International Journal of Knowledge and Web Intelligence http://www.inderscience.com/browse/index.php?journalID=284&year=2011&vol=2&issue=4 Inderscience Publishers Ltd en-uk International Journal of Knowledge and Web Intelligence 1755-8255 1755-8263 © 2011 Inderscience Publishers Ltd editor@inderscience.com https://www.inderscience.com/images/files/coverImgs/ijkwi_scoverijkwi.jpg http://www.inderscience.com/browse/index.php?journalID=284&year=2011&vol=2&issue=4 http://www.inderscience.com/link.php?id=45162 The use of ontologies for knowledge representation has had a fast increase in the last years and they are used in several application context. One of these challenging applications is the web. Managing large amount of information on internet needs more efficient and effective methods and techniques for mining and representing information. In this article, we present a methodology for automatic topic annotation of web pages. We describe an algorithm for words disambiguation using an apposite metric for measuring the semantic relatedness and we show a technique which allows to detect the topic of the analysed document using ontologies extracted from a knowledge base. The strategy is implemented in a system where these information are used to build a topic hierarchy automatically created and not a priori defined for classifying web pages. Experimental results are presented and discussed in order to measure the effectiveness of our approach. Automatic web pages hierarchical classification using dynamic domain ontologies
Antonio M. Rinaldi
International Journal of Knowledge and Web Intelligence, Vol. 2, No. 4 (2011) pp. 231 - 256
The use of ontologies for knowledge representation has had a fast increase in the last years and they are used in several application context. One of these challenging applications is the web. Managing large amount of information on internet needs more efficient and effective methods and techniques for mining and representing information. In this article, we present a methodology for automatic topic annotation of web pages. We describe an algorithm for words disambiguation using an apposite metric for measuring the semantic relatedness and we show a technique which allows to detect the topic of the analysed document using ontologies extracted from a knowledge base. The strategy is implemented in a system where these information are used to build a topic hierarchy automatically created and not a priori defined for classifying web pages. Experimental results are presented and discussed in order to measure the effectiveness of our approach.

]]> 10.1504/IJKWI.2011.045162 International Journal of Knowledge and Web Intelligence, Vol. 2, No. 4 (2011) pp. 231 - 256 Antonio M. Rinaldi Dipartimento di Informatica e Sistemistica, Università di Napoli Federico II, 80125 Via Claudio, 21, Napoli, Italy knowledge engineering document analysis text processing semantic networks ontologies web page classification natural language processing NLP hierarchical classification topic annotation subject annotation websites. 2012-01-29T23:20:50-05:00 2 4 231 256 2012-01-29T23:20:50-05:00 http://www.inderscience.com/link.php?id=45163 Web page prediction plays an important role by predicting and fetching probable web page of next request in advance, resulting in reducing the user latency. The users surf the internet either by entering URL or search for some topic or through link of same topic. For searching and for link prediction, clustering plays an important role. Besides the topic, navigational behaviour is not ignored. This paper proposes a web page prediction model giving significant importance to the user's interest using the clustering technique and the navigational behaviour of the user through Markov model. The clustering technique is used for the accumulation of the similar web pages. Similar web pages of same type reside in the same cluster, the cluster containing web pages have the similarity with respect to topic of the session. The clustering algorithms considered are K-means and K-mediods, where K is determined by HITS algorithm. Finally, the predicted web pages are stored in form of cellular automata to make the system more memory efficient. Clustering-based web page prediction
Ruma Dutta; Anirban Kundu; Debajyoti Mukhopadhyay
International Journal of Knowledge and Web Intelligence, Vol. 2, No. 4 (2011) pp. 257 - 271
Web page prediction plays an important role by predicting and fetching probable web page of next request in advance, resulting in reducing the user latency. The users surf the internet either by entering URL or search for some topic or through link of same topic. For searching and for link prediction, clustering plays an important role. Besides the topic, navigational behaviour is not ignored. This paper proposes a web page prediction model giving significant importance to the user's interest using the clustering technique and the navigational behaviour of the user through Markov model. The clustering technique is used for the accumulation of the similar web pages. Similar web pages of same type reside in the same cluster, the cluster containing web pages have the similarity with respect to topic of the session. The clustering algorithms considered are K-means and K-mediods, where K is determined by HITS algorithm. Finally, the predicted web pages are stored in form of cellular automata to make the system more memory efficient.

]]> 10.1504/IJKWI.2011.045163 International Journal of Knowledge and Web Intelligence, Vol. 2, No. 4 (2011) pp. 257 - 271 Ruma Dutta; Anirban Kundu; Debajyoti Mukhopadhyay Netaji Subhash Engineering College, West Bengal University of Technology, Garia, Kolkata, 700152, West Benagal, India. ' Kuang-Chi Institute of Advanced Technology, Software Building, No. 9 Gaoxin Zhong, 1st Road, High-Tech Industrial Estate, Nanshan District, Shenzhen, Guangdong, 518057, China. ' Maharashtra Institute of Technology, S. No. 124, Paud Road, Kothrud, Pune 411038, Maharashtra, India; Web Intelligence and Distributed Computing Research Lab (WIDiCoReL), GreenTower, C-9/1, Golf Green, Kolkata, 700095, India web page prediction HITS algorithm clustering cellular automata user latency similar web pages web page similarity web search. 2012-01-29T23:20:50-05:00 2 4 257 271 2012-01-29T23:20:50-05:00 http://www.inderscience.com/link.php?id=45164 Making search engines responsive to human needs requires understanding of user navigations through the search results in response to the submitted queries. The user behaviour characterisation provides an interesting perspective towards understanding the workload imposed on the search engine and can be used to address crucial points such as load balancing, content caching, data distribution and result optimisation. The user browsing behaviour is recorded in the query logs of search engines and usually referred to as web usage data. In this paper, a technique to utilise the users' browsing behaviour at the crawling and indexing process is being proposed so as to direct the crawler to download the important pages, which were not previously crawled. As the work attempts to index most of important pages based on user feedback, it would benefit the search engine to enhance its efficiency. To add further to the proposed work, the existing data structures maintained by the search engines has been refined so as to support the proposed user feedback mechanism and open more research directions. A framework for utilising usage trends in the crawling and indexing process of search engines
Neelam Duhan; A.K. Sharma
International Journal of Knowledge and Web Intelligence, Vol. 2, No. 4 (2011) pp. 272 - 291
Making search engines responsive to human needs requires understanding of user navigations through the search results in response to the submitted queries. The user behaviour characterisation provides an interesting perspective towards understanding the workload imposed on the search engine and can be used to address crucial points such as load balancing, content caching, data distribution and result optimisation. The user browsing behaviour is recorded in the query logs of search engines and usually referred to as web usage data. In this paper, a technique to utilise the users' browsing behaviour at the crawling and indexing process is being proposed so as to direct the crawler to download the important pages, which were not previously crawled. As the work attempts to index most of important pages based on user feedback, it would benefit the search engine to enhance its efficiency. To add further to the proposed work, the existing data structures maintained by the search engines has been refined so as to support the proposed user feedback mechanism and open more research directions.

]]> 10.1504/IJKWI.2011.045164 International Journal of Knowledge and Web Intelligence, Vol. 2, No. 4 (2011) pp. 272 - 291 Neelam Duhan; A.K. Sharma Department of Computer Engineering, YMCA University of Science and Technology, Zakir Nagar, Sector-6, Faridabad, India. ' Department of Computer Engineering, YMCA University of Science and Technology, Zakir Nagar, Sector-6, Faridabad, India World Wide Web internet search engines crawlers indexing query logs usage trends user behaviour crawling load balancing content caching data distribution results optimisation browsing behaviour search engine efficiency. 2012-01-29T23:20:50-05:00 2 4 272 291 2012-01-29T23:20:50-05:00 http://www.inderscience.com/link.php?id=45165 We discuss how to reengineer complex PDF-based documents, such as specifications and technical books, so that end users have a better experience with them. Specifications of the object management group (OMG) are our initial targets. Such specifications are dense and intricate to use, and tend to have complicated structures. Our approach includes format conversion, logical structure extraction, text extraction and multi-layer hypertext generation. Logical structure extraction is central, and results in an XML document with a schema tailored to the type of document. Many key concepts of a document are expressed in this schema, including concepts extracted from the patterns of words used in headings. For example in OMG specifications, package relationships and class associations can often be extracted from the wording of headings. When we produce, in the final step, a multilayer hypertext version of the document, these extracted concepts allow a richer user experience. Reengineering PDF-based documents targeting complex software specifications
Mehrdad Nojoumian; Timothy C. Lethbridge
International Journal of Knowledge and Web Intelligence, Vol. 2, No. 4 (2011) pp. 292 - 319
We discuss how to reengineer complex PDF-based documents, such as specifications and technical books, so that end users have a better experience with them. Specifications of the object management group (OMG) are our initial targets. Such specifications are dense and intricate to use, and tend to have complicated structures. Our approach includes format conversion, logical structure extraction, text extraction and multi-layer hypertext generation. Logical structure extraction is central, and results in an XML document with a schema tailored to the type of document. Many key concepts of a document are expressed in this schema, including concepts extracted from the patterns of words used in headings. For example in OMG specifications, package relationships and class associations can often be extracted from the wording of headings. When we produce, in the final step, a multilayer hypertext version of the document, these extracted concepts allow a richer user experience.

]]> 10.1504/IJKWI.2011.045165 International Journal of Knowledge and Web Intelligence, Vol. 2, No. 4 (2011) pp. 292 - 319 Mehrdad Nojoumian; Timothy C. Lethbridge David R. Cheriton School of Computer Science, University of Waterloo, Waterloo, Ontario, N2L 3G1, Canada. ' School of Electrical Engineering and Computer Science, 800 King Edward Ave., Ottawa, ON K1N 6N5, Canada digital libraries electronic publishing improving user experiences browsing interfaces e-publishing document reengineering PDF based documents software specifications object management group OMG specifications XML documents format conversion logical structure extraction text extraction multi-layer hypertext generation package relationships class associations document headings word patterns. 2012-01-29T23:20:50-05:00 2 4 292 319 2012-01-29T23:20:50-05:00