| Atsumi M. (1997) Extraction of user's interests from web pages based on genetic algorithm. English version of the original Japanese paper published in IPSJ SIG Notes (Information Processing Society of Japan, The Special Interest Groups Notes), 97(51), pp 13-18. |
....in the web with two different individual representations. However, both GAs have in common the fact that they do not focus on the use of information about web page structure. By contrast, in subsection 3.1.2 we will discuss a GA that focus on the use of information about web page structure. In [2] an individual represents the profile of a user s interest, consisting of a set of terms and their corresponding weights. Hence, the GA tries to find the best possible combination of terms (words) and term weights that allow the retrieval of documents relevant for the user. More precisely, an ....
....constraint; b) using special repair operators that transform an invalid individual into a valid one; or (c) avoiding the creation of an invalid individual altogether, by not applying a genetic operator when it would produce an invalid individual. The third approach (c) seems to be the one used in [2]. Crossover and mutation are performed only if they produce valid offspring, respecting the term uniqueness constraint. The crossover operator is based on the idea of two point crossover, as discussed in section 2.1. There are two kinds of mutation operator, weight mutation and term mutation. ....
[Article contains additional citation context not shown here]
Atsumi M. (1997) Extraction of user's interests from web pages based on genetic algorithm. English version of the original Japanese paper published in IPSJ SIG Notes (Information Processing Society of Japan, The Special Interest Groups Notes), 97(51), pp 13-18.
No context found.
Atsumi, M. (1997). Extraction of User's Interests from Web Pages based on Genetic Algorithm. IPSJ SIG Vol. 97 No. 51, pp. 13-18.
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