基于在线评论的用户需求识别及共现分析——以新能源汽车为例
User Demand Identification and Co-Occurrence Analysis Based on Online Comments—Taking New Energy Vehicles as an Example
摘要: 为了从非结构化的新能源汽车用户在线评论中获取用户需求和偏好，本文基于RoBerta进行词嵌入，利用文本切分策略将多产品属性评论文本切分，并利用CNN-LSTM模型实现评论文本分类，再通过PLSA主题模型获取用户需求主题并结合关键词进行需求分析；最后通过网络分析方法揭示需求主题间的关联关系。结果显示，基于语义相似性和切分策略的文本分类方法在分类任务中表现较好，研究结果能够为企业改进产品设计、优化用户体验和制定营销策略提供一定参考。
Abstract: In order to extract user demand and preferences from unstructured online reviews of new energy vehicles, this paper employs the RoBerta word embedding model, utilizes text segmentation strategies to split multi-product attribute review texts, and implements review text classification with the CNN-LSTM model. Then, it obtains user demand themes through the PLSA topic model and conducts demand analysis by combining keywords. Finally, the association between demand themes is revealed through network analysis methods. The results indicate that the text classification method based on semantic similarity and segmentation strategies performs well in classification tasks. The research findings can provide references for enterprises to improve product design, optimize user experience, and develop marketing strategies.
文章引用：王国亚. 基于在线评论的用户需求识别及共现分析——以新能源汽车为例[J]. 电子商务评论, 2025, 14(3): 754-766. https://doi.org/10.12677/ecl.2025.143765

参考文献

[1] Fang, B., Ye, Q., Kucukusta, D. and Law, R. (2016) Analysis of the Perceived Value of Online Tourism Reviews: Influence of Readability and Reviewer Characteristics. Tourism Management, 52, 498-506. [Google Scholar] [CrossRef] 
[2] Farhadloo, M., Patterson, R.A. and Rolland, E. (2016) Modeling Customer Satisfaction from Unstructured Data Using a Bayesian Approach. Decision Support Systems, 90, 1-11. [Google Scholar] [CrossRef] 
[3] 朱丽叶, 袁登华, 张静宜. 在线用户评论质量与评论者等级对消费者购买意愿的影响——产品卷入度的调节作用[J]. 管理评论, 2017, 29(2): 87-96.
[4] Wang, Q., Zhang, W., Li, J., Mai, F. and Ma, Z. (2022) Effect of Online Review Sentiment on Product Sales: The Moderating Role of Review Credibility Perception. Computers in Human Behavior, 133, Article ID: 107272. [Google Scholar] [CrossRef] 
[5] Chang, Y., Ku, C. and Chen, C. (2019) Social Media Analytics: Extracting and Visualizing Hilton Hotel Ratings and Reviews from Tripadvisor. International Journal of Information Management, 48, 263-279. [Google Scholar] [CrossRef] 
[6] 毕达天, 楚启环, 曹冉. 基于文本挖掘的消费者差评意愿的影响因素研究[J]. 情报理论与实践, 2020, 43(10): 137-143.
[7] Lee, M., Jeong, M. and Lee, J. (2017) Roles of Negative Emotions in Customers’ Perceived Helpfulness of Hotel Reviews on a User-Generated Review Website: A Text Mining Approach. International Journal of Contemporary Hospitality Management, 29, 762-783. [Google Scholar] [CrossRef] 
[8] 赵宇晴, 阮平南, 刘晓燕, 单晓红. 基于在线评论的用户满意度评价研究[J]. 管理评论, 2020, 32(3): 179-189.
[9] Guo, Y., Barnes, S.J. and Jia, Q. (2017) Mining Meaning from Online Ratings and Reviews: Tourist Satisfaction Analysis Using Latent Dirichlet Allocation. Tourism Management, 59, 467-483. [Google Scholar] [CrossRef] 
[10] Dong, Y., Fu, Y., Wang, L., Chen, Y., Dong, Y. and Li, J. (2020) A Sentiment Analysis Method of Capsule Network Based on BiLSTM. IEEE Access, 8, 37014-37020. [Google Scholar] [CrossRef] 
[11] Hong, H., Xu, D., Wang, G.A. and Fan, W. (2017) Understanding the Determinants of Online Review Helpfulness: A Meta-Analytic Investigation. Decision Support Systems, 102, 1-11. [Google Scholar] [CrossRef] 
[12] 郭宇靖, 吉宁. 新能源汽车“由大到强”还要迈过几道坎? [N]. 经济参考报, 2024-04-09(004).
[13] 贾宇婷, 吴丹. 公共数字文化移动服务平台用户隐性需求和显性需求识别[J]. 图书馆论坛, 2024, 44(4): 93-103.
[14] 沙勇忠, 苏有丽. 基于社会诉求大数据的公共服务需求管理模型研究[J]. 图书与情报, 2023(6): 75-85.
[15] 于志刚, 成思源, 杨雪荣, 谢通. 融合可拓学与在线评论挖掘的产品改进需求识别研究[J]. 智能系统学报, 2023, 18(5): 1047-1059.
[16] 王松, 王卫霞. 互联网开放式创新社区用户画像构建及用户创新需求识别[J]. 科技管理研究, 2023, 43(7): 158-170.
[17] 石海林, 许明金, 李维思, 周海球, 魏巍, 邬亭玉. 基于AHP-QFD的产业竞争情报需求识别方法研究[J]. 情报杂志, 2022, 41(11): 55-61.
[18] 张东鑫, 张敏. 图情领域LDA主题模型应用研究进展述评[J]. 图书情报知识, 2022, 39(6): 143-157.
[19] Jia, S. (2020) Motivation and Satisfaction of Chinese and U.S. Tourists in Restaurants: A Cross-Cultural Text Mining of Online Reviews. Tourism Management, 78, Article ID: 104071. [Google Scholar] [CrossRef] 
[20] 孙宝生, 敖长林, 王菁霞, 赵明阳. 基于网络文本挖掘的生态旅游满意度评价研究[J]. 运筹与管理, 2022, 31(12): 165-172.
[21] Ding, K., Choo, W.C., Ng, K.Y. and Zhang, Q. (2023) Exploring Changes in Guest Preferences for Airbnb Accommodation with Different Levels of Sharing and Prices: Using Structural Topic Model. Frontiers in Psychology, 14, Article ID: 1120845. [Google Scholar] [CrossRef] [PubMed]
[22] 王克勤, 高智姣, 乔亚楠, 李靖, 同淑荣. 在线评论中的用户需求识别及其演化趋势挖掘[J]. 机械科学与技术, 2023, 42(7): 1070-1080.
[23] 刘鹏, 闫煜析, 冯立杰, 王金凤. 用户需求导向下基于三级技术功效矩阵的产品创新机会识别[J]. 情报理论与实践, 2023, 46(8): 138-146.
[24] Guo, Y., Wang, F., Xing, C. and Lu, X. (2022) Mining Multi-Brand Characteristics from Online Reviews for Competitive Analysis: A Brand Joint Model Using Latent Dirichlet Allocation. Electronic Commerce Research and Applications, 53, Article ID: 101141. [Google Scholar] [CrossRef] 
[25] 蔡永明, 长青. 共词网络LDA模型的中文短文本主题分析[J]. 情报学报, 2018, 37(3): 305-317.
[26] 赵敬华, 谢婉瑜, 吕锡婷, 等. 基于RF-BERT和UGC的用户需求识别及其发展趋势预测[J]. 情报科学, 2024, 42(1): 132-142.
[27] 李贺, 谷莹, 刘嘉宇. 数据驱动下基于语义相似性的产品需求识别研究[J]. 情报理论与实践, 2022, 45(5): 99-106.
[28] Han, Y. and Moghaddam, M. (2020) Eliciting Attribute-Level User Needs from Online Reviews with Deep Language Models and Information Extraction. Journal of Mechanical Design, 143, Article ID: 061403. [Google Scholar] [CrossRef] 
[29] 包清临, 柴华奇, 赵嵩正, 王吉林. 采用机器学习算法的技术机会挖掘模型及应用[J]. 上海交通大学学报, 2020, 54(7): 705-717.
[30] 丁沛, 马铁驹, 马也. 基于在线评论的新能源汽车销量影响因素研究[J]. 系统科学与数学, 2022, 42(10): 2647-2664.

为你推荐