Scholarlink

<p>With the development of the Internet, online reviews have become an indispensable reference in decision-making processes. As a prevalent social behavior, group decision-making (GDM) is widely applied across various domains. Integrating valuable information from online reviews with GDM not only bridges real-world applications through authentic data but also significantly enhances decision accuracy and reliability. However, members’ preferences in GDM are fuzzy and conflicting, making consensus achievement critical for opinion coordination. This paper proposes an online review-driven group consensus decision-making method based on sentiment analysis and an adaptive feedback model. The method transforms online reviews into attribute-level sentiment scores, uses a novel Precise-Interval Fuzzy Preference Relation (PIFPR) structure to objectively extract endo-confidence, determines influence weights by fusing subjective and objective factors, and implements an adaptive feedback mechanism with tailored adjustment strategies. Using TripAdvisor hotel selection as a case study, the method’s practical feasibility is demonstrated. Simulation experiments show that preference adjustment cost is reduced by over 9.9%, confidence adjustment cost decreases by 4.07% on average, and total cost exhibits minimal fluctuation across parameter variations, fully validating the method’s superior efficiency, convergence speed, stability, and reliability in real-world GDM scenarios.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

An Adaptive Consensus Reaching Process Based on Online Reviews and Sentiment Analysis for Group Decision-Making

  • 期刊论文

  • 发表日期：

    2026年1月3日

查看全文
  • Huiyan Yang,
  • Yanyan Wang,
  • Junfeng Chu,
  • Yingming Wang

摘要

With the development of the Internet, online reviews have become an indispensable reference in decision-making processes. As a prevalent social behavior, group decision-making (GDM) is widely applied across various domains. Integrating valuable information from online reviews with GDM not only bridges real-world applications through authentic data but also significantly enhances decision accuracy and reliability. However, members’ preferences in GDM are fuzzy and conflicting, making consensus achievement critical for opinion coordination. This paper proposes an online review-driven group consensus decision-making method based on sentiment analysis and an adaptive feedback model. The method transforms online reviews into attribute-level sentiment scores, uses a novel Precise-Interval Fuzzy Preference Relation (PIFPR) structure to objectively extract endo-confidence, determines influence weights by fusing subjective and objective factors, and implements an adaptive feedback mechanism with tailored adjustment strategies. Using TripAdvisor hotel selection as a case study, the method’s practical feasibility is demonstrated. Simulation experiments show that preference adjustment cost is reduced by over 9.9%, confidence adjustment cost decreases by 4.07% on average, and total cost exhibits minimal fluctuation across parameter variations, fully validating the method’s superior efficiency, convergence speed, stability, and reliability in real-world GDM scenarios.