Utilizing Universal Information Extraction based on Generative Large Language Model to mine online reviews for navigating online health consultation

IF 6.8 1区计算机科学 0 COMPUTER SCIENCE, INFORMATION SYSTEMS

Information Sciences Pub Date : 2025-06-16 DOI:10.1016/j.ins.2025.122428

Yanfang Ma , Lina Liu , Yu Gong , Yan Tu , Zibiao Li

{"title":"Utilizing Universal Information Extraction based on Generative Large Language Model to mine online reviews for navigating online health consultation","authors":"Yanfang Ma , Lina Liu , Yu Gong , Yan Tu , Zibiao Li","doi":"10.1016/j.ins.2025.122428","DOIUrl":null,"url":null,"abstract":"<div><div>Given the limited medical resources and the increasing healthcare demand, mobile health applications (mHealth apps) have become an important complement to enhance medical accessibility. As the number of mHealth apps is booming, it is difficult for patients to select an ideal application, particularly for the critical function, online health consultation services, which are seldom concerned. This study proposes a method to select a suitable application for online health consultation. First, we employ the Octopus crawler software to collect online reviews about online health consultation from Little Red Book and Weibo, popular content sharing platforms. Then, Universal Information Extraction based on Generative Large Language Model (UIE-GLLM) is introduced to process online reviews, which can automatically identify the evaluation attributes that patients really care about. And then, linguistic hesitant Z-number (LHZN), a preference expression method enabling decision makers to convey ambiguity in evaluation information, is introduced to express the applications based on the attributes learned by UIE-GLIM. Finally, an optimal application is obtained using large-scale group decision-making method. Comparative analysis indicates that LHZN significantly improve consensus degree. Compared with LDA and TF-IDF, UIE-GLLM can extract more comprehensive attributes from reviews without complex preprocessing.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"719 ","pages":"Article 122428"},"PeriodicalIF":6.8000,"publicationDate":"2025-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Information Sciences","FirstCategoryId":"94","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0020025525005602","RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"0","JCRName":"COMPUTER SCIENCE, INFORMATION SYSTEMS","Score":null,"Total":0}

引用次数: 0

Abstract

Given the limited medical resources and the increasing healthcare demand, mobile health applications (mHealth apps) have become an important complement to enhance medical accessibility. As the number of mHealth apps is booming, it is difficult for patients to select an ideal application, particularly for the critical function, online health consultation services, which are seldom concerned. This study proposes a method to select a suitable application for online health consultation. First, we employ the Octopus crawler software to collect online reviews about online health consultation from Little Red Book and Weibo, popular content sharing platforms. Then, Universal Information Extraction based on Generative Large Language Model (UIE-GLLM) is introduced to process online reviews, which can automatically identify the evaluation attributes that patients really care about. And then, linguistic hesitant Z-number (LHZN), a preference expression method enabling decision makers to convey ambiguity in evaluation information, is introduced to express the applications based on the attributes learned by UIE-GLIM. Finally, an optimal application is obtained using large-scale group decision-making method. Comparative analysis indicates that LHZN significantly improve consensus degree. Compared with LDA and TF-IDF, UIE-GLLM can extract more comprehensive attributes from reviews without complex preprocessing.

查看原文本刊更多论文

基于生成式大语言模型的通用信息提取挖掘在线评论，为在线健康咨询导航

鉴于有限的医疗资源和不断增长的医疗需求，移动健康应用程序（移动健康应用程序）已成为提高医疗可及性的重要补充。随着移动健康应用程序数量的激增，患者很难选择一个理想的应用程序，特别是对于关键功能，在线健康咨询服务，很少有人关注。本研究提出一种选择适合在线健康咨询的应用程序的方法。首先，我们使用八达通爬虫软件在小红书和微博这两个热门的内容分享平台上收集在线健康咨询的在线评论。然后，引入基于生成式大语言模型的通用信息提取（UIE-GLLM）对在线评论进行处理，自动识别患者真正关心的评价属性；然后，基于ie - glim学习到的属性，引入语言犹豫z数（LHZN）这一决策者表达评价信息歧义性的偏好表达方法来表达应用。最后，利用大规模群体决策方法得到了最优应用。对比分析表明，LHZN显著提高了共识度。与LDA和TF-IDF相比，ie - gllm可以从评论中提取更全面的属性，无需进行复杂的预处理。

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

Information Sciences 工程技术-计算机：信息系统

CiteScore

14.00

自引率

17.30%

发文量

1322

审稿时长

10.4 months

期刊介绍： Informatics and Computer Science Intelligent Systems Applications is an esteemed international journal that focuses on publishing original and creative research findings in the field of information sciences. We also feature a limited number of timely tutorial and surveying contributions. Our journal aims to cater to a diverse audience, including researchers, developers, managers, strategic planners, graduate students, and anyone interested in staying up-to-date with cutting-edge research in information science, knowledge engineering, and intelligent systems. While readers are expected to share a common interest in information science, they come from varying backgrounds such as engineering, mathematics, statistics, physics, computer science, cell biology, molecular biology, management science, cognitive science, neurobiology, behavioral sciences, and biochemistry.