Opinion texts summarization based on texts concepts with multi-objective pruning approach.

IF 2.5 3区计算机科学 Q2 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Journal of Supercomputing Pub Date : 2023-01-01 DOI:10.1007/s11227-022-04842-4

Sajjad Jahanbakhsh Gudakahriz, Amir Masoud Eftekhari Moghadam, Fariborz Mahmoudi

{"title":"Opinion texts summarization based on texts concepts with multi-objective pruning approach.","authors":"Sajjad Jahanbakhsh Gudakahriz, Amir Masoud Eftekhari Moghadam, Fariborz Mahmoudi","doi":"10.1007/s11227-022-04842-4","DOIUrl":null,"url":null,"abstract":"<p><p>Considering the huge volume of opinion texts published on various social networks, it is extremely difficult to peruse and use these texts. The automatic creation of summaries can be a significant help for the users of such texts. The current paper employs manifold learning to mitigate the challenges of the complexity and high dimensionality of opinion texts and the K-Means algorithm for clustering. Furthermore, summarization based on the concepts of the texts can improve the performance of the summarization system. The proposed method is unsupervised extractive, and summarization is performed based on the concepts of the texts using the multi-objective pruning approach. The main parameters utilized to perform multi-objective pruning include relevancy, redundancy, and coverage. The simulation results show that the proposed method outperformed the MOOTweetSumm method while providing an improvement of 11% in terms of the ROGUE-1 measure and an improvement of 9% in terms of the ROGUE-L measure.</p>","PeriodicalId":50034,"journal":{"name":"Journal of Supercomputing","volume":"79 5","pages":"5013-5036"},"PeriodicalIF":2.5000,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9540092/pdf/","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Supercomputing","FirstCategoryId":"94","ListUrlMain":"https://doi.org/10.1007/s11227-022-04842-4","RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"COMPUTER SCIENCE, HARDWARE & ARCHITECTURE","Score":null,"Total":0}

引用次数: 1

Abstract

Considering the huge volume of opinion texts published on various social networks, it is extremely difficult to peruse and use these texts. The automatic creation of summaries can be a significant help for the users of such texts. The current paper employs manifold learning to mitigate the challenges of the complexity and high dimensionality of opinion texts and the K-Means algorithm for clustering. Furthermore, summarization based on the concepts of the texts can improve the performance of the summarization system. The proposed method is unsupervised extractive, and summarization is performed based on the concepts of the texts using the multi-objective pruning approach. The main parameters utilized to perform multi-objective pruning include relevancy, redundancy, and coverage. The simulation results show that the proposed method outperformed the MOOTweetSumm method while providing an improvement of 11% in terms of the ROGUE-1 measure and an improvement of 9% in terms of the ROGUE-L measure.

Abstract Image

查看原文本刊更多论文

基于文本概念的多目标剪枝方法的意见文本摘要。

考虑到各种社交网络上发表的大量意见文本，阅读和使用这些文本是极其困难的。摘要的自动创建可以为这些文本的用户提供重要的帮助。本文采用流形学习来缓解意见文本的复杂性和高维性的挑战，并采用K-Means算法进行聚类。此外，基于文本概念的摘要可以提高摘要系统的性能。提出的方法是无监督抽取，并利用多目标剪枝方法根据文本的概念进行摘要。用于执行多目标剪枝的主要参数包括相关性、冗余和覆盖率。仿真结果表明，该方法优于MOOTweetSumm方法，在ROGUE-1度量方面提高了11%，在ROGUE-L度量方面提高了9%。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Journal of Supercomputing 工程技术-工程：电子与电气

CiteScore

6.30

自引率

12.10%

发文量

734

审稿时长

13 months

期刊介绍： The Journal of Supercomputing publishes papers on the technology, architecture and systems, algorithms, languages and programs, performance measures and methods, and applications of all aspects of Supercomputing. Tutorial and survey papers are intended for workers and students in the fields associated with and employing advanced computer systems. The journal also publishes letters to the editor, especially in areas relating to policy, succinct statements of paradoxes, intuitively puzzling results, partial results and real needs. Published theoretical and practical papers are advanced, in-depth treatments describing new developments and new ideas. Each includes an introduction summarizing prior, directly pertinent work that is useful for the reader to understand, in order to appreciate the advances being described.