Abstract:
Automatic text summarization plays increasingly an important role with the
exponential growth of documents on the Web. Numerous approaches have been
proposed to identify important contents for automatic text summarization.
Sentence scoring approaches mark scores for input sentences rank all of them
decadently. Only higher ranked sentences are selected to be part of the summary.
Find the informative sentences is an important issue for the researchers in an
extractive based automatic text summarization. This research aim to use extraction
based automatic single document text summarization method using evolutionary
algorithm called Ant Colony Optimization algorithm ACO to produce good
summaries. We use ACO algorithm to find out the best sub set feature weight
score. To the best of our knowledge has never been used for solving text
summarization problem before. To evaluate the proposed method standard dataset
from Document Understanding Conference (DUC) 2002 in used and the Recall-
Oriented Understudy for Gisting Evaluation (ROUGE) as the standard evaluation
measurement toolkit is used .Set of evolutionary algorithms are used in this
research in term of evolutionary the experimental results showed our proposed
method has performed well compared with algorithms (Particle Swarm
Optimization methods and Genetic Algorithm). Although our targeted ACO
algorithm is select to improve the performance of text summarization has not out
performance the latest proposed method (Differential Evolution) but performance
satisfactory
