{"id":20082948,"url":"https://github.com/carrychang/customer_satisfaction_analysis","last_synced_at":"2025-04-08T08:16:45.310Z","repository":{"id":37663823,"uuid":"162680457","full_name":"CarryChang/Customer_Satisfaction_Analysis","owner":"CarryChang","description":"基于在线民宿 UGC 数据的意见挖掘项目，包含数据挖掘和NLP 相关的处理，负责数据采集、主题抽取、情感分析等任务。目的是克服用户打分和评论不一致，实时对在线民宿的满意度评测，包含在线评论采集和情感可视化分析。搭建了百度地图POI查询入口，可以进行自动化的批量查询 POI 信息的功能；构建了基于在线民宿语料的 LDA 自动主题聚类模型，利用主题中心词能找出对应的主题属性字典；以用户打分作为标注，然后 litNlp 自带的字符级 TextCNN 进行情感分析，将情感分类概率分布作为情感趋势，最后通过 POI 热力图的方式对不同地域的民宿满意度进行展示。软件版本请见链接。","archived":false,"fork":false,"pushed_at":"2024-10-30T13:25:47.000Z","size":121234,"stargazers_count":424,"open_issues_count":0,"forks_count":127,"subscribers_count":11,"default_branch":"master","last_synced_at":"2025-04-01T05:38:16.026Z","etag":null,"topics":["customer-satisfaction-analysis","litnlp","nlp-machine-learning","sentiment-analysis"],"latest_commit_sha":null,"homepage":"https://github.com/CarryChang/Real_Time_DataMining_Software","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/CarryChang.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2018-12-21T07:20:24.000Z","updated_at":"2025-03-30T14:21:47.000Z","dependencies_parsed_at":"2024-11-13T15:49:09.646Z","dependency_job_id":"0c92fac0-baf9-4f61-b1bb-04d9db559f5f","html_url":"https://github.com/CarryChang/Customer_Satisfaction_Analysis","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CarryChang%2FCustomer_Satisfaction_Analysis","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CarryChang%2FCustomer_Satisfaction_Analysis/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CarryChang%2FCustomer_Satisfaction_Analysis/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CarryChang%2FCustomer_Satisfaction_Analysis/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/CarryChang","download_url":"https://codeload.github.com/CarryChang/Customer_Satisfaction_Analysis/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247801175,"owners_count":20998339,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["customer-satisfaction-analysis","litnlp","nlp-machine-learning","sentiment-analysis"],"created_at":"2024-11-13T15:45:19.532Z","updated_at":"2025-04-08T08:16:45.262Z","avatar_url":"https://github.com/CarryChang.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"[![996.icu](https://img.shields.io/badge/link-996.icu-red.svg)](https://996.icu)\n#### Customer_satisfaction_Analysis \n\n[![Stargazers over time](https://starchart.cc/CarryChang/Customer_Satisfaction_Analysis.svg)](https://starchart.cc/CarryChang/Customer_Satisfaction_Analysis)\n\n##### 结果整合\n\u003cdiv align=center\u003e\u003cimg  src=\"https://github.com/CarryChang/Customer_Satisfaction_Analysis/blob/master/pic/情感分析图.png\"\u003e\u003c/div\u003e\n\n##### Demo 演示\n  - [视频演示demo](https://github.com/CarryChang/C-CNN-for-Chinese-Sentiment-Analysis/blob/master/video/demo.mp4)\n  - [详细步骤](https://www.lanqiao.cn/courses/2628)\n\n##### 基于用户 UGC 的在线民宿满意度挖掘，负责数据采集、主题抽取、情感分析等任务。开发的目的是克服用户打分和评论不一致，实现了在线评论采集和用户满意度分析。\n\n\u003cdiv align=center\u003e\u003cimg  src=\"https://github.com/CarryChang/Customer_Satisfaction_Analysis/blob/master/pic/不一致.png\"\u003e\u003c/div\u003e\n\n#####  主要功能包括在线原始评论采集、主题聚类、评论情感分析与结果可视化展示等四个模块，如下所示。\n\n\u003cdiv align=center\u003e\u003cimg  src=\"https://github.com/CarryChang/Customer_Satisfaction_Analysis/blob/master/pic/流程.png\"\u003e\u003c/div\u003e\n\n\n\u003e1.   提取后的民宿地址和在线评论等信息如下。\n\n\u003cdiv align=center\u003e\u003cimg  src=\"https://github.com/CarryChang/Customer_Satisfaction_Analysis/blob/master/pic/数据库.png\"\u003e\u003c/div\u003e\n\n\u003e2.   搭建了百度地图 POI 查询入口，可以进行自动化的批量查询地理信息。\n\n\u003cdiv align=center\u003e\u003cimg  src=\"https://github.com/CarryChang/Customer_Satisfaction_Analysis/blob/master/pic/地址.png\"\u003e\u003c/div\u003e\n\n\u003e 3.   通过高频词可视化展示，归纳出评论主题。\n\n\u003cdiv align=center\u003e\u003cimg  src=\"https://github.com/CarryChang/Customer_Satisfaction_Analysis/blob/master/pic/gaopin1.png\"\u003e\u003c/div\u003e\n\u003cdiv align=center\u003e\u003cimg  src=\"https://github.com/CarryChang/Customer_Satisfaction_Analysis/blob/master/pic/高频2.png\"\u003e\u003c/div\u003e\n\n\u003e 4.   构建了基于在线民宿语料的 LDA 自动化主题聚类模型，利用主题中心词能找出对应的主题属性字典，并使用用户打分作为标注，然后通过多种分类模型，选用最优模型对提出的评价主体 进行情感分析，针对主题属性表进行主题提取后的文本进行情感分析，分别得出当前主题对应的情感趋势，横坐标为所有关于主题为“环境”的情感得分，纵坐标为对应的情感的条数，可以起到纵观当前“环境”主题下的情感趋势，趋势往右代表当前主题评价较好，总共有{“交通”，“价格”，“体验”，“服务”，“特色”，“环境”，“设施”，“餐饮”}的主题，选取“环境”主题进行可视化之后的结果如下图所示。\n\n\u003cdiv align=center\u003e\u003cimg  src=\"https://github.com/CarryChang/Customer_Satisfaction_Analysis/blob/master/pic/lda_topic_select.png\"\u003e\u003c/div\u003e\n\u003cdiv align=center\u003e\u003cimg  src=\"https://github.com/CarryChang/Customer_Satisfaction_Analysis/blob/master/pic/lda_topic_select1.png\"\u003e\u003c/div\u003e\n\u003cdiv align=center\u003e\u003cimg  src=\"https://github.com/CarryChang/Customer_Satisfaction_Analysis/blob/master/pic/主题.png\"\u003e\u003c/div\u003e\n\n\u003e 5.   通过POI热力图的方式对在线民宿满意度进行展示。\n\n\u003cdiv align=center\u003e\u003cimg  src=\"https://github.com/CarryChang/Customer_Satisfaction_Analysis/blob/master/pic/poi可视化.png\"\u003e\u003c/div\u003e\n\u003cdiv align=center\u003e\u003cimg  src=\"https://github.com/CarryChang/Customer_Satisfaction_Analysis/blob/master/pic/poi打分.png\"\u003e\u003c/div\u003e\n\n\u003e 6.   代码结构如下。\n\n\u003cdiv align=center\u003e\u003cimg  src=\"https://github.com/CarryChang/Customer_Satisfaction_Analysis/blob/master/pic/结构1.png\"\u003e\u003c/div\u003e\n\n##### 专利信息\n\u003cdiv align=center\u003e\u003cimg  src=\"https://github.com/CarryChang/Customer_Satisfaction_Analysis/blob/master/pic/ip.png\"\u003e\u003c/div\u003e\n\n\n#####  新版本特性\n\u003e 1. 使用 litNLP 深度情感推理\n\u003e 2. 增加多进程提高多个 topic 下的文本匹配速度\n\u003e 3. Project_Main.py 直接完成细粒度情感极性可视化操作\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcarrychang%2Fcustomer_satisfaction_analysis","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fcarrychang%2Fcustomer_satisfaction_analysis","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcarrychang%2Fcustomer_satisfaction_analysis/lists"}