摘要
葡萄酒商品标题是影响销量的重要因素之一。基于葡萄酒标题进行文本关联规则挖掘,并对商品销量的影响因素进行随机森林模型构建。词频分析表明,“葡萄酒”“红酒”“干红”和“进口”是标题中的核心词,并且高销量葡萄酒中“气泡”“甜酒”“甜型”以及“女士”的出现频数明显增多。文本关联规则分析显示,低销量产品中标题设置混乱,而高销量产品的标题词中“法国”与“波尔多”关联度高。随机森林模型中的14个销量影响因素重要性排序表明,商品价格是消费者考虑的最主要影响因素。本研究旨在为网购葡萄酒的标题设置及销量影响因素提供参考,以辅助商家评估消费者偏好,调整供货与销售策略。
As an important factor affecting the exposure rate,wine product titles have received widespread attention.Text association rules were analyzed based on wine titles in online shopping.Additionally,the random forest model was developed for estimating influencing factors of sales.The differences in high-frequency words were explored through word frequency analysis.Word frequency analysis showed that wine,red wine,dry red and import were key words in the title.The occurrence of sparkling,sweet wine,sweet and female increased significantly in high-volume wines.The text association rule analysis showed that the title of low sales is confused,while the title words of high sales have a correlation between France and Bordeaux.The importance ranking of 14 sales impact factors in the random forest model showed that commodity price was the most important influencing factor considered by consumers.This study could provide a reference for online wine retailers in evaluating consumer preferences and adjusting supply and sales strategies.
作者
孙菀霞
谢均扬
任芮瑄
纠松涛
张才喜
SUN Wanxia;XIE Junyang;REN Ruixuan;JIU Songtao;ZHANG Caixi(School of Agriculture and Biology,Shanghai Jiao Tong University,Shanghai 200240,China;School of Electronic Information and Electrical Engineering,Shanghai Jiao Tong University,Shnaghai 200240,China)
出处
《中外葡萄与葡萄酒》
北大核心
2021年第6期110-114,共5页
Sino-Overseas Grapevine & Wine
基金
国家自然科学基金(32102346)
上海市青年科技英才扬帆计划(21YF1422100)上海交通大学新进青年教师启动计划(21X010500643)。
关键词
葡萄酒
网购
文本挖掘
随机森林
wine
online shopping
text mining
random forest