| N.L. Geller. On the citation influence methodology of Pinski and Narin. Information Processing & Management, 14:93--95, 1978. |
....which identifies high quality pages for a given topic by analysing the linkage between authorities, which are pages that are focussed on the topic, and hubs, which are pages that contain useful links to relevant pages on the topic. This approach originates from the area 10 of citation analysis [PN76, Gel78], whose aim is to measure the influence of research in a given subfield using citation data; see also [Lar96] where co citation analysis is used to cluster related web pages. The output of the HITS algorithm is a densely linked focussed subgraph of hubs and authorities which is called a ....
N.L. Geller. On the citation influence methodology of Pinski and Narin. Information Processing & Management, 14:93--95, 1978.
....which identifies high quality pages for a given topic by analysing the linkage between authorities, which are pages that are focussed on the topic, and hubs, which are pages that contain useful links to relevant pages on the topic. This approach originates from the area of citation analysis [PN76, Gel78], whose aim is to measure the influence of research in a given subfield using citation data; see also [Lar96] where co citation analysis is used to cluster related web pages. The output of the HITS algorithm is a densely linked focussed subgraph of hubs and 10 authorities which is called a ....
N.L. Geller. On the citation influence methodology of Pinski and Narin. Information Processing & Management, 14:93--95, 1978.
....high quality pages for a given topic by analysing the linkage between authorities, which are pages that are focused on the topic, and hubs, which are pages that contain useful links to relevant pages on the topic. The roots of this approach originate from the area of citation analysis [PN76, Gel78] whose aim is to measure the influence of 14 research in a given subfield using citation data; see also [Lar96] where co citation analysis is used to cluster related web pages. The output of the HITS algorithm is a densely linked focused subgraph of hubs and authorities which is called a web ....
N.L. Geller. On the citation influence methodology of Pinski and Narin. Information Processing & Management, 14:93--95, 1978.
....is influential if, recursively, it is heavily cited by other influential journals. One can recognize a natural parallel between this and our self referential construction of hubs and authorities; we will discuss the connections below. The concrete construction of Pinski and Narin, as modified by Geller [1978], is the following: The measure of standing of journal j will be called its influence weight and denoted w j . The matrix A of connection strengths will have entries specified as follows: A ij denotes the fraction of the citations from journal i that go to journal j. Following the informal ....
....cites j. Thus, the set of influence weights w j is designed to be a nonzero, nonnegative solution to the system of equations w j ## i A ij w i ; and hence, if w is the vector of influence weights, one has w # 0, w # 0, and A T w # w. This implies that w is a principal eigenvector of A T . Geller [1978] observed that the influence weights correspond to the stationary distribution of the following random process: beginning with an arbitrary journal j, one chooses a random reference that has appeared in j and moves to the journal specified in the reference. Doreian [1988; 1994] showed that one can ....
GELLER, N. 1978. On the citation influence methodology of Pinski and Narin. Inf. Proc. Manage. 14, 93--95.
....if, recursively, it is heavily cited by other influential journals. One can recognize a natural parallel between this and our self referential construction of hubs and authorities; we will discuss the connections below. The concrete construction of Pinski and Narin, as modified by Geller [27], is the following. The measure of standing of journal 15 j will be called its influence weight and denoted w j . The matrix A of connection strengths will have entries specified as follows: A ij denotes the fraction of the citations from journal i that go to journal j. Following the informal ....
....set of influence weights w j is designed to be a non zero, non negative solution to the system of equations w j = # i A ij w i ; and hence, if w is the vector of influence weights, one has w # 0, w #= 0, and A T w = w. This implies that w is a principal eigenvector of A T . Geller [27] observed that the influence weights correspond to the stationary distribution of the following random process: beginning with an arbitrary journal j, one chooses a random reference that has appeared in j and moves to the journal specified in the reference. Doreian [19, 20] showed that one can ....
N. Geller, "On the citation influence methodology of Pinski and Narin," Inf. Proc. and Management, 14(1978), pp. 93--95.
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