A Hybrid Approach For Web Search Result Clustering Based On Genetic Algorithm With K-means

Nowadays, search engines tend to use the latest technologies in enhancing the personalization of web
searches, which leads to a better understanding of user needs. One of these technologies is web search results
clustering which returns meaningful labeled clusters from a set of Web snippets retrieved from any Web
search engine for a given user’s query. Search result clustering aims to improve searching for information
from the potentially huge amount of search results. These search results consist of URLs, titles, and snippets
(descriptions or summaries) of web pages. Dealing with search results is considered as treating large-scale
data, which indeed has a significant impact on effectiveness and efficiency. However, unlike traditional text
mining, queries and snippets tend to be shorter which leads to more ambiguity. K-means tend to converge to
local optima and depend on the initial value of cluster centers. In the past, many heuristic algorithms have
been introduced to overcome this local optima problem. Nevertheless, these algorithms suffer several
shortcomings. In this paper, we present an efficient hybrid web search results clustering algorithm referred
to as G-K-M, whereby, we combine K-means with a modified genetic algorithm. The AOL standard dataset
is used for evaluating web data log clustering. ODP-239 and MORESQUE are used as the main gold standards
for the evaluation of search results clustering algorithms. The experimental results show that the proposed
approach demonstrates its significant advantages over traditional clustering. Besides, results show that
proposed methods are promising approaches that can make search results more understandable to the users
and yield promising benefits in terms of personalization.