Please wait a minute...
Advanced Search
数据分析与知识发现  2018, Vol. 2 Issue (11): 19-27     https://doi.org/10.11925/infotech.2096-3467.2018.0835
  专题 本期目录 | 过刊浏览 | 高级检索 |
基于在线评论情感分析的海淘APP用户满意度研究*
赵杨(), 李齐齐, 陈雨涵, 曹文航
武汉大学信息管理学院 武汉 430072
Examining Consumer Reviews of Overseas Shopping APP with Sentiment Analysis
Zhao Yang(), Li Qiqi, Chen Yuhan, Cao Wenhang
School of Information Management, Wuhan University, Wuhan 430072, China
全文: PDF (1546 KB)   HTML ( 4
输出: BibTeX | EndNote (RIS)      
摘要 

【目的】对用户在线评论文本进行情感分析, 评价用户满意度, 为海淘APP运营商提供对策建议。【方法】基于APP Store上的海淘APP用户在线评论数据, 采用Canopy+K-means方法对海淘APP属性特征进行聚类, 确定用户满意度评价维度, 进而应用CNN-SVM情感分析模型得到各维度的用户满意度评分。【结果】研究结果表明: 影响海淘APP用户满意度最重要的因素是商品, 其次分别是价格、交互、服务、物流; 垂直类海淘APP的用户满意度整体高于境外买手类和综合类海淘APP; 海淘APP在物流和服务方面的用户满意度整体较低。 【局限】样本选择较为有限。【结论】采用情感分析方法对海淘APP用户在线评论进行文本分析, 为APP用户满意度评价提供有效方法。

服务
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章
赵杨
李齐齐
陈雨涵
曹文航
关键词 情感分析海淘APP用户满意度CNN-SVM    
Abstract

[Objective] This paper analyzes the sentiment of online reviews, and then evaluates the consumer’s satisfaction with overseas shopping APP, aiming to improve its performance. [Methods] First, we collected reviews of these APPs from the APP Store. Then, we clustered the APPs’ attributes with Canopy and K-means algorithms, which defines the evaluation dimensions of consumer’s satisfaction. Finally, we computed scores of the consumer’s satisfaction with the CNN-SVM sentiment analysis model. [Results] The most important factor affecting the consumer’s satisfaction with overseas shopping APP was commodities, followed by price, interaction, service, and logistics. The consumer’s satisfaction level with the vertical overseas shopping APP was higher than that of the overseas buyer APP and the comprehensive overseas shopping APP. The consumer’s satisfaction level is relatively low with logistics and services. [Limitations] More overseas shopping APP should be included in future research. [Conclusions] The sentiment analysis method is an effective way to analyze consumer’s satisfaction with online reviews of overseas shopping APP.

Key wordsSentiment Analysis    Overseas Shopping APP    Consumer Satisfaction    CNN-SVM
收稿日期: 2018-07-26      出版日期: 2018-12-11
ZTFLH:  TP391 G35  
基金资助:*本文系湖北省自然科学基金项目“基于社交媒体用户兴趣特征迁移学习的个性化推荐方法研究”(项目编号: 2018CFB758)的研究成果之一
引用本文:   
赵杨, 李齐齐, 陈雨涵, 曹文航. 基于在线评论情感分析的海淘APP用户满意度研究*[J]. 数据分析与知识发现, 2018, 2(11): 19-27.
Zhao Yang,Li Qiqi,Chen Yuhan,Cao Wenhang. Examining Consumer Reviews of Overseas Shopping APP with Sentiment Analysis. Data Analysis and Knowledge Discovery, 2018, 2(11): 19-27.
链接本文:  
http://manu44.magtech.com.cn/Jwk_infotech_wk3/CN/10.11925/infotech.2096-3467.2018.0835      或      http://manu44.magtech.com.cn/Jwk_infotech_wk3/CN/Y2018/V2/I11/19
  研究框架
  CNN-SVM模型结构
发表时间 用户ID 星级评分 评论标题 评论内容
2017-11-04 14:55:42 豐收F1 5 值得信赖 在几个知名网站都经常购买各种商品, 第一在网易考拉购买, 物流给力, 价格实惠。
2017-11-04 14:50:58 没有草莓牛奶就不开心的人 1 讨厌强制更新 就这样, 商品也不齐全。
2017-05-12 16:59:56 crjjzz 4 不错的网购APP 目前在这网购APP买的东西都蛮好用的, 都验过正品, 价格实惠在那里。
2017-10-25 14:41:15 无尽土豆泥 2 我选择淘宝 ……不仅没便宜, 甚至还贵了很多, 拿ns举例, 美亚和日亚便宜的才卖2000, 淘宝2600, 这上面居然3300……骗谁啊!
  海淘APP用户在线评论数据格式示例
  聚类效果图
  海淘APP特征聚类结果
  海淘APP属性权重
算法 准确率(Precision) 召回率
(Recall)
F1值
(F1 Score)
Decision Tree 79.18 79.91 79.85
SVM 91.32 87.31 89.22
CNN 94.28 91.59 92.87
CNN-SVM 97.79 96.21 96.97
  情感分类结果比较(%)
APP类别 名称 商品 价格 物流 交互 服务
境外
买手类
HIGO 74.52 86.25 78.35 57.89 61.67
洋码头 63.06 82.26 45.71 87.74 33.96
综合类 网易考拉 83.56 84.91 77.78 74.19 51.43
小红书 70.83 75.00 30.77 64.86 37.04
亚马逊 87.21 82.11 60.64 54.39 35.29
波罗蜜 86.96 84.34 49.33 66.20 30.95
折疯了 86.13 86.63 85.00 85.85 54.55
垂直类 宝贝格子 83.72 96.55 93.94 79.17 90.91
蜜芽 77.88 83.33 42.86 46.30 39.66
环球捕手 69.84 85.50 40.91 73.68 34.21
  海淘APP各属性维度的用户满意度评分
[1] 周涛, 方文侃. 移动社交APP位置分享服务持续使用研究[J]. 杭州电子科技大学学报: 社会科学版, 2016, 12(3): 1-7.
[1] (Zhou Tao, Fang Wenkan.On Sustained Usage of Mobile Social APP Location Sharing Service[J]. Journal of Hangzhou Dianzi University: Social Sciences, 2016, 12(3): 1-7.)
[2] 张一帆. 我国旅游APP用户满意度的实证研究[D]. 海口: 海南大学, 2015.
[2] (Zhang Yifan.Empirical Study of Customer Satisfaction About Tourism APP in China[D]. Haikou: Hainan University, 2015.)
[3] Dwikesumasari P R, Ervianty R M.Customer Loyalty Analysis of Online Travel Agency APP with Customer Satisfaction as a Mediation Variable[C]//Proceedings of the 2017 International Conference on Organizational Innovation. 2017.
[4] 明均仁, 张俊. 高校移动图书馆APP用户满意度影响因素[J]. 图书馆论坛, 2018, 38(4): 84-94.
[4] (Ming Junren, Zhang Jun.Research on the Factors Influencing User Satisfaction of University Mobile Library APP[J]. Library Tribune, 2018, 38(4): 84-94.)
[5] 李武, 赵星. 大学生社会化阅读APP持续使用意愿及发生机理研究[J]. 中国图书馆学报, 2016, 42(1): 52-65.
doi: 10.13530/j.cnki.jlis.160005
[5] (Li Wu, Zhao Xing.Understanding the Continuance Intention of Social Reading Apps by College Students[J]. Journal of Library Science in China, 2016, 42(1): 52-65.)
doi: 10.13530/j.cnki.jlis.160005
[6] Song B, Lee C, Park Y.Identifying Critical Factors for Customer Satisfaction in Mobile Application Service: A Semantic Text Mining and Bayesian Network Approach[J]. International Proceedings of Economics Development & Research, 2011, 8: 33-37.
[7] Pang B, Lee L, Vaithyanathan S.Thumbs Up? Sentiment Classification Using Machine Learning Techniques[C]// Proceedings of the 2002 ACL Conference on Empirical Methods in Natural Language Processing. 2002: 79-86.
[8] 史伟, 王洪伟, 何绍义. 基于语义的中文在线评论情感分析[J]. 情报学报, 2013, 32(8): 860-867.
doi: 10.3772/j.issn.1000-0135.2013.08.009
[8] (Shi Wei, Wang Hongwei, He Shaoyi.Sentiment Analysis of Chinese Online Reviews Based on Semantics[J]. Journal of the China Society for Scientific and Technical Information, 2013, 32(8): 860-867.)
doi: 10.3772/j.issn.1000-0135.2013.08.009
[9] 王洪伟, 宋媛, 杜战其, 等. 基于在线评论情感分析的快递服务质量评价[J]. 北京工业大学学报, 2017, 43(3): 402-412.
doi: 10.11936/bjutxb2016010063
[9] (Wang Hongwei, Song Yuan, Du Zhanqi, et al.Evaluation of Service Quality for Express Industry Through Sentiment Analysis of Online Reviews[J]. Journal of Beijing University of Technology, 2017, 43(3): 402-412.)
doi: 10.11936/bjutxb2016010063
[10] Yih W, He X, Meek X.Semantic Parsing for Single-Relation Question Answering[C]// Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics. 2014, 2: 643-648.
[11] Collobert R, Weston J, Bottou L, et al.Natural Language Processing (Almost) from Scratch[J]. Journal of Machine Learning Research, 2011, 12: 2493-2537.
[12] Kim Y.Convolutional Neural Networks for Sentence Classification[OL]. arXiv Preprint. arXiv: 1408.5882.
doi: 10.1109/CLEI.2017.8226381
[13] Mohamed A, Dahl G, Hinton G.Deep Belief Networks for Phone Recognition[C]// Proceedings of the 2009 NIPS Workshop on Deep Learning for Speech Recognition and Related Applications. 2009.
[14] Huang F J, Lecun Y.Large-scale Learning with SVM and Convolutional for Generic Object Categorization[C]// Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 2006: 284-291.
[15] Le Q V, Ngiam J, Chen Z, et al.Tiled Convolutional Neural Networks[C]// Proceedings of the 24th Annual Conference on Neural Information Processing Systems. 2010: 1279-1287.
[16] Coates A, Ng A Y, Lee H.An Analysis of Single-Layer Networks in Unsupervised Feature Learning[C]// Proceedings of the 14th International Conference on Artificial Intelligence and Statistics. 2011.
[17] Rozi M F, Mukhlash I, Soetrisno, et al. Opinion Mining on Book Review Using CNN-L2-SVM Algorithm[C]// Proceedings of the 2018 International Conference on Mathematics: Pure, Applied and Computation. 2018. DOI :10.1088/1742-6596/974/1/012004.
[18] Socher R, Pennington J, Huang E H.Semi-Supervised Recursive Autoencoders for Predicting Sentiment Distributions[C]// Proceedings of the 2011 Conference on Empirical Methods in Natural Language Processing. 2011: 151-161.
[19] Ren J, Yeoh W, Ee M S, et al.Online Consumer Reviews and Sales: Examining the Chicken-Egg Relationships[J]. Journal of the Association for Information Science & Technology, 2017, 69(3): 449-460.
doi: 10.1002/asi.23967
[20] Che W X, Li Z H, Liu T.LTP: A Chinese Language Technology Platform[C]// Proceedings of the 23rd International Conference on Computational Linguistics. 2010: 13-16.
[21] 赵志滨, 刘欢, 姚兰, 等. 中文产品评论的维度挖掘及情感分析技术研究[J]. 计算机科学与探索, 2018, 12(3): 341-349.
[21] (Zhao Zhibin, Liu Huan, Yao Lan, et al.Research on Dimensional Mining and Sentiment Analysis for Chinese Product Comments[J]. Journal of Frontiers of Computer Science and Technology, 2018, 12(3): 341-349.)
[1] 徐红霞,于倩倩,钱力. 基于主题模型和情感分析的话题交互数据观点对抗性分析 *[J]. 数据分析与知识发现, 2020, 4(7): 110-117.
[2] 姜霖,张麒麟. 基于引文细粒度情感量化的学术评价研究*[J]. 数据分析与知识发现, 2020, 4(6): 129-138.
[3] 石磊,王毅,成颖,魏瑞斌. 自然语言处理中的注意力机制研究综述*[J]. 数据分析与知识发现, 2020, 4(5): 1-14.
[4] 李铁军,颜端武,杨雄飞. 基于情感加权关联规则的微博推荐研究*[J]. 数据分析与知识发现, 2020, 4(4): 27-33.
[5] 沈卓,李艳. 基于PreLM-FT细粒度情感分析的餐饮业用户评论挖掘[J]. 数据分析与知识发现, 2020, 4(4): 63-71.
[6] 薛福亮,刘丽芳. 一种基于CRF与ATAE-LSTM的细粒度情感分析方法*[J]. 数据分析与知识发现, 2020, 4(2/3): 207-213.
[7] 谭荧,张进,夏立新. 社交媒体情境下的情感分析研究综述[J]. 数据分析与知识发现, 2020, 4(1): 1-11.
[8] 聂卉,何欢. 引入词向量的隐性特征识别研究*[J]. 数据分析与知识发现, 2020, 4(1): 99-110.
[9] 岑咏华,谭志浩,吴承尧. 财经媒介信息对股票市场的影响研究: 基于情感分析的实证 *[J]. 数据分析与知识发现, 2019, 3(9): 98-114.
[10] 卢伟聪,徐健. 基于三分网络的网络用户评论情感分析 *[J]. 数据分析与知识发现, 2019, 3(8): 10-20.
[11] 尤众喜,华薇娜,潘雪莲. 中文分词器对图书评论和情感词典匹配程度的影响 *[J]. 数据分析与知识发现, 2019, 3(7): 23-33.
[12] 蒋翠清,郭轶博,刘尧. 基于中文社交媒体文本的领域情感词典构建方法研究*[J]. 数据分析与知识发现, 2019, 3(2): 98-107.
[13] 余本功,张培行,许庆堂. 基于F-BiGRU情感分析的产品选择方法*[J]. 数据分析与知识发现, 2018, 2(9): 22-30.
[14] 曾子明,杨倩雯. 基于LDA和AdaBoost多特征组合的微博情感分析*[J]. 数据分析与知识发现, 2018, 2(8): 51-59.
[15] 王秀芳,盛姝,路燕. 一种基于话题聚类及情感强度的微博舆情分析模型*[J]. 数据分析与知识发现, 2018, 2(6): 37-47.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
版权所有 © 2015 《数据分析与知识发现》编辑部
地址:北京市海淀区中关村北四环西路33号 邮编:100190
电话/传真:(010)82626611-6626,82624938
E-mail:jishu@mail.las.ac.cn