面向服务改进的生鲜物流评论动机识别研究
Research on Motivation Identification Strategy of Fresh Logistics Review for Service Quality Improvement
摘要: 随着互联网技术的飞速发展和消费者对生鲜产品需求的增长，生鲜电商行业迅速崛起，成为在线购物的重要组成部分。生鲜产品由于其易腐性、保质期短和对运输储存条件的高要求，对物流服务质量提出了更高的挑战。同时，消费者在线评论作为用户生成内容的一种形式，对物流服务质量的改进和发展具有显著影响。本研究针对生鲜电商行业的快速发展和消费者需求，提出了面向服务质量改进的生鲜物流评论动机识别策略。通过改进预训练模型增加多层注意力结构，构建基于RoBERTa-HA模型的识别框架，利用深度学习技术对消费者在线评论中的动机进行提取和识别，为电商平台提供服务质量改进的策略，能够为物流服务提供商提供量化的消费者需求和偏好信息。
Abstract: With the rapid development of internet technology and the increasing consumer demand for fresh products, the fresh food e-commerce industry has emerged as a significant component of online shopping. Due to the perishability, short shelf life, and high requirements for transportation and storage conditions of fresh products, the industry faces elevated challenges in ensuring logistics service quality. Meanwhile, consumer online reviews, as a form of user-generated content, play a pivotal role in improving and advancing logistics service quality. This study addresses the rapid growth of the fresh food e-commerce industry and evolving consumer demands by proposing a motivation identification strategy for fresh logistics reviews aimed at service quality enhancement. By introducing a multi-layer attention mechanism to refine pre-trained models, this study develops a recognition framework based on the RoBERTa-HA model. Leveraging deep learning techniques, it extracts and identifies consumer motivations embedded in online reviews, providing e-commerce platforms with actionable strategies to improve service quality. The proposed approach also offers logistics service providers quantitative insights into consumer needs and preferences.
文章引用：伍星有, 张成. 面向服务改进的生鲜物流评论动机识别研究[J]. 数据挖掘, 2025, 15(1): 94-106. https://doi.org/10.12677/hjdm.2025.151008

参考文献

[1] Perreault, W.D. and Russ, F.A. (1976) Physical Distribution Service in Industrial Purchase Decisions: A Survey of Industrial Purchasing Managers Reveals that Physical Distribution Service Rates Second Only to Product Quality in Influencing Industrial Purchase Decisions. Journal of Marketing, 40, 3-10. [Google Scholar] [CrossRef] 
[2] 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.
[3] 魏如清, 唐方成. 用户生成内容对在线购物的社会影响机制——基于社会化电商的实证分析[J]. 华东经济管理, 2016, 30(4): 124-131.
[4] 张敏, 武晋, 贾慧敏, 等. 消费者动机对食品信息传播的影响因素分析[J]. 中国健康教育, 2021, 3(3): 222-227.
[5] Radford, A., Narasimhan, K., Salimans, T., et al. (2018) Improving Language Understanding by Generative Pre-Training. arXiv: 1801.09872.
[6] Devlin, J., Chang, M.W., Lee, K., et al. (2019) BERT: Pre-Training of Deep Bidirectional Transformers for Language Understanding.
http://arxiv.org/abs/1810.04805
[7] Acheampong, F.A., Wenyu, C. and Nunoo-Mensah, H. (2020) Text-Based Emotion Detection: Advances, Challenges, and Opportunities. Engineering Reports, 2, e12189. [Google Scholar] [CrossRef] 
[8] Acheampong, F.A., Nunoo-Mensah, H. and Wenyu, C. (2020) Comparative Analyses of Bert, Roberta, Distilbert, and Xlnet for Text-Based Emotion Recognition. 2020 17th International Computer Conference on Wavelet Active Media Technology and Information Processing (ICCWAMTIP), Chengdu, 18-20 December 2020, 117-121.
[9] 冯国明, 张晓冬, 刘素辉. 基于CapsNet的中文文本分类研究[J]. 数据分析与知识发现, 2019, 2(12): 68-76.
[10] 杜学美, 张倩, 苏强. 基于服务蓝图的网上零售业感知服务质量[J]. 工业工程, 2013, 16(1): 19-24.
[11] 胡君臣, 杨林锋. 员工情绪表现结构维度及对感知服务质量影响初探[J]. 管理评论, 2012, 24(1): 116-126.

为你推荐