Online–offline combined adaptive hotel recommendation system considering attribute importance and group consensus

IF 6.8 1区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Decision Support Systems Pub Date : 2025-07-08 DOI:10.1016/j.dss.2025.114503

Peide Liu , Ran Dang , Peng Wang , Yingcheng Xu , Yunfeng Zhang

{"title":"Online–offline combined adaptive hotel recommendation system considering attribute importance and group consensus","authors":"Peide Liu , Ran Dang , Peng Wang , Yingcheng Xu , Yunfeng Zhang","doi":"10.1016/j.dss.2025.114503","DOIUrl":null,"url":null,"abstract":"<div><div>With the proliferation of tourism websites, online reviews have become indispensable for offline decision-makers when selecting hotels. Solely relying on personal judgment poses risks amid diverse preferences. Thus, this study aimed to create a hotel recommendation system that integrates online reviews and ratings with offline travel groups. First, the sentiment analysis of online reviews was integrated with ratings using heterogeneous reviewer weights, transforming them into probabilistic linguistic term sets. Second, by predicting reviewers' travel types and clustering them, a method was devised to calculate subgroup weights, considering online group size and offline social trust networks. Third, attribute importance was determined via an online–offline method (attribute importance optimization model) considering the intensity and ordinal information. Subsequently, an adaptive consensus optimization model was developed based on a novel measurement method. This study offers personalized recommendations for offline decision-makers, providing essential guidance for travel agencies and platforms to enhance services and holding significant practical value.</div></div>","PeriodicalId":55181,"journal":{"name":"Decision Support Systems","volume":"196 ","pages":"Article 114503"},"PeriodicalIF":6.8000,"publicationDate":"2025-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Decision Support Systems","FirstCategoryId":"94","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0167923625001046","RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}

引用次数: 0

Abstract

With the proliferation of tourism websites, online reviews have become indispensable for offline decision-makers when selecting hotels. Solely relying on personal judgment poses risks amid diverse preferences. Thus, this study aimed to create a hotel recommendation system that integrates online reviews and ratings with offline travel groups. First, the sentiment analysis of online reviews was integrated with ratings using heterogeneous reviewer weights, transforming them into probabilistic linguistic term sets. Second, by predicting reviewers' travel types and clustering them, a method was devised to calculate subgroup weights, considering online group size and offline social trust networks. Third, attribute importance was determined via an online–offline method (attribute importance optimization model) considering the intensity and ordinal information. Subsequently, an adaptive consensus optimization model was developed based on a novel measurement method. This study offers personalized recommendations for offline decision-makers, providing essential guidance for travel agencies and platforms to enhance services and holding significant practical value.

查看原文本刊更多论文

考虑属性重要性和群体共识的线上线下组合自适应酒店推荐系统

随着旅游网站的激增，在线评论已经成为线下决策者在选择酒店时不可或缺的工具。在多样化的偏好中，仅仅依靠个人判断会带来风险。因此，本研究旨在创建一个酒店推荐系统，将在线评论和评分与线下旅游团体相结合。首先，将在线评论的情感分析与使用异构评论者权重的评级相结合，将其转换为概率语言术语集。其次，通过预测评论者的旅行类型并对其进行聚类，设计了一种考虑在线群体规模和离线社会信任网络的子群体权重计算方法。第三，通过考虑强度和序数信息的线上-线下方法（属性重要性优化模型）确定属性重要性。随后，基于一种新的测量方法，建立了自适应共识优化模型。本研究为线下决策者提供个性化的建议，为旅行社和平台提升服务提供必要的指导，具有重要的实用价值。

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

Decision Support Systems 工程技术-计算机：人工智能

CiteScore

14.70

自引率

6.70%

发文量

119

审稿时长

13 months

期刊介绍： The common thread of articles published in Decision Support Systems is their relevance to theoretical and technical issues in the support of enhanced decision making. The areas addressed may include foundations, functionality, interfaces, implementation, impacts, and evaluation of decision support systems (DSSs).