol.
    [Show full text]
  • A Query Focused Multi Document Automatic Summarization
    PACLIC 24 Proceedings 545 A Query Focused Multi Document Automatic Summarization Pinaki Bhaskar and Sivaji Bandyopadhyay Department of Computer Science & Engineering, Jadavpur University, Kolkata – 700032, India [email protected], [email protected] Abstract. The present paper describes the development of a query focused multi-document automatic summarization. A graph is constructed, where the nodes are sentences of the documents and edge scores reflect the correlation measure between the nodes. The system clusters similar texts having related topical features from the graph using edge scores. Next, query dependent weights for each sentence are added to the edge score of the sentence and accumulated with the corresponding cluster score. Top ranked sentence of each cluster is identified and compressed using a dependency parser. The compressed sentences are included in the output summary. The inter-document cluster is revisited in order until the length of the summary is less than the maximum limit. The summarizer has been tested on the standard TAC 2008 test data sets of the Update Summarization Track. Evaluation of the summarizer yielded accuracy scores of 0.10317 (ROUGE-2) and 0.13998 (ROUGE–SU-4). Keywords: Multi Document Summarizer, Query Focused, Cluster based approach, Parsed and Compressed Sentences, ROUGE Evaluation. 1 Introduction Text Summarization, as the process of identifying the most salient information in a document or set of documents (for multi document summarization) and conveying it in less space, became an active field of research in both Information Retrieval (IR) and Natural Language Processing (NLP) communities. Summarization shares some basic techniques with indexing as both are concerned with identification of the essence of a document.
    [Show full text]
  • Semantic Based Document Clustering Using Lexical Chains
    International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395 -0056 Volume: 04 Issue: 01 | Jan -2017 www.irjet.net p-ISSN: 2395-0072 SEMANTIC BASED DOCUMENT CLUSTERING USING LEXICAL CHAINS SHABANA AFREEN1, DR. B. SRINIVASU2 1M.tech Scholar, Dept. of Computer Science and Engineering, Stanley College of Engineering and Technology for Women, Telangana-Hyderabad, India. 2Associate Professor, Dept. of Computer Science and Engineering, Stanley College of Engineering and Technology for Women, Telangana -Hyderabad, India. ---------------------------------------------------------------------***--------------------------------------------------------------------- Abstract – Traditional clustering algorithms do not organizing large document collections into smaller consider the semantic relationships among documents so that meaningful and manageable groups, which plays an cannot accurately represent cluster of the documents. To important role in information retrieval, browsing and overcome these problems, introducing semantic information comprehension [1]. from ontology such as WordNet has been widely used to improve the quality of text clustering. However, there exist 1.2 Problem Description several challenges such as extracting core semantics from Feature vectors generated using Bow results in very large texts, assigning appropriate description for the generated dimensional vectors. The feature selected is directly clusters and diversity of vocabulary. proportional to dimension. Extract core semantics from texts selecting the feature will In this project we report our attempt towards integrating reduced number of terms which depict high semantic conre WordNet with lexical chains to alleviate these problems. The content. proposed approach exploits the way we can identify the theme The quality of extracted lexical chains is highly depends on of the document based on disambiguated core semantic the quality and quantity of the concepts within a document.
    [Show full text]
  • Latent Semantic Sentence Clustering for Multi-Document Summarization
    UCAM-CL-TR-802 Technical Report ISSN 1476-2986 Number 802 Computer Laboratory Latent semantic sentence clustering for multi-document summarization Johanna Geiß July 2011 15 JJ Thomson Avenue Cambridge CB3 0FD United Kingdom phone +44 1223 763500 http://www.cl.cam.ac.uk/ c 2011 Johanna Geiß This technical report is based on a dissertation submitted April 2011 by the author for the degree of Doctor of Philosophy to the University of Cambridge, St. Edmund’s College. Technical reports published by the University of Cambridge Computer Laboratory are freely available via the Internet: http://www.cl.cam.ac.uk/techreports/ ISSN 1476-2986 Latent semantic sentence clustering for multi-document summarization Johanna Geiß Summary This thesis investigates the applicability of Latent Semantic Analysis (LSA) to sentence clustering for Multi-Document Summarization (MDS). In contrast to more shallow approaches like measuring similarity of sentences by word overlap in a traditional vector space model, LSA takes word usage patterns into account. So far LSA has been successfully applied to different Information Retrieval (IR) tasks like information filtering and document classification (Dumais, 2004). In the course of this research, different parameters essential to sentence clustering using a hierarchical agglomerative clustering algorithm (HAC) in general and in combination with LSA in particular are investigated. These parameters include, inter alia, information about the type of vocabulary, the size of the semantic space and the optimal numbers of dimensions to be used in LSA. These parameters have not previously been studied and evaluated in combination with sentence clustering (chapter 4). This thesis also presents the first gold standard for sentence clustering in MDS.
    [Show full text]
  • Clustering News Articles Using K-Means and N-Grams by Desmond
    CLUSTERING NEWS ARTICLES USING K-MEANS AND N-GRAMS BY DESMOND BALA BISANDU (A00019335) SCHOOL OF IT & COMPUTING, AMERICAN UNIVERSITY OF NIGERIA, YOLA, ADAMAWA STATE, NIGERIA SPRING, 2018 CLUSTERING NEWS ARTICLES USING K-MEANS AND N-GRAMS BY DESMOND BALA BISANDU (A00019335) In partial fulfillment of the requirements for the award of degree of Master of Science (M.Sc.) in Computer Science submitted to the School of IT & Computing, American University of Nigeria, Yola SPRING, 2018 ii DECLARATION I, Desmond Bala BISANDU, declare that the work presented in this thesis entitled ‘Clustering News Articles Using K-means and N-grams’ submitted to the School of IT & Computing, American University of Nigeria, in partial fulfillment of the requirements for the award of the Master of Science (M.Sc.) in Computer Science. I have neither plagiarized nor submitted the same work for the award of any other degree. In case this undertaking is found incorrect, my degree may be withdrawn unconditionally by the University. Date: 16th April, 2018 Desmond Bala Bisandu Place: Yola A00019335 iii CERTIFICATION I certify that the work in this document has not been previously submitted for a degree nor neither has it been submitted as a part of a requirements for a degree except fully acknowledged within this text. ---------------------------- --------------------------- Student Date (Desmond Bala Bisandu) ----------------------------- --------------------------- Supervisor Date (Dr. Rajesh Prasad) ------------------------------ --------------------------- Program Chair Date (Dr. Narasimha Rao Vajjhala) ------------------------------ --------------------------- Graduate Coordinator, SITC Date (Dr. Rajesh Prasad) ------------------------------ --------------------------- Dean, SITC Date (Dr. Mathias Fonkam) iv ACKNOWLEDGEMENT My gratitude goes to the Almighty God for giving me the strength, knowledge, and courage to carry out this thesis successfully.
    [Show full text]
  • A Brief Survey of Text Mining: Classification, Clustering and Extraction Techniques
    A Brief Survey of Text Mining: Classification, Clustering and Extraction Techniques Mehdi Allahyari Seyedamin Pouriyeh Mehdi Assefi Computer Science Department Computer Science Department Computer Science Department University of Georgia University of Georgia University of Georgia Athens, GA Athens, GA Athens, GA [email protected] [email protected] [email protected] Saied Safaei Elizabeth D. Trippe Juan B. Gutierrez Computer Science Department Institute of Bioinformatics Department of Mathematics University of Georgia University of Georgia Institute of Bioinformatics Athens, GA Athens, GA University of Georgia [email protected] [email protected] Athens, GA [email protected] Krys Kochut Computer Science Department University of Georgia Athens, GA [email protected] ABSTRACT 1 INTRODUCTION The amount of text that is generated every day is increasing dra- Text Mining (TM) field has gained a great deal of attention in recent matically. This tremendous volume of mostly unstructured text years due the tremendous amount of text data, which are created in cannot be simply processed and perceived by computers. There- a variety of forms such as social networks, patient records, health fore, efficient and effective techniques and algorithms are required care insurance data, news outlets, etc. IDC, in a report sponsored to discover useful patterns. Text mining is the task of extracting by EMC, predicts that the data volume will grow to 40 zettabytes1 meaningful information from text, which has gained significant by 2020, leading to a 50-time growth from the beginning of 2010 attentions in recent years. In this paper, we describe several of [52]. the most fundamental text mining tasks and techniques including Text data is a good example of unstructured information, which text pre-processing, classification and clustering.
    [Show full text]
  • Text Summarization Using Clustering Technique Anjali R
    International Journal of Engineering Trends and Technology (IJETT) - Volume4 Issue8- August 2013 Text Summarization using Clustering Technique Anjali R. Deshpande #1, Lobo L. M. R. J. *2 #1 Student M. E.(C. S. E.) Part–II, Walchand Institute of Technology, Solapur University, Solapur, India. #2Professor & Head, Department of InformationTechnology, Walchand Institute of Technology, Solapur University, Solapur, India. Abstract— A summarization system consists of reduction of a A. Multi-document Summarization text document to generate a new form which conveys the key It is an automatic procedure designed to extract the information meaning of the contained text. from multiple text documents written about the same topic. Resulting Due to the problem of information overload, access to sound and summary allows individual users, such as professional information correctly-developed summaries is necessary. Text summarization consumers, to quickly familiarize themselves with information is the most challenging task in information retrieval. Data contained in a large collection of documents. reduction helps a user to find required information quickly The multi-document summarization task is much more complex than without wasting time and effort in reading the whole document summarizing a document & it’s a very large task. This difficulty collection. This paper presents a combined approach to arises from thematic diversity within a large set of documents. A document and sentence clustering as an extractive technique of good summarization technology aims to combine the main themes summarization. with completeness, readability, and conciseness [2]. The present implementation includes development of an extractive Keywords— Extractive Summarization, Abstractive technique that combines first clustering of documents & then Summarization, Multi-document summarization, Document clustering of sentences in these documents.
    [Show full text]