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  

Weak Demand Signal Identification Based on a Dynamic Topic Model:Taking BYD's New Energy Vehicles as an Example

作　　者：赵动员 唐中君[1] 孙凤霞 Zhao Dongyuan;Tang Zhongjun;Sun Fengxia(Beijing Modern Manufacturing Development,School of Economics and Management,Beijing University of Technology,Beijing 100124;School of Economics and Management,Huaibei Normal University,Huaibei 235000)

机构地区：[1]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 [2]淮北师范大学经济与管理学院,淮北235000

出　　处：《情报杂志》2024年第10期81-89,共9页Journal of Intelligence

基　　金：国家自然科学基金面上项目“基于类比推理的短生命周期无形体验品需求预测”(编号:71672004)研究成果。

摘　　要：[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。[Research purpose]The intensification of competition and the demand for innovation have made product research and development 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 introduces 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 identifying weak demand signals based on a dynamic topic model.An empirical analysis is carried out using customer reviews of the automotive 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 results show that the method proposed in this study is effective and feasible and can accurately identify weak demand signals with higher sensitivity.

关 键 词：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 

分 类 号：G359.2[文化科学—情报学]