D. Rafiei and A. O. Mendelzon. What is this Page Known for? Computing Web Page Reputations. In Proc. of the 9th International World Wide Web Conference, pages 823--835, 2000.  Home/Search   Document Not in Database   Summary   Related Articles   Check

....Guided by some experimental queries, we propose some formal criteria for evaluating and comparing link analysis algorithms. Keywords: link analysis, web searching, hubs, authorities, SALSA, Kleinberg s algorithm, threshold, Bayesian. 1 Introduction In recent years, a number of papers [7, 14, 5, 20, 15, 8] have considered the use of hypertext links to determine the value of different web pages. In particular, these papers consider the extent to which hypertext links between World Wide Web documents can be used to determine the relative authority values of these documents for various search ....

....at each step as follows: With probability ffl it jumps to a sample from a distribution D( Delta) e.g. the uniform distribution) and with probability 1 Gamma ffl it jumps uniformly at random to one of the pages linked from the current page. This idea is also used by Rafiei and Mendelzon [20] for computing the reputation of a page. Intuitively, the value of PR(i) is a measure of the importance or authority of the web page i. This ranking is used as one component of the Google search engine, to help determine how to order the pages returned by a web search query. 2.2 Kleinberg s ....

[Article contains additional citation context not shown here]

D. Rafiei and A. Mendelzon. What is this page known for? Computing web page reputations. In Proceedings of the 9th International World Wide Web Conference, Amsterdam, Netherlands, 2000.

....of Kleinberg [31, 32] and Brin and Page [9] was followed by a number of extensions and modifications. Bharat and Henzinger [5] and Chakrabarti et al. 11] consider improvements on the HITS algorithm by using textual information to weight the importance of nodes and links. Rafiei and Mendelzon [42, 38] consider a variation of the HITS algorithm that uses random jumps, similar to SALSA. The same algorithm is also considered by Ng Zheng and Jordan [39, 40] termed Randomized HITS. Extensions of the HITS algorithm that use multiple eigenvectors were proposed by Ng, Zheng and Jordan [40] and ....

....algorithm. Surprisingly, we observed that experimentally it performs very similarly to the INDEGREE algorithm. 4 A Theoretical Framework for the Analysis of LAR Algorithms The seminal work of Kleinberg [31] and Brin and Page [9] was followed by an avalanche of Link Analysis Ranking algorithms [8, 5, 34, 42, 3, 1, 40]. Faced with this wide range of choices for LAR algorithms, researchers usually resort to experiments to evaluate them and determine which one is more appropriate for the problem at hand. However, experiments are only indicative of the behavior of the LAR algorithm. In many cases, experimental ....

D. Rafiei and A. Mendelzon. What is this page known for? Computing web page reputations. In Proceedings of the 9th International World Wide Web Conference, Amsterdam, Netherlands, 2000.

....of multigrid methods, see [16] 8. 2 PageRank Seminal algorithms for graph analysis for Web search were introduced by Page et al. 17] PageRank) and Kleinberg [14] HITS) Much additional work has been done on improving these algorithms and extending them to new search and text mining tasks [4, 6, 18, 3, 19, 11]. More applicable to our work are several papers which discuss the computation of PageRank itself [10, 2, 13] Haveliwala [10] explores memory efficient computation, and suggests using induced orderings, rather than residuals, to measure convergence. Arasu et al. 2] uses the Gauss Seidel method ....

D. Rafiei and A. O. Mendelzon. What is this page known for? Computing web page reputations. In Proceedings of the Ninth International World Wide Web Conference, 2000.

....web pages. Independently, Brin and Page proposed the PageRank algorithm [5] which become an integral component of the successful Google search engine [9] These two algorithms spawned the research field of link analysis ranking, and they were followed by a substantial amount of research work [4, 3, 13, 16, 2, 1, 15]. Most of link analysis ranking algorithms start with a set of web pages, interconnected with hypertext links. Given the underlying graph, the algorithms extract the principal eigenvector (s) of a matrix associated with the graph, and rank the pages according to the value of each page in this ....

....by good hubs. In PAGERANK good authorities are pointed to by good authorities. The HITS and PAGERANK algorithms were followed by a substantial number of variations and enhancements. Most of the subsequent work follows a similar algebraic approach, manipulating some matrix related to the web graph [4, 3, 13, 16, 2, 1, 15]. Recently, there were some interesting attempts in applying statistical, and machine learning tools for computing authority weights [4, 6, 11] 3. DYNAMICAL SYSTEMS A dynamical system describes a weight propagation scheme on the nodes of a graph. We construct the Base Set as described by ....

[Article contains additional citation context not shown here]

D. Rafiei and A. Mendelzon. What is this page known for? Computing web page reputations. In Proceedings of the 9th International World Wide Web Conference, Amsterdam, Netherlands, 2000.

....of multigrid methods, see [15] 7. 2 PageRank Seminal algorithms for graph analysis for Web search were introduced by Page et al. 16] PageRank) and Kleinberg [14] HITS) Much additional work has been done on improving these algorithms and extending them to new search and text mining tasks [3, 4, 17, 2, 18, 8]. More applicable to our work are several papers which discuss the computation of PageRank itself [7, 1, 11] Haveliwala [7] explores memory efficient computation, and suggests using induced orderings, rather than residuals, to measure convergence. Arasu et al. 1] uses the Gauss Seidel method to ....

D. Rafiei and A. O. Mendelzon. What is this page known for? Computing web page reputations. In Proceedings of the Ninth International World Wide Web Conference, 2000.

....of multigrid methods, see [17] 7. 2 PageRank Seminal algorithms for graph analysis for Web search were introduced by Page et al. 18] PageRank) and Kleinberg [15] HITS) Much additional work has been done on improving these algorithms and extending them to new search and text mining tasks [4, 6, 19, 3, 20, 11]. More applicable to our work are several papers which discuss the computation of PageRank itself [10, 2, 14] Haveliwala [10] explores memory efficient computation, and suggests using induced orderings, rather than residuals, to measure convergence. Arasu et al. 2] uses the Gauss Seidel method ....

D. Rafiei and A. O. Mendelzon. What is this page known for? Computing web page reputations. In Proceedings of the Ninth International World Wide Web Conference, 2000.

....of multigrid methods, see [16] 8. 2 PageRank Seminal algorithms for graph analysis for Web search were introduced by Page et al. 17] PageRank) and Kleinberg [14] HITS) Much additional work has beendone on improving these algorithms and extending them to new search and text mining tasks [4, 6, 18, 3, 19, 11]. More applicable to our work are several papers which discuss the computation of PageRank itself [10,2, 13] Haveliwala [10] explores memory efficient computation,and suggests using induced orderings, rather than residuals, to measure convergence. Arasu et al. 2] uses the Gauss Seidel method to ....

D. Rafiei and A. O. Mendelzon. What is this page known for? Computing web page reputations. In Proceedings of the Ninth International World Wide Web Conference, 2000.

....Automatic generation of RDF metadata is also presented in [10] where a metadata element set, closely related to the Dublin Core, is given to record the characteristics of the resources. Further strategies to generate characteristic terms of a web site from the WWW automatically are presented in [15] and [17] 5 Architecture of QUEST In this section we introduce the architecture of QUEST a meta search engine for specialized collections on the web which has been realized prototypically at our chair 9 . 9 The protoype can be accessed at ....

D. Rafiei and A. O. Mendelzon. What is this Page known for? Computing Web Page Reputations. In Proceedings of the 9th International WWW Conference, 2000.

....4 Department of Computer Science, University of Toronto, Toronto, Ontario, Canada M5S 3G4. E mail: tsap cs.toronto.edu. Web: http: www.cs. toronto.edu tsap 0 Finding Authorities and Hubs From Link Structures on the World Wide Web 1 Introduction In recent years, a number of papers [3, 8, 11, 9, 4] have considered the use of hypertext links to determine the value of different web pages. In particular, these papers consider the extent to which hypertext links between World Wide Web documents can be used to determine the relative authority values of these documents for various search ....

....on page i by a random walk which proceeds at each step as follows: With probability d it jumps to a sample from the distribution D( Delta) and with probability 1 Gamma d it jumps uniformly at random to one of the pages linked from the current page. This idea is also used by Rafiei and Mendelzon [11] for computing the reputation of a page. Intuitively, the value of PR(i) is a measure of the importance or authority of the web page i. This ranking is used as one component of the Google search engine, to help determine how to order the pages returned by a web search query. 1 2.2 Kleinberg s ....

[Article contains additional citation context not shown here]

D. Rafiei and A. Mendelzon. What is this page known for? Computing web page reputations. In 9th International World Wide Web Conference, Amsterdam, Netherlands, 2000.

....Guided by some experimental queries, we propose some formal criteria for evaluating and comparing link analysis algorithms. Keywords: link analysis, web searching, hubs, authorities, SALSA, Kleinberg s algorithm, threshold, Bayesian. 1 Introduction In recent years, a number of papers [7, 14, 5, 19, 15, 8] have considered the use of hypertext links to determine the value of different web pages. In particular, these papers consider the extent to which hypertext links between World Wide Web documents can be used to determine the relative authority values of these documents for various search ....

....at each step as follows: With probability ffl it jumps to a sample from a distribution D( Delta) e.g. the uniform distribution) and with probability 1 Gamma ffl it jumps uniformly at random to one of the pages linked from the current page. This idea is also used by Rafiei and Mendelzon [19] for computing the reputation of a page. Intuitively, the value of PR(i) is a measure of the importance or authority of the web page i. This ranking is used as one component of the Google search engine, to help determine how to order the pages returned by a web search query. 2.2 Kleinberg s ....

[Article contains additional citation context not shown here]

D. Rafiei and A. Mendelzon. What is this page known for? Computing web page reputations. In Proceedings of the 9th International World Wide Web Conference, Amsterdam, Netherlands, 2000. 23

....That is, links emanating from pages with high reputations are weighted more heavily. The concepts of authorities and hubs, together with the Page Rank model, can also be used to compute the reputation rank of a page; and those topics for which the page has a good reputation are then identified [45]. Some other ad hoc methods include an HVV (Hyperlink Vector Voting) method [37] and a system WebQuery [9] The former method uses the content of hyperlinks to a document to rank its relevance to the query terms, while the latter system studies 6 the structural relationships among the nodes ....

Davood Rafiei and Alberto O. Mendelzon. What is this page known for? Computing Web page reputations. In Proceedings of the 9 th International World Wide Web Conference, Amsterdam, Netherlands, May 2000.

....et al. 5] and Bharat and Henzinger [6] propose heuristic methods for differentially weighting links. Our algorithm can be viewed as a more principled approach to the same problem. It can also be viewed as an analog for PageRank of Cohn and Hofman s [7] variation of HITS. Rafiei and Mendelzon s [8] algorithm, which biases PageRank towards pages containing a specific word, is a predecessor of our work. Haveliwala [9] proposes applying an optimized version of PageRank to the subset of pages containing the query terms, and suggests that users do this on their own machines. We first describe ....

D. Rafiei and A. Mendelzon.What is this page known for? Computing web page reputations. Proceedings of the Ninth International World Wide Web Conference.

....summarize the results derived in [10] and show how they give insight into ways of designing stable link analysis algorithms. This then motivates two new algorithms: Randomized HITS, which merges the hubs and authorities notion from HITS with a stabilizing reset mechanism from PageRank (see also [14]) and Subspace HITS, which provides a principled way of combining multiple eigenvectors from HITS to yield aggregate authority scores. These new algorithms are also demonstrated empirically to produce good results on both academic citation and web query data. We also explore the issue of the ....

Davood Rafiei and Alberto Mendelzon. What is this Page Known for? Computing Web Page Reputations. In Proc. WWW9 Conference, 2000.

....Guided by some experimental queries, we propose some formal criteria for evaluating and comparing link analysis algorithms. Keywords link analysis, web searching, hubs, authorities, SALSA, Kleinberg s algorithm, threshold, Bayesian 1. INTRODUCTION In recent years, a number of papers [3, 8, 11, 9, 4] have considered the use of hypertext links to determine the value of di#erent web pages. In particular, these papers consider the extent to which hypertext links between World Wide Web documents can be used to determine the relative authority values of these documents for various search queries. ....

....spent on page i by a random walk which proceeds at each step as follows: With probability d it jumps to a sample from the distribution D( and with probability 1 d it jumps uniformly at random to one of the pages linked from the current page. This idea is also used by Rafiei and Mendelzon [11] for computing the reputation of a page. Intuitively, the value of PR(i) is a measure of the importance or authority of the web page i. This ranking is used as one component of the Google search engine, to help determine how to order the pages returned by a web search query. 2.2 Kleinberg s ....

[Article contains additional citation context not shown here]

D. Rafiei and A. Mendelzon. What is this page known for? Computing web page reputations. In 9th International World Wide Web Conference, Amsterdam, Netherlands, May 2000.

....4 Department of Computer Science, University of Toronto, Toronto, Ontario, Canada M5S 3G4. E mail: tsap cs.toronto.edu. Web: http: www.cs. toronto.edu tsap 0 Finding Authorities and Hubs From Link Structures on the World Wide Web 1 Introduction In recent years, a number of papers [3, 8, 11, 9, 4] have considered the use of hypertext links to determine the value of di erent web pages. In particular, these papers consider the extent to which hypertext links between World Wide Web documents can be used to determine the relative authority values of these documents for various search queries. ....

....of time spent on page i by a random walk which proceeds at each step as follows: With probability d it jumps to a sample from the distribution D( and with probability 1 d it jumps uniformly at random to one of the pages linked from the current page. This idea is also used by Ra ei and Mendelzon [11] for computing the reputation of a page. Intuitively, the value of PR(i) is a measure of the importance or authority of the web page i. This ranking is used as one component of the Google search engine, to help determine how to order the pages returned by a web search query. 1 2.2 Kleinberg s ....

[Article contains additional citation context not shown here]

D. Raei and A. Mendelzon. What is this page known for? Computing web page reputations. In 9th International World Wide Web Conference, Amsterdam, Netherlands, 2000.

....sources is a challenge to metasearch engines. We present an autonomous ranking method, meaning one that does not depend on the individual rankings returned by the engines participating in the search. Instead, it applies our TOPIC method for evaluating the reputation of a web page on a topic [7, 6] to the problem of ranking the results to a query. TOPIC is available at www.cs.toronto.edu db topic) Methods for ranking query result pages based on some notion of relatedness or authoritativeness have been studied in the literature [5, 1] and implemented in commercial systems [3] There is ....

D. Rafiei and A.O. Mendelzon. What is this page known for? Computing Web page reputations. In Proceedings of the 9th International World Wide Web Conference, pages 823--835, Amsterdam, May 2000. Elsevier Science.

....that are considered authorities on that topic. The algorithm, known as HITS, is based on the hypothesis that for broad topics, authority is conferred by a set of hub pages, which are recursively defined as a set of pages with a large number of links to many relevant authorities. In earlier work [18], we developed two formulations of the notion of reputation based on random walk models of simple Web browsing behaviours. The first model, based on the idea of one level influence propagation, generalizes PageRank; the main difference is that the ranking is performed with respect to a specific ....

....by the Web surfers searching for pages on that topic. Specifically, for a given page p and topic t, RM (p; t) is, to some degree, a rough approximation to the number of visits made to page p by a random surfer who wanders the Web by following the links and searching for pages on topic t (see [18] for details) 2.2 Rank Computations Consider the rank computation in the simple case where both a page p and a word or phrase t are given. We can use a search engine to estimate the values of In(p) I(p; t) and N(t) and then plug these estimates in to compute RM (p; t) For example, we can ....

D. Rafiei and A. O. Mendelzon. What is this page known for? Computing Web page reputations. In Proc. of the WWW9 Conference, pages 823--835, Amsterdam, May 2000. Elsevier Science.

No context found.

D. Rafiei and A. O. Mendelzon. What is this Page Known for? Computing Web Page Reputations. In Proc. of the 9th International World Wide Web Conference, pages 823--835, 2000.

No context found.

D. Rafiei and A. Mendelzon (2000). What is this page known for? Computing web page reputations. Proceedings of the Ninth International World Wide Web Conference.

No context found.

D. Rafiei and A. O. Mendelzon. What is this page known for? Computing web page reputations. In Proceedings of the Ninth International World Wide Web Conference, 2000.

No context found.

D. Rafiei and A. Mendelzon (2000). What is this page known for? Computing web page reputations. Proceedings of the Ninth International World Wide Web Conference.

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC