南京审计大学商学院;
在数字化时代，企业管理者需要通过大数据技术积极倾听消费者对产品和服务的反馈，以不断改进其运营绩效。社交媒体是消费者购物后自由分享和讨论他们对产品和服务感知的重要渠道。对海量消费者不断发出的杂乱文本信息进行分析、总结和提炼，以得到消费者群体的核心表达是一个困难的问题。文章提出了基于大语言模型和社会表征理论进行社交媒体分析的新方法框架，并以新浪微博推文数据源的淘宝退货服务为例，说明该方法框架的具体应用。案例分析发现，退货困难、产品质量、物流配送、包装问题等是消费者反映的核心问题。其中退货困难、产品质量问题往往伴随消费者更负面的情绪。与传统主题分析技术相比，新方法框架可以帮助企业从消费者社交媒体数据中提炼多维度、多层次的社会表征，为了解消费者对企业产品和服务的感知提供更准确、更深入、更全面的洞察。
| 1,004 | 0 | 43 |
| 下载次数 | 被引频次 | 阅读次数 |
[1]鲍彤,章成志. ChatGPT中文信息抽取能力测评———以三种典型的抽取任务为例[J].数据分析与知识发现, 2023,(9):1-11.
[2]蔡礼彬,万方亮,李平.从“网红”到“长红”：旅游公共服务吸引力与供给次序———基于抖音“淄博烧烤”话题的用户评论分析[J].消费经济, 2024,(2):26-36.
[3]李旭,王刊良.社交媒体用户营销信息分享行为———受评忧虑与系统反馈视角[J].管理科学, 2020,(4):82-97.
[4]林宝民,涂红伟,夏俊俊.在线旅游消费者困惑对信任的影响——基于情绪评价理论视角[J].消费经济, 2019,(2):89-96.
[5]孙焕良,王思懿,刘俊岭,许景科.社交媒体数据中水灾事件求助信息提取模型[J/OL].计算机应用. https://link.cnki.net/urlid/51.1307.TP.20231114.2323.022, 2023-11-15/2024-07-03.
[6]王炳成,李丰娟,崔巍.短视频生活场域还原对消费者购买意愿的影响[J].消费经济, 2022,(4):74-83.
[7]王志刚,邱长波.基于主题的政务微博评论用户画像研究[J].情报杂志, 2022,(3):159-165.
[8]余红,马旭.社会表征理论视域下网络公共事件的共识达成机制研究———以“电梯劝烟猝死案”的社交媒体讨论为考察对象[J].情报杂志, 2019,(8):136-144, 150.
[9]张信东,原东良.基于微博的投资者情绪对股票市场影响研究[J].情报杂志, 2017,(8):81-87.
[10]张颖怡,章成志,周毅,陈必坤.基于ChatGPT的多视角学术论文实体识别：性能测评与可用性研究[J].数据分析与知识发现, 2023,(9):12-24.
[11]赵蜜.社会表征论:发展脉络及其启示[J].社会学研究, 2017,(4):218-241, 246.
[12]赵阳,陈国强,冯学钢.从口碑到网络口碑：脉络、框架与展望[J].消费经济, 2022,(4):84-96.
[13]郑文镇,唐锡晋.大语言模型增强下的社媒平台热榜主题分析[J].系统科学与数学, 2024,(6):1630-1648.
[14]衷玉红,李世森,汪永胜.企业品牌定位与社会表征关系研究[J].企业经济, 2019,(10):116-120.
[15]朱逸,朱瑞庭,郭薇.社交媒体广告：感知价值、消费者共创与购买意愿探究———基于“SEM+机器学习”的分析策略[J].管理现代化,2023,(4):112-120.
[16] Abric, J. C. Jeux, Conflits et Représentations Sociales[D]. Aix-en-Provence, France:Universitéde Provence, 1976.
[17] Abric, J. C. L’Approche Structurale des Représentations Sociales:Développements Récents[J]. Psychologie et Société, 2001, 4(2):81-104.
[18] Abric, J. C. Prácticas Sociales y Representaciones[M]. México:Ediciones Coyoacán, 1994.
[19] Achiam, J., Adler, S., and Agarwal, S., et al. Gpt-4 Technical Report[J]. Ar Xiv Preprint Ar Xiv:2303. 08774, 2023.
[20] Bastian, M., Heymann, S., and Jacomy, M. Gephi:An Open Source Software for Exploring and Manipulating Networks[C]. San Jose, California,USA:Proceedings of the International AAAI Conference on Web and Social Media, 2009:361-362.
[21] Bikku, T., Jarugula, J., and Kongala, L., et al. Exploring the Effectiveness of BERT for Sentiment Analysis on Large-Scale Social Media Data[C].Hubli, India:IEEE, 2023:1-4.
[22] Blei, D. M., Ng, A. Y., and Jordan, M. I. Latent Dirichlet Allocation[J]. Journal of Machine Learning Research, 2003, 3:993-1022.
[23] Brown, T., Mann, B., and Ryder, N., et al. Language Models are Few-Shot Learners[J]. Advances in Neural Information Processing Systems,2020, 33:1877-1901.
[24] Cawsey, T., and Rowley, J. E. Social Media Brand Building Strategies in B2B Companies[J]. Marketing Intelligence&Planning, 2016, 34(6):754-776.
[25] Chen, J., Kou, G., and Peng, Y., et al. Effect of Marketing Messages and Consumer Engagement on Economic Performance:Evidence from Weibo[J]. Internet Research, 2020, 30(5):1565-1581.
[26] Chu, S. C., and Sung, Y. Using a Consumer Socialization Framework to Understand Electronic Word-of-Mouth(e WOM)Group Membership among Brand Followers on Twitter[J]. Electronic Commerce Research and Applications, 2015, 14(4):251-260.
[27] Cluley, R., and Green, W. Social Representations of Marketing Work:Advertising Workers and Social Media[J]. European Journal of Marketing,2019, 53(5):830-847.
[28] Falk, P. K. Mallet-Machine Learning for Language Toolkit[J]. Technical Services Quarterly, 2014, 31(4):410-411.
[29] Flament, C., and Rouquette, M. L. Anatomie des Idées Ordinaires:Comment?tudier les Représentations Sociales[M]. Paris:Armand Colin,2003:175.
[30] Guo, L., Vargo, C. J., and Pan, Z., et al. Big Social Data Analytics in Journalism and Mass Communication:Comparing Dictionary-Based Text Analysis and Unsupervised Topic Modeling[J]. Journalism&Mass Communication Quarterly, 2016, 93(2):332-359.
[31] Habibi, M. R., Laroche, M., and Richard, M. O. The Roles of Brand Community and Community Engagement in Building Brand Trust on Social Media[J]. Computers in Human Behavior, 2014, 37(37):152-161.
[32] Hajli, M. N. A study of the Impact of Social Media on Consumers[J]. International Journal of Market Research, 2014, 56(3):387-404.
[33] He, W., Tian, X., and Chen, Y., et al. Actionable Social Media Competitive Analytics for Understanding Customer Experiences[J]. Journal of Computer Information Systems, 2016, 56(2):145-155.
[34] Ibrahim, N. F., and Wang, X. A Text Analytics Approach for Online Retailing Service Improvement:Evidence from Twitter[J]. Decision Support Systems, 2019, 121:37-50.
[35] Joia, L. A., and Proen?a, R. The Social Representation of Fintech from the Perspective of Traditional Financial Sector Professionals:Evidence from Brazil[J]. Financial Innovation, 2022, 8(1):93.
[36] Jovchelovitch, S. Knowledge in Context:Representations, Community and Culture[M]. London:Routledge, 2019.
[37] Li, L., Fan, L., and Atreja, S., et al.“HOT”ChatGPT:The Promise of ChatGPT in Detecting and Discriminating Hateful, Offensive, and Toxic Comments on Social Media[J]. ACM Transactions on the Web, 2024, 18(2):1-36.
[38] Mazzotti, A. J. A. A Abordagem Estrutural das Representa??es Sociais[J]. Psicologia da Educa??o, 2002:14-15.
[39] Morin, M. Jean-Claude Abric:La Pratique Sociale au C?ur de la Recherche[J]. Papers on Social Representations, 2016, 25(2):111-119.
[40] Pu, X., Jiang, Q., and Fan, B. Chinese Public Opinion on Japan’s Nuclear Wastewater Discharge:A Case Study of Weibo Comments Based on a Thematic Model[J]. Ocean Coastal Management, 2022, 225:106188.
[41] Sá, C. P. Núcleo Central das Representa??es Sociais[M]. Petrópolis:Vozes, 1996.
[42] Tang, R., Chuang, Y. N., and Hu, X. The Science of Detecting LLM-Generated Text[J]. Communications of the ACM, 2024, 67(4):50-59.
[43] Vergès, P. EVOC-Ensemble de Programmes Permettant 1’Analyse desvocations:Manuel Version 15 Octobre 2003[M]. Aix-en-Provence:LAMES, 2003.
[44] Vergès, P. Représentations Sociales Partagés, Périphériques, Indifférentes, d’une Minorité:Méthodes d’Approche[J]. Les Cahiers Internationaux de Psychologie Sociale, 1995, 28:77-95.
[45] Zhao, W. X., Zhou, K., and Li, J., et al. A Survey of Large Language Models[J]. Ar Xiv Preprint Ar Xiv:2303. 18223, 2023.
基本信息:
DOI：
中图分类号:TP18;F724.6;F274
引用信息:
[1]马少辉,王炜辰.基于大语言模型的消费者社交媒体表征分析：以淘宝退货服务为例[J].消费经济,2024,40(06):85-98.
基金信息:
国家自然科学基金面上项目（72072092）; 江苏省研究生科研与实践创新计划项目（SJCX24＿1186）