Neelam Duhan

Page ranking based on number of visits of links of Web page

Search engines generally return a large number of pages in response to user queries. To assist the users to navigate in the result list, ranking methods are applied on the search results. Most of the ranking algorithms proposed in the literature are either link or content oriented, which do not consider user usage trends. In this paper, a page ranking mechanism called Page Ranking based on Visits of Links(VOL) is being devised for search engines, which works on the basic ranking algorithm of Google i.e. PageRank and takes number of visits of inbound links of Web pages into account. This concept is very useful to display most valuable pages on the top of the result list on the basis of user browsing behavior, which reduces the search space to a large scale. The paper also presents a method to find link-visit counts of Web pages and a comparison between VOL with the PageRank algorithm.

A Novel Approach for Organizing Web Search Results using Ranking and Clustering

World Wide Web is considered the most valuable place for Information Retrieval and Knowledge Discovery. While retrieving information through user queries, a search engine results in a large and unmanageable collection of documents. Web mining tools are used to classify, cluster and order the documents so that users can easily navigate through the search results and find the desired information content. A more efficient way to organize the documents can be a combination of clustering and ranking, where clustering can group the documents and ranking can be applied for ordering the pages within each cluster. Based on this approach, in this paper, a mechanism is being proposed that provides ordered results in the form of clusters in accordance with user‟s query. An efficient page ranking method is also proposed that orders the results according to both the relevancy and the importance of documents. This approach helps user to restrict his search to some top documents in particular clusters of his interest.

DBCCOM: Density Based Clustering with Constraints and Obstacle Modeling

Spatial data clustering groups similar objects based on their distance, connectivity, or their relative density in space whereas in the real world, there exist many physical constraints e.g. highways, rivers, hills etc. that may affect the result of clustering. Therefore, these obstacles when taken into consideration render the cluster analysis a hopelessly slow exercise. In this paper, a clustering method is being proposed that considers the presence of physical obstacles and uses obstacle modeling as a preprocessing step. With a view to prune the search space and reduce the complexity at search levels, the work further incorporates the hierarchical structure into the existing clustering structure. The clustering algorithm can detect clusters of arbitrary shapes and sizes and is insensitive to noise and input order.

A semantic search system using query definitions

A Web Search Engine is designed to search for information over World Wide Web. When user submits a query, the generated information is often very large and inaccurate, that results in increased user perceived latency. In this paper, a novel approach of Definition-based search is being introduced that solves this problem. The proposed system searches and displays results based on themes, definitions and synonyms of the query keywords generally extracted from the web resources and stored in a separate definition repository. It extends the traditional keyword based web search in order to provide semantic and context based search. The system works as a layer above the keyword based search engine to generate sub-queries based on different meanings of query keywords, which in turn, are sent to the next layer i.e. to keyword-based search engine to perform Web search. The experiments show that this approach is efficient as it results in relevant pages and reduces the search space to a large extent.

Page ranking algorithms in online digital libraries: A survey

With the exponential growth of academic digital libraries, ranking has become an extremely challenging task. When a researcher tries to retrieve relevant scientific literature, or perform a literature review based upon which to build their research, then ranking of search results of a user query plays an important role. Ranking provides an order so that users can easily navigate through the search results and find the desired information content. The various ranking algorithms have been proposed based upon many factors like citations to publications, content similarity, annotations etc. This paper presents an outline regarding various page ranking algorithms for academic digital libraries and highlights comparison of these algorithms in context of performance. This comparative analysis encourages for further required improvement in the related field.

A Novel Approach for Semantic Prefetching Using Semantic Information and Semantic Association

Exponential growth of web accesses on the Internet causes substantial delays in providing services to the user. Web prefetching is an effective solution that can improve the performance of the web by reducing the latency perceived by the user. Content on the web page also provides meaningful data to predict the future requests. This paper presents a content-based semantic prefetching approach. The proposed approach basically works on the semantic preferences of the tokens present in the anchor text associated with the URLs. To make more accurate predictions, it also uses the semantic information which is explicitly embedded with each link. It then computes the semantic association between the tokens and links then associates weightage in order to improve the prediction accuracy. This prefetching scheme would be more effective for long browsing sessions and will achieve good hit rate.

EasyOnto: A Collaborative Semiformal Ontology Development Platform

With an incessant development of the information technology, ontology has been widely applied to various fields for knowledge representation. Therefore, ontology construction and ontology extension has become a great area of research. Creating ontology should not be confined to the thinking process of few ontology engineers. To develop common ontologies for information sharing, they should satisfy the requirements of different people for a particular domain. Also, ontology engineering should be a collaborative process for faster development. As Social Web is growing, its simplicity proves to be successful in attracting mass participation. This paper aims in developing a platform “EasyOnto” which provide simple and easy graphical user interface for users to collaboratively contribute in developing semiformal ontology.

Evolution of FOAF and SIOC in Semantic Web: A Survey

The era of social web has been growing tremendously over the web. Users are getting allured towards new paradigms tools and services of social web. The amount of information available on social web is produced by sharing of beliefs, reviews and knowledge by various online communities. Interoperability and portability of social data are one of the major bottlenecks of social network applications like Facebook, Twitter, Flicker and many more. In order to represent and integrate social information explicitly and efficiently, it is mandatory to enrich social information with the power of semantics. The paper is categorized into following sections. Section 2 describes various studies conducted in context of social semantic web. Section 3 makes readers aware of concept of social web and various issues associated with it. Section 4 describes use of ontologies in achieving interoperability between social and semantic web. Section 5 concludes the giver paper.

Ontological Extension to Multilevel Indexing

The World Wide Web (WWW) creates many new challenges to information retrieval. As the information on Web grows so rapidly, the need of a user efficiently searching some specific piece of information becomes increasingly imperative. The index structure has been considered as a key part of the search process in search engines. Indexing is an assistive technology mechanism commonly used in search engines. Indices are used to quickly locate data without having to search every row in a database table every time it is accessed. Hence, it helps in improving the speed and performance of the search system. Building a good search system, however, is very difficult due to the fundamental challenge of predicting users search intent. The indexing scheme used in the solution is multilevel index structure, in which indices are arranged in levels and promote sequential as well as direct access of records stored in the index; also, the documents are clustered on the basis of context based which provides more refined results to the user query.

Collaborative Filtering-Based Recommender System

Recommender systems have changed the way people find products, information, and services on the web. These kinds of systems study patterns of behavior to know someone’s interest will in a collection of things he has never experienced. Collaborative filtering is a popular recommendation algorithm that works to find user’s interest patterns and recommendations based on the ratings or behavior of other users or target user in the system. The assumption behind this method is to find a user with similar interest to the active user and use his/her preference for recommendation to the active user. But several issues exist in the kind of method. For example, accuracy, sparsity, and cold start. In this paper, an improved recommendation technique is proposed to address the issues identified.