Open AccessIntegration Distance Similarity with Keyword Algorithm for Improving Cohesion between Sentences in Text Summarization
Author(s) -
Rizki Darmawan,
Adi Wijaya
Publication year - 2019
Publication title -
iop conference series. materials science and engineering
Language(s) - English
Resource type - Journals
eISSN - 1757-899X
pISSN - 1757-8981
DOI - 10.1088/1757-899x/532/1/012019
Subject(s) - jaccard index , cohesion (chemistry) , automatic summarization , computer science , dice , cosine similarity , keyword extraction , similarity (geometry) , natural language processing , artificial intelligence , information retrieval , data mining , pattern recognition (psychology) , algorithm , mathematics , statistics , chemistry , organic chemistry , image (mathematics)
In recent time the exponential growth of textual information available on the Web, end user need to be able to access information in summary form. Commonly the method to get the summary is extraction method. One of extraction method that easier and commonly used is Keyword Algorithm, but this algorithm has a weakness in the cohesion between the sentences. Distance similarity method is one method used for solving the cohesion problem. The idea of this paper is to improve cohesion between sentences based on extraction of keyword algorithm. The hybrid keyword algorithm and the distance similarity method is proposed. The proposed method was compared three distance similarity such as Cosine, Dice and Jaccard that looking for the cohesiveness between sentences according to keyword algorithm extraction and performance as standard of evaluation. The result showed that Dice has the highest cohesion degree is 45.87 %. Although the best performance is Cosine that performance is influenced with gold standard of abstractive human summary.