DOCSLIB.ORG

Journey from Data Mining to Web Mining to Big Data

Total Page：16

File Type：pdf, Size：1020Kb

Download full-text PDF Read full-text
Journey from Data Mining to Web Mining to Big Data International Journal of Computer Trends and Technology (IJCTT) – volume 10 number 1 – Apr 2014 Journey from Data Mining to Web Mining to Big Data Richa Gupta Department of Computer Science University of Delhi ABSTRACT : This paper describes the journey Based on the type of patterns to be mined, data of big data starting from data mining to web mining tasks can be classified into summarization, mining to big data. It discusses each of this method classification, clustering, association and trends in brief and also provides their applications. It analysis [1]. states the importance of mining big data today using fast and novel approaches. Summarization is the abstraction or generalization of data. Data is summarized and abstracted to give Keywords- data mining, web mining, big data a smaller set which provides overview of data and some useful information [1]. 1 INTRODUCTION Classification is the method of classifying objects Data is the collection of values and variables into certain groups based on their attributes. Certain related in certain sense and differing in some other classes are made by analyzing the relationship sense. The size of data has always been increasing. between the attributes and classes of objects in the training set [1]. Storing this data without using it in any sense is simply waste of storage space and storing time. Association is the discovery of togetherness or Data should be processed to extract some useful connection of objects. The association is based on knowledge from it. certain rules, known as association rules. These rules reveal the associative relationship among objects, that is, they find the correlation in a set of 2 DATA MINING objects [1]. Data Mining is analysing the data from different perspectives and summarizing it into useful Clustering is the identification of clusters or information that can be used for business solutions groups for a set of objects whose classes are and predicting the future trends. Mining the unknown. Clustering should be done such that the information helps organizations make proactive, similarities between objects of same clusters are knowledge-driven decisions and answer questions maximized and similarities between different that were previously time consuming to resolve. clusters are minimized. Data mining (DM), also called Knowledge- Trend analysis is discovering of interesting Discovery in Databases (KDD) or Knowledge- patterns in the dimension of time. It is the matching Discovery and Data Mining, is the process of of objects’ changing trends such as increasing automatically searching large volumes of data for streaks [1]. patterns such as association rules. It is a fairly recent topic in computer science but applies many Data Mining tools can be classified into three older computational techniques from statistics, categories: traditional data mining tools, information retrieval, machine learning and pattern dashboards and text-mining tools. recognition. Traditional Data Mining Tools helps companies establish data patterns and Data mining is important as the particular user will trends using complex algorithms and be looking for pattern and not for complete data in techniques usually situated on a single the database, it is better to read wanted data than computer. The majority are available in unwanted data. Data mining extract only required Windows and Unix versions. They patterns from the database in a short time span normally handle data using offline tools [2]. ISSN: 2231-2803 http://www.ijcttjournal.org Page18 International Journal of Computer Trends and Technology (IJCTT) – volume 10 number 1 – Apr 2014 Dashboards reflect data changes enabling the difference between different websites the user to see how the business is [4]. performing. Web usage mining – it attempts to Text mining tools mines data from discover useful knowledge from the data different kinds of texts, example, obtained from web user sessions. It tries Microsoft word, acrobat PDF, text files. to find usage patterns from the web data These tools scan the content and convert to understand and better serve the needs the selected data into format that is of Web-based applications. Some compatible with tool’s database [2]. applications of web usage mining are adaptive websites, web personalization 2.1 APPLICATIONS OF DATA and recommendation, business MINING intelligence. Artificial neural networks. 3.1 APPLICATIONS OF WEB MINING Business applications. In this it is used for It has its great use in e-commerce and e- database marketing, retail data analysis, services stock selection, credit approval etc. In e-learning Science applications. It is used in Self-organizing websites astronomy, molecular biology, medicine, Digital libraries geology etc. E-government Health care management Security and crime investigation Tax fraud detection 4 BIG DATA 3 WEB MINING There has been a lot of growth in the amount of As the usage of web started to increase, so does the data generated by web these days. The data has demand of data mining. Web mining is the been so large that it becomes difficult to analyse it application of data mining techniques to discover with the help of our traditional mining methods. usage patterns from large Web repositories. It Big data term has been coined for data that exceeds reveals interesting and unknown knowledge about the processing capability [6]. It has three main key both users and websites which can be used for characteristics analysis. It is used to understand customer behaviour, evaluate the effectiveness of a particular Volume – the size of data is now larger website and help quantify the success of a than terabytes and petabytes. This large marketing campaign [3, 4]. Web mining can be scale makes it difficult to analyse using classified into three types based on the type of data: conventional methods. Velocity – big data should be used to mine Web content mining – it is the process of large amount of data within a pre-defined extracting useful information and period of time. The traditional methods of knowledge from the web mining may take huge time to mine such a contents/data/documents. Content may volume of data. consist of text, images, audio, video or Variety – big data comes from various structured records such as lists and tables. sources. It is designed to handle Web content mining is differentiated from structured, semi-structured as well as two different points of view: Information unstructured data. Whereas the traditional Retrieval View and Database View [5]. methods were designed to handle Web structure mining – it is the process structured data and that too not of such of using graph theory to analyse the node large volume. and connection structure of a website. It tries to discover the underlying link Big data is a general term for massive amount of structures of the web. It can be used to digital data being collected from various sources, generate information on the similarity or that are too large and raw in form. Big data deals with new challenges like complexity, security, risks ISSN: 2231-2803 http://www.ijcttjournal.org Page19 International Journal of Computer Trends and Technology (IJCTT) – volume 10 number 1 – Apr 2014 to privacy. Big data is redefining the data faster methods of mining data which uses the management from extraction, transformation and parallel computing capability of processors. This processing to cleaning and reducing [7]. term is known as Big data. We have also provided with the applications of different methods of 4.1 APPLICATIONS OF BIG DATA mining. In social networking sites to find for usage patterns In google search REFERENCES Astronomy [1] http://academic.csuohio.edu/fuy/Pub/pot97.pdf Sensor networks [2]http://www.theiia.org/intAuditor/itaudit/archives/2006/august Government data /data-mining-101-tools-and-techniques/ Web logs [3] Bodyan G.C, Shestakov T.V, “Web Mining in Technology Mobile phones Management”, Engineering Universe for Scientific Research Natural disaster and resource management and Management, Vol 1 Issue 2, April 2009 Scientific research [4] http://en.wikipedia.org/wiki/Web_mining [5] Jaideep Srivastava, P. Desikan, Vipin Kumar, 5 CONCLUSION http://dmr.cs.umn.edu/Papers/P2004_4.pdf In this paper, we have reviewed the journey on how [6] Richa Gupta, Sunny Gupta, Anuradha Singhal, "Big Data: on big data evolved. It defines the traditional Overview", International Journal of Computer Trends and mining methods as data mining, then with the Technology (IJCTT), Vol 9, No.5, March 2014 advancement of web, came the concept of web mining. And later on, the size and variety of data [7] Gang-Hoon Kim, Silvana Trimi, Ji-Hyong Chung, "Big-Data Applications in the Government Sector", Communications of the pushed us to think ahead and develop new and ACM, Vol. 57, No.3, Pages 78-75 ISSN: 2231-2803 http://www.ijcttjournal.org Page20 .
Load more

Recommended publications
  • Towards Semantic Web Mining
    Towards Semantic Web Mining Bettina Berendt1, Andreas Hotho2, and Gerd Stumme2 1 Institute of Information Systems, Humboldt University Berlin Spandauer Str. 1, D–10178 Berlin, Germany http://www.wiwi.hu-berlin.de/˜berendt [email protected] 2 Institute of Applied Informatics and Formal Description Methods AIFB, University of Karlsruhe, D–76128 Karlsruhe, Germany http://www.aifb.uni-karlsruhe.de/WBS {hotho, stumme}@aifb.uni-karlsruhe.de Abstract. Semantic Web Mining aims at combining the two fast-deve- loping research areas Semantic Web and Web Mining. The idea is to improve, on the one hand, the results of Web Mining by exploiting the new semantic structures in the Web; and to make use of Web Mining, on the other hand, for building up the Semantic Web. This paper gives an overview of where the two areas meet today, and sketches ways of how a closer integration could be profitable. 1 Introduction Semantic Web Mining aims at combining the two fast-developing research areas Semantic Web and Web Mining. The idea is to improve the results of Web Mining byexploiting the new semantic structures in the Web. Furthermore, Web Mining can help to build the Semantic Web. The aim of this paper is to give an overview of where the two areas meet today, and to sketch how a closer integration could be profitable. We will provide references to typical approaches. Most of them have not been developed explic- itlyto close the gap between the Semantic Web and Web Mining, but theyfit naturallyinto this scheme. We do not attempt to mention all the relevant work, as this would surpass the paper, but will rather provide one or two examples out of each category.
    [Show full text]
  • Analysis of Web Logs and Web User in Web Mining
    International Journal of Network Security & Its Applications (IJNSA), Vol.3, No.1, January 2011 ANALYSIS OF WEB LOGS AND WEB USER IN WEB MINING L.K. Joshila Grace 1, V.Maheswari 2, Dhinaharan Nagamalai 3, 1Research Scholar, Department of Computer Science and Engineering [email protected] 2 Professor and Head,Department of Computer Applications 1,2 Sathyabama University,Chennai,India 3Wireilla Net Solutions PTY Ltd, Australia ABSTRACT Log files contain information about User Name, IP Address, Time Stamp, Access Request, number of Bytes Transferred, Result Status, URL that Referred and User Agent. The log files are maintained by the web servers. By analysing these log files gives a neat idea about the user. This paper gives a detailed discussion about these log files, their formats, their creation, access procedures, their uses, various algorithms used and the additional parameters that can be used in the log files which in turn gives way to an effective mining. It also provides the idea of creating an extended log file and learning the user behaviour. KEYWORDS Web Log file, Web usage mining, Web servers, Log data, Log Level directive. 1. INTRODUCTION Log files are files that list the actions that have been occurred. These log files reside in the web server. Computers that deliver the web pages are called as web servers. The Web server stores all of the files necessary to display the Web pages on the users computer. All the individual web pages combines together to form the completeness of a Web site. Images/graphic files and any scripts that make dynamic elements of the site function.
    [Show full text]
  • Data Mining Techniques for Social Media Analysis
    Advances in Engineering Research (AER), volume 142 International Conference for Phoenixes on Emerging Current Trends in Engineering and Management (PECTEAM 2018) A Survey: Data Mining Techniques for Social Media Analysis 1Elangovan D, 2Dr.Subedha V, 3Sathishkumar R, 4 Ambeth kumar V D 1Research scholar, Department of Computer Science Engineering, Sathyabama University, India 2Professor, Department of Computer Science Engineering, Panimalar Institute of Technology, Chennai, India 3Assistant Professor, 4Associate Professor, Department of Computer Science Engineering, Panimalar Engineering College, Chennai, India [email protected],[email protected], [email protected],[email protected] Abstract—Data mining is the extraction of present information databases. The overall objective of the data mining technique from high volume of data sets, it’s a modern technology. The is to extract information from a huge data set and transform it main intention of the mining is to extract the information from a into a comprehensible structure for more use. The different large no of data set and convert it into a reasonable structure for data Mining techniques are further use. The social media websites like Facebook, twitter, instagram enclosed the billions of unrefined raw data. The I. Characterization. various techniques in data mining process after analyzing the II. Classification. raw data, new information can be obtained. Since this data is III. Regression. active and unstructured, conventional data mining techniques IV. Association. may not be suitable. This survey paper mainly focuses on various V. Clustering. data mining techniques used and challenges that arise while using VI. Change Detection. it. The survey of various work done in the field of social network analysis mainly focuses on future trends in research.
    [Show full text]
  • Review of Various Web Page Ranking Algorithms in Web Structure Mining
    National Conference on Recent Research in Engineering and Technology (NCRRET -2015) International Journal of Advance Engineering and Research Development (IJAERD) e-ISSN: 2348 - 4470 , print-ISSN:2348-6406 Review of Various Web Page Ranking Algorithms in Web Structure Mining Asst. prof. Dhwani Dave Computer Science and Engineering DJMIT ,Mogar Abstract: The World Wide Web contains large amount of data. These data is stored in the form of web pages .All II. WEB MINING CATEGORIES these pages can be accessed using search engines. These search engines need to be very efficient as there are large Web Mining consists of three main number of Web pages as well as queries are submitted to categories based on the web data used as input in the search engines. Page ranking algorithms are used by the Web Data Mining. (1) Web Content Mining; (2) Web search engines to present the search results by considering the relevance, importance and content score. Several web Usage and (3); Web Structure Mining. mining techniques are used to order them according to the user interest. In this paper such page ranking techniques are A. Web Content Mining discussed. Keywords: Web Content Mining, Web Usage Mining, Web Web content mining is the procedure of retrieving Structure Mining, PageRank, HITS, Weighted PageRank the information from the web into more structured forms and indexing the information to retrieve it quickly. It focuses mainly on the structure within a I. INTRODUCTION web documents as an inner document level [9]. The web is a rich source of information and B. Web Usage Mining it continues to increase in size and difficulty.
    [Show full text]
  • Text and Web Mining a Big Challenge for Data Mining
    Text and Web Mining A big challenge for Data Mining Nguyen Hung Son Warsaw University Outline • Text vs. Web mining • Search Engine Inside: – Why Search Engine so important – Search Engine Architecture • Crawling Subsystem • Indexing Subsystem • Search Interface • Text/web mining tools • Results and Challenges • Future Trends TEXT AND WEB MINING OVERVIEW Text Mining • The sub-domain of Information Retrieval and Natural Language Processing – Text Data: free-form, unstructured & semi- structured data – Domains: Internal/intranet & external/internet • Emails, letters, reports, articles, .. – Content management & information organization – knowledge discovery: e.g. “topic detection”, “phrase extraction”, “document grouping”, ... Web mining • The sub-domain of IR and multimedia: – Semi-structured data: hyper-links and html tags – Multimedia data type: Text, image, audio, video – Content management/mining as well as usage/traffic mining The Problem of Huge Feature Space A small text database Transaction databases (1.2 MB) Typical basket data (several GBs to TBs) 2000 unique 700,000 items unique phrases!!! Association rules Phrase association patterns Access methods for Texts Information Direct Retrieval browsing <dallers> <gulf > <wheat> <shipping > <silk worm missile> <sea men> <strike > <port > <ships> <the gulf > <us.> <vessels > <attack > Survey and <iranian > <strike > browsing tool by <iran > Text data mining Natural Language Processing • Text classification/categorization • Document clustering: finding groups of similar documents • Information extraction • Summarization: no corresponding notion in Data Mining Text Mining vs. NLP • Text Mining: extraction of interesting and useful patterns in text data – NLP technologies as building blocks – Information discovery as goals – Learning-based text categorization is the simplest form of text mining Text Mining : Text Refining + Knowledge Distillation Document-based Document Clustering Text collection Text categorization IF Visualization Domain dependent ..
    [Show full text]
  • Web Mining.Pdf
    Web Mining : Accomplishments & Future Directions Jaideep Srivastava University of Minnesota USA [email protected] http://www.cs.umn.edu/faculty/srivasta.html Mr. Prasanna Desikan’s help in preparing these slides is acknowledged © Jaideep Srivastava 1 Web Mining Web is a collection of inter-related files on one or more Web servers. Web mining is the application of data mining techniques to extract knowledge from Web data Web data is Web content – text, image, records, etc. Web structure – hyperlinks, tags, etc. Web usage – http logs, app server logs, etc. © Jaideep Srivastava 27 Pre-processing Web Data Web Content Extract “snippets” from a Web document that represents the Web Document Web Structure Identifying interesting graph patterns or pre- processing the whole web graph to come up with metrics such as PageRank Web Usage User identification, session creation, robot detection and filtering, and extracting usage path patterns © Jaideep Srivastava 30 Web Usage Mining © Jaideep Srivastava 63 What is Web Usage Mining? A Web is a collection of inter-related files on one or more Web servers Web Usage Mining Discovery of meaningful patterns from data generated by client-server transactions on one or more Web localities Typical Sources of Data automatically generated data stored in server access logs, referrer logs, agent logs, and client-side cookies user profiles meta data: page attributes, content attributes, usage data © Jaideep Srivastava 64 ECLF Log File Format IP Address rfc931 authuser Date and time of request request
    [Show full text]
  • A Survey on Web Multimedia Mining
    The International Journal of Multimedia & Its Applications (IJMA) Vol.3, No.3, August 2011 A SURVEY ON WEB MULTIMEDIA MINING Pravin M. Kamde 1, Dr. Siddu. P. Algur 2 1 Assistant Professor, Department of Computer Science & Engineering, Sinhgad College of Engineering, Pune, Maharashtra, Email: [email protected] 2 Professor & Head, Department of Information Science & Engineering, BVB College of Engineering & Technology, Hubli, Karnataka, Email: [email protected] ABSTRACT Modern developments in digital media technologies has made transmitting and storing large amounts of multi/rich media data (e.g. text, images, music, video and their combination) more feasible and affordable than ever before. However, the state of the art techniques to process, mining and manage those rich media are still in their infancy. Advances developments in multimedia acquisition and storage technology the rapid progress has led to the fast growing incredible amount of data stored in databases. Useful information to users can be revealed if these multimedia files are analyzed. Multimedia mining deals with the extraction of implicit knowledge, multimedia data relationships, or other patterns not explicitly stored in multimedia files. Also in retrieval, indexing and classification of multimedia data with efficient information fusion of the different modalities is essential for the system's overall performance. The purpose of this paper is to provide a systematic overview of multimedia mining. This article is also represents the issues in the application process component for multimedia mining followed by the multimedia mining models. KEYWORDS Web Mining, Text Mining; Image Mining; Video Mining; Audio Mining. 1. INTRODUCTION Now days the World Wide Web is a popular and interactive medium to discriminate information.
    [Show full text]
  • Data, Text, and Web Mining for Business Intelligence
    International Journal of Data Mining & Knowledge Management Process (IJDKP) Vol.3, No.2, March 2013 DATA , TEXT , AND WEB MINING FOR BUSINESS INTELLIGENCE : A SURVEY Abdul-Aziz Rashid Al-Azmi Department of Computer Engineering, Kuwait University, Kuwait [email protected] ABSTRACT The Information and Communication Technologies revolution brought a digital world with huge amounts of data available. Enterprises use mining technologies to search vast amounts of data for vital insight and knowledge. Mining tools such as data mining, text mining, and web mining are used to find hidden knowledge in large databases or the Internet. Mining tools are automated software tools used to achieve business intelligence by finding hidden relations, and predicting future events from vast amounts of data. This uncovered knowledge helps in gaining completive advantages, better customers’ relationships, and even fraud detection. In this survey, we’ll describe how these techniques work, how they are implemented. Furthermore, we shall discuss how business intelligence is achieved using these mining tools. Then look into some case studies of success stories using mining tools. Finally, we shall demonstrate some of the main challenges to the mining technologies that limit their potential. KEYWORDS business intelligence, competitive advantage, data mining, information systems, knowledge discovery 1. INTRODUCTION We live in a data driven world, the direct result of advents in information and communication technologies. Millions of resources for knowledge are made possible thanks to the Internet and Web 2.0 collaboration technologies. No longer do we live in isolation from vast amounts of data. The Information and Communication Technologies revolution provided us with convenience and ease of access to information, mobile communications and even possible contribution to this amount of information.
    [Show full text]
  • Web Text Mining for News by Classification
    ISSN : 2278 – 1021 International Journal of Advanced Research in Computer and Communication Engineering Vol. 1, Issue 6, August 2012 Web Text Mining for news by Classification Ms. Sarika Y. Pabalkar Pad Dr. D.Y Patil Institute of Institute of Engineering and Technology, Pimpri , Pune, Maharashtra, India. ABSTRACT— In today’s world most information resources on the World Wide Web are published as HTML or XML pages and number of web pages is increasing rapidly with expansion of the web. In order to make better use of web information, technologies that can automatically re-organize and manipulate web pages are pursued such as by web information retrieval, web page classification and other web mining work. Research and application of Web text mining is an important branch in the data mining. Now people mainly use the search engine to look up Web information. The search engine like Google can hardly provide individual service according to different need of different user. However, Web text mining aims to resolve this problem. In Web text mining, the text extraction and the characteristic express of its extraction contents are the foundation of mining work, the text classification is the most important and basic mining method. Thus classification means classify each text of text set to a certain class depending on the definition of classification system. Thus, the challenge becomes not only to find all the subject occurrences, but also to filter out just those that have the desired meaning. Nowadays people usually use the search engine—Google, Yahoo etc. to browse the Web information mainly. But these search engines involve so wide range, whose intelligence level is low.
    [Show full text]
  • Web Personalized Index Based N-GRAM Extraction
    International Journal of Inventive Engineering and Sciences (IJIES) ISSN: 2319–9598, Volume-3 Issue-3, February 2015 Web Personalized Index based N-GRAM Extraction Ahmed Mudassar Ali, M. Ramakrishnan Document/HTML parsing: It parses terms from input Abstract— Web mining is the analysis step of the document. The HTML parser reads the content of a web page "Knowledge Discovery in Web Databases" process which is into character sequences, and then marks the blocks of an intersection of computer science and statistics. In this HTML tags and the blocks of text content. At this stage, the process results are produced from pattern matching and HTML parser uses a character encoding scheme to encode clustering which may not be relevant to the actual search. the text. Like this any given input text document can be read For example result for tree may be apple tree, mango tree by the parser in a similar way. whereas the user is searching for binary tree. N-grams are Word net processing: Word Net is an electronic lexical applied in applications like searching in text documents, database that uses word senses to determine underlying where one must work with phrases. Eg: plagiarism semantics. It differs from the traditional dictionary in that, it detection. Thus relevancy becomes major part in searching. is organized by meaning. A stop words list is created and the We can achieve relevancy using n-gram algorithm. We parsed documents are looked in for the stop words and the show an index based method to discover patterns in large process extracts only the lexical terms.
    [Show full text]
  • Comparative Study of Web Mining Algorithms
    International Journal of Engineering Research & Technology (IJERT) ISSN: 2278-0181 Vol. 3 Issue 4, April - 2014 Comparative Study of Web Mining Algorithms Rachna Singh Bhullar Dr. Praveen Dhyani Computer Science Department, Banasthali University – Jaipur Campus, Jaipur Guru Nanak Dev University, Rajasthan, India. Amritsar, Punjab, India Abstract: Every second data is shared between web servers and databases. As a result, demand of most relevant and web users either in the form of uploading or downloading to or efficient data from the web databases and storage of data from the web sites. In both the cases web servers play a very important role of providing the most efficient and relevant data on the web databases is increasing exponentially. In such a from the web databases. To accomplish this task various web situation, task of retrieving the efficient data is extremely mining algorithms are used by web servers to satisfy the need of challenging. Web mining is the collection of those data web users. In this paper we are presenting an overview of web mining techniques which are best suited to perform such a mining algorithms and a comparative study among them. In the last section of this paper, we are suggesting some questions which challenging task.Web mining can be categorized into Web cannot be answered by any of the web content or web usage Usage Mining, Web Structure Mining, and Web Content mining algorithms which motivated us to implement the web Mining. These are described as follows:- structure mining algorithms. Web Usage Mining (WUM):- Keywords- Web Usage Mining, Web Content Mining, Web Structure Mining, Web Content Outlier Mining, Web Mining Algorithms.
    [Show full text]
  • Probabilistic Semantic Web Mining Using Artificial Neural Analysis 1.1 Data, Information, and Knowledge
    (IJCSIS) International Journal of Computer Science and Information Security, Vol. 7, No. 3, March 2010 Probabilistic Semantic Web Mining Using Artificial Neural Analysis 1.1 Data, Information, and Knowledge 1. T. KRISHNA KISHORE, 2. T.SASI VARDHAN, AND 3. N. LAKSHMI NARAYANA Abstract Most of the web user’s requirements are 1.1.1 Data search or navigation time and getting correctly matched result. These constrains can be satisfied Data are any facts, numbers, or text that with some additional modules attached to the can be processed by a computer. Today, existing search engines and web servers. This paper organizations are accumulating vast and growing proposes that powerful architecture for search amounts of data in different formats and different engines with the title of Probabilistic Semantic databases. This includes: Web Mining named from the methods used. Operational or transactional data such as, With the increase of larger and larger sales, cost, inventory, payroll, and accounting collection of various data resources on the World No operational data, such as industry Wide Web (WWW), Web Mining has become one sales, forecast data, and macro economic data of the most important requirements for the web Meta data - data about the data itself, such users. Web servers will store various formats of as logical database design or data dictionary data including text, image, audio, video etc., but definitions servers can not identify the contents of the data. 1.1.2 Information These search techniques can be improved by The patterns, associations, or relationships adding some special techniques including semantic among all this data can provide information.
    [Show full text]