基于模糊综合评价的美团评论数据情感分析

Emotional Analysis of Meituan Review Data Based on Fuzzy Comprehensive Evaluation

美团平台上店铺的评分是一个综合性评分,并不能从多个角度说明店铺情况,客户根据综合评分很难选择到符合自己需求的店铺。现有评价模型在商品属性选择和权重上依靠有经验的管理者给出,存在很大的主观性。针对这些问题,提出了基于模糊综合评价的情感分析模型。该模型首先采用关键词提取与模糊矩阵相结合方法,对评论的语料进行关键词提取,然后根据关键词权重设置模糊矩阵,最后将评论情感分析结果放在模糊矩阵中,构建出基于模糊矩阵的综合情感评价模型。在美团评论数据集上进行实验,结果是综合评价分与美团平台的综合性评分只相差0.02%,说明该模型结果非常准确。模型给出了店铺除综合评分以外的其它关键词得分,全面分析了店铺的口味、环境、价格等因素评分,为顾客选择提供了多角度指导。所得出的评分也给商家提供了很好的指导意见,以帮助商家调整经营模式和策略。

The ratings of the stores on the Meituan platform are comprehensive,and it is impossible to explain the situation of the stores from multiple angles.It is difficult for customers to select a store that meets their needs according to the comprehensive score.The commodity attributes and weights of the evaluation model are given by experienced managing statt.This evaluation model is very subjective.Aiming at these problems,this paper proposes a sentiment analysis model based on fuzzy comprehensive evaluation.First,the model adopts the method of combining keyword extraction and fuzzy matrix,extracts the keywords from the corpus of comments,and then sets the fuzzy matrix according to the weight of the keywords.Finally,the results of the comment sentiment analysis are placed in the fuzzy matrix to construct fuzzy comprehensive emotion evaluation model based on fuzzy matrix.The comprehensive evaluation results obtained by the experiment on the Meituan review dataset differed only 0.02%from the comprehensive score of the Meituan platform,indicating that the results obtained by the model are extremely accurate.The model gives the scores of other keywords in addition to the comprehensive scores of the stores,comprehensively analyzes the scores of the stores’taste,environment,price and other factors,providing customers with a multi-angle selection guide;the resulting scores also provide good guidance to merchants to help them adjust their business models and strategies.