图书情报工作

图书情报工作 >

2017 , Vol. 61 >Issue 22: 13 - 19

DOI: https://doi.org/10.13266/j.issn.0252-3116.2017.22.002

专题：商业数据分析与挖掘

商品属性的情感表达与商品销售热度的相关性研究

  • 阮光册 ,
  • 周健超
展开
  • 1. 华东师范大学信息管理系 上海 200241;
    2. 天睿信科技术系统有限公司 上海 201109
阮光册(ORCID:0000-0001-8685-5234),副教授,博士,硕士生导师,E-mail:rgc1976@126.com;周健超(ORCID:0000-0001-5207-3023),业务应用顾问,硕士。

收稿日期: 2017-05-01

  修回日期: 2017-08-17

  网络出版日期: 2017-11-20

收起

Research on the Correlation Between Users' Sentiment Expression and Commodity Sales Ranking

  • Ruan Guangce ,
  • Zhou Jianchao
Expand
  • 1. Information Management Department, East China Normal University, Shanghai 200241;
    2. Teradata Corporation, Shanghai 201109

Received date: 2017-05-01

  Revised date: 2017-08-17

  Online published: 2017-11-20

Fold

摘要

[目的/意义]在线评论蕴含评论者对商品的情感态度，成为潜在消费者购物决策的参考。分析用户对商品属性的情感表达与商品销售热度之间的关系，对用户和商家具有重要的实践和理论意义。[方法/过程]采用LDA主题模型抽取商品属性特征，并对这些属性进行情感极性分析，然后用多元线性回归方程探求商品属性的情感表达对在线商品销量排名之间的关联关系。[结果/结论]研究表明：反映商品"质"的特征属性更受用户的关注，其情感极性与商品的销量排名之间存在较高的正相关性。

关键词： 在线评论; 情感分析; 主题模型; 销售热度; 多元回归

本文引用格式

阮光册 , 周健超 . 商品属性的情感表达与商品销售热度的相关性研究[J]. 图书情报工作, 2017 , 61(22) : 13 -19 . DOI: 10.13266/j.issn.0252-3116.2017.22.002

Abstract

[Purpose/significance] Online reviews contain commodity emotional attitude of users. Analysis of the relationship between the users'emotional tendency of commodity and the commodity sales has important practical and theoretical significance for users and businesses.[Method/process]This paper uses the LDA model to extract the theme features vocabulary of commodity. Then, it analyzes the vocabulary sentiment. And last, it searches the relationship between the sentiment value of commodity characteristics and the online sales ranking by using Multiple regression model.[Result/conclusion] The results show that the characteristics of the "quality" and the "shopping" experience were more closely watched by users. Andthere is a high correlation between their emotional evaluation and the sales rankings of goods.

Key words： online reviews; sentiment analysis; LDA; sales ranking; multiple regression model

参考文献

[1] SCHLOSSER A E. Can including pros and cons increase the helpfulness and persuasiveness of online reviews? the interactive effects of ratings and arguments[J]. Journal of consumer psychology, 2011, 21(3):226-239.
[2] DUAN W, GU B, WHINSTON AB. Informational cascades and software adoption on the Internet:an empirical investigation[J]. MIS quarterly, 2009, 33(1):23-48.
[3] CHEVALIER J A, MAYZLIN D. The effect of word of mouth on sales:online book reviews[J]. Journal of marketing research, 2006, 43(3):345-354.
[4] 史伟, 王洪伟, 何绍义,等.基于微博情感分析的电影票房预测研究[J].华中师范大学学报(自科版), 2015, 49(1):66-72.
[5] ZHU F, ZHANG X Q. Impact of online consumer reviews on sales:the moderating role of product and consumer characteristics[J]. Journal of marketing, 2010, 74(2):133-148.
[6] 李俊,陈黎,王亚强,等.面向电子商务网站的产品属性提取算法[J].小型微型计算机系统,2013,34(11):2477-2481.
[7] MORAES R, VALIATIJ F, GAVIAO NETO W P. Document level sentiment classification an empirical comparison between SVM and ANN[J]. Expert system with applications, 2013, 40(2):621-633.
[8] BLEI D M, NG A Y, JORDAN M I. Latent dirichlet allocation[J]. The journal of machine learning research, 2003, 3(3):993-1022.
[9] 阮光册.基于LDA的网络评论主题发现研究[J].情报杂志, 2014(3):161-164.
[10] 陈文涛, 张小明, 李舟军.构建微博用户兴趣模型的主题模型的分析[J].计算机科学, 2013, 40(4):127-130.
Options
文章导航

/

〈 〉