Recommendation algorithms aim at proposing “next” pages to a user based on her navigational behavior. In the vast majority of related algorithms, only the usage data are used to produce recommendations. We claim that taking also into account the web structure and using link analysis algorithms ameliorates the quality of recommendations. In this paper we present UPR, a personalization algorithm ...

Web-page re-ranking plays an important role in Web systems. Satisfactory and Useful knowledge discovery from Web usage data representation for effective Webpage recommendations are challenging and crucial. This paper proposes a novel method to efficiently provide better Web-page recommendation through semantic-enhancement by integrating the Web usage knowledge and domain. A number of effective ...

The Web is a large collection of heterogeneous pages. Web documents are not always descriptive and accurate in content. In addition, a significant difference between the problems of Web search and traditional text search is the availability of hyperlinks between pages. A page on the Web might possibly be cited by or cite other pages. When evaluating a page, the neighborhood of the page might be...

PageRank, the popular link-analysis algorithm for ranking web pages, assigns a query and user independent estimate of “importance” to web pages. Query and user sensitive extensions of PageRank, which use a basis set of biased PageRank vectors, have been proposed in order to personalize the ranking function in a tractable way. We analytically compare three recent approaches to personalizing Page...

The TREC-2002 Web Track moved away from non-Web relevance ranking and towards Webspecific tasks on a 1.25 million page crawl “.GOV”. The topic distillation task involved finding pages which were relevant, but also had characteristics which would make them desirable inclusions in a distilled list of key pages. The named page task is a variant of last year’s homepage finding task. The task is to ...

Early Web search engines closely resembled Information Retrieval (IR) systems which had matured over several decades. Around 1996–1999, it became clear that the spontaneous formation of hyperlink communities in the Web graph had much to offer to Web search, leading to a flurry of research on hyperlink-based ranking of query responses. In this paper we show that, over and above inter-page hyperl...

Makoto Yamada,Kyoto University Beyond Ranking: Optimizing Whole-Page Presentation (WSDM'16) Modern search engines aggregate results from different verticals: webpages, news, images, video, shopping, knowledge cards, local maps, etc. Unlike ten blue links", these search results are heterogeneous in nature and not even arranged in a list on the page. This revolution directly challenges the conven...

In the classical theory of social choice, a theory developed by game-theorists and theoretical economists, we consider a set of agents (voters) and a set of alternatives. Each agent ranks the alternatives, and the major aim is to find a good way to aggregate the individual preferences into a social preference. The major tool offered in this theory is the axiomatic approach: study properties (te...

In this paper we introduce a method for Web page-ranking, based on computational geometry to evaluate and test by examples, order relationships among web pages belonging to different knowledge domains. The goal is, through an organising procedure, to learn from these examples a real-valued ranking function that induces ranking via a convexity feature. We consider the problem of self-organising ...

In this paper, we formalize the novel concept of incremental reverse nearest neighbor ranking and suggest an original solution for this problem. We propose an efficient approach for reporting the results incrementally without the need to restart the search from scratch. Our approach can be applied to a multidimensional feature database which is hierarchically organized by any R-tree like index ...