首页|基于动态主题模型的需求弱信号识别——以比亚迪新能源汽车为例

基于动态主题模型的需求弱信号识别——以比亚迪新能源汽车为例

扫码查看
[研究目的]竞争的加剧和创新的要求使得产品研发愈加复杂,企业急需在一个动态变化的市场中摸索前行.因此,如何有效识别需求弱信号成为亟待解决和最具挑战性的难题.[研究方法]从顾客端出发,引入并融合新颖度、出现率、支持率以及点击率等评价指标,借鉴Kim等开发的信号组合图作为信号分类体系,提出一种基于动态主题模型的需求弱信号识别方法.以"汽车之家"网站上比亚迪新能源汽车顾客评论为数据源进行实证分析,从需求弱信号识别数量和识别质量两个维度与关键词分析方法进行对比.[研究结论]结果表明,该研究提出的方法具有有效性和可行性,能够准确地识别出需求弱信号,具有更高的灵敏度.
Weak Demand Signal Identification Based on a Dynamic Topic Model:Taking BYD's New Energy Vehicles as an Example
[Research purpose]The intensification of competition and the demand for innovation have made product research and develop-ment increasingly complex,and enterprises urgently need to explore and move forward in a dynamically changing market.Therefore,how to effectively identify weak demand signals has become an urgent and most challenging problem.[Research method]This study intro-duces and integrates evaluation indicators such as novelty,occurrence rate,support rate,and click-through rate from the customer side,draws on the signal combination diagram developed by Kim and Lee as a signal classification system,and then proposes a method for iden-tifying weak demand signals based on a dynamic topic model.An empirical analysis is carried out using customer reviews of the automo-tive company BYD's new energy vehicles on the website Auto Home as the data source,and the results are compared from two dimensions of the quantity and quality of weak demand identification with the ones obtained by the keyword analysis.[Research conclusion]The re-sults show that the method proposed in this study is effective and feasible and can accurately identify weak demand signals with higher sen-sitivity.

weak demand signalweak demand signal recognitioncomment textsignal combination diagramDTM modelnew energy vehicles

赵动员、唐中君、孙凤霞

展开 >

北京工业大学经济与管理学院北京现代制造业发展研究基地 北京 100124

淮北师范大学经济与管理学院 淮北 235000

需求弱信号 需求弱信号识别 评论文本 信号组合图 DTM模型 新能源汽车

国家自然科学基金面上项目

71672004

2024

情报杂志
陕西省科学技术信息研究所

情报杂志

CSTPCDCSSCICHSSCD北大核心
影响因子:1.502
ISSN:1002-1965
年,卷(期):2024.43(10)