基于神经网络的CEO表情分析及其对发布会媒体关注度的影响*

doi:10.11925/infotech.2096-3467.2022.0787

数据分析与知识发现

2023, Vol. 7

Issue (8): 46-61 https://doi.org/10.11925/infotech.2096-3467.2022.0787

研究论文

本期目录 | 过刊浏览 | 高级检索

基于神经网络的CEO表情分析及其对发布会媒体关注度的影响*

李洋,赵吉昌(

)

北京航空航天大学经济管理学院北京 100191

CEO Facial Expression Analysis Based on Neural Networks and Its Impacts on Media Attention at Press Conferences

Li Yang,Zhao Jichang(

)

School of Economics and Management, Beihang University, Beijing 100191, China

摘要
图/表
参考文献
相关文章
Metrics

全文: PDF (3489 KB) HTML ( 26 )
输出: BibTeX | EndNote (RIS)

摘要

【目的】基于神经网络检测实时视频流中的人脸表情以探究CEO在产品发布会上的情绪特征与媒体关注度的关联。【方法】收集34家电子产品公司566场产品发布会视频，通过 MTCNN等模型对产品发布会上CEO的表情进行检测，结合统计学分析方法对CEO的情绪表达模式进行探究，并采用关联性分析的方法探究CEO情绪特征对发布会媒体关注度的影响。【结果】不同公司CEO在发布会中存在迥异的情绪表达模式，可聚集为与企业主营产品类型密切关联的若干类簇，各类簇中也存在截然不同的情绪惯性表达以及影响趋势，且愤怒情绪占比与发布会媒体关注度均在95%置信度下显著正相关（Pearson相关系数均大于0.21）。【局限】 仅面向电子产品发布会，所采集的各公司数据分布也不均匀。【结论】应用深度学习实现了基于视频流的CEO表情快速检测，分析了CEO情绪表达模式及其影响，提出了CEO情绪管理对品牌传播等的建议。

	服务

	把本文推荐给朋友
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	李洋
	赵吉昌

关键词 ：表情分析, 神经网络, CEO, 发布会, 媒体关注度

Abstract：

[Objective] This paper uses neural networks to detect facial expressions in real-time video streams, aiming to explore the correlation between CEO’s emotional characteristics at product launch events and media attention. [Methods] A total of 566 product launch event videos from 34 electronics companies were collected. Facial expressions of CEOs during the events were detected using models like MTCNN. Then, we investigated the patterns of CEO’s emotional expressions and explored the influence of their characteristics on media attention with correlation analysis. [Results] CEOs of different companies exhibited distinct emotional expression patterns during the launch events, which could be clustered closely associated with the main product types of the companies. Each cluster also had significant emotional inertia expression and influence trends. The proportion of anger was positively correlated with media attention during the launch events at a confidence level of 95% (with Pearson’s correlation coefficients exceeding 0.21). [Limitations] This study focuses on electronic product launch events, and the collected data from various companies were not unevenly distributed. [Conclusions] Deep learning enable the rapid detection of CEO facial expressions based on video streams. This study analyzed CEO’s emotional expression patterns and their influence and provided suggestions for CEO’s emotional management in brand communication.

Key words： Expression Analysis Neural Network CEO Press Conference Media Attention

收稿日期: 2022-07-27 出版日期: 2023-10-08

ZTFLH:

TP391

基金资助:* 国家自然科学基金面上项目(71871006)

通讯作者: 赵吉昌,ORCID:0000-0002-5319-8060,E-mail: jichang@tuaa.edu.cn。

引用本文:

李洋, 赵吉昌. 基于神经网络的CEO表情分析及其对发布会媒体关注度的影响*[J]. 数据分析与知识发现, 2023, 7(8): 46-61.
Li Yang, Zhao Jichang. CEO Facial Expression Analysis Based on Neural Networks and Its Impacts on Media Attention at Press Conferences. Data Analysis and Knowledge Discovery, 2023, 7(8): 46-61.

链接本文:

https://manu44.magtech.com.cn/Jwk_infotech_wk3/CN/10.11925/infotech.2096-3467.2022.0787 或 https://manu44.magtech.com.cn/Jwk_infotech_wk3/CN/Y2023/V7/I8/46

Fig.1 研究框架

Fig.2 人脸识别网络构架

Table 1 产品发布会视频分布结构

Table 2 百度搜索指数数据结构

Fig.3 荣耀公司百度搜索指数特征波动类型

Fig.4 9家公司CEO情绪得分均值分布

Fig.5 34家公司CEO主体情绪聚类谱系图

Fig.6 基于聚类结果的CEO情绪特征分布

Fig.7 30阶延迟内CEO的情绪自相关情况（以魅族公司为例）

Fig.8 IQOO公司CEO愤怒情绪对其他情绪交叉相关性影响

Table 3 公司CEO情绪分布与百度搜索指数增幅相关性分析

[1]	Hirshleifer D, Low A, Teoh S H. Are Overconfident CEOs Better Innovators?[J]. United Kingdom: The Journal of Finance, 2012, 67(4): 1457-1498.
[2]	李峰, 崔康乐. 企业社会责任行为对东道国消费者的影响研究——基于中国品牌国际化视角[J]. 华东经济管理, 2022, 36(6): 89-104.
[2]	(Li Feng, Cui Kangle. Research on the Impact of Corporate Social Responsibility Behavior on Consumers in the Host Country: From the Perspective of Chinese Brand Internationalization[J]. East China Economic Management, 2022, 36(6): 89-104.)
[3]	张彩燕. 企业社会责任对企业品牌的影响作用研究[J]. 现代商业, 2022(5): 24-26.
[3]	(Zhang Caiyan. Research on the Influence of Corporate Social Responsibility on Corporate Brand[J]. Modern Business, 2022(5): 24-26.)
[4]	张琼. 论移动互联时代广告文案在品牌价值上的功能体现[J]. 应用写作, 2022(2): 21-27.
[4]	(Zhang Qiong. On the Function of Advertising Copy in the Era of Mobile Internet in Brand Value[J]. Applied Writing, 2022(2): 21-27.)
[5]	梁子玉. 品牌建构:苹果公司的植入式广告探析[J]. 新闻研究导刊, 2022, 13(1): 242-244.
[5]	(Liang Ziyu. Brand Building: An Analysis of Apple’s Product Placement[J]. Journal of Journalism and Research, 2022, 13(1): 242-244.)
[6]	Haroon Hakimi. 影响新闻发布会的关键因素:公共关系从业人员和新闻工作者的互动研究[D]. 重庆: 西南大学, 2021.
[6]	(Haroon Hakimi. The Effective Elements of a Press Conference:The Coorientation Approach of Public Relations Practitioner and Journalists[D]. Chongqing: Southwest University, 2021.)
[7]	姜继涛. 产品发布会在手机营销中的作用与对策分析[J]. 现代营销, 2018(1): 67.
[7]	(Jiang Jitao. Analysis of the Function and Countermeasures of Product Launch in Mobile Phone Marketing[J]. Modern Marketing, 2018(1): 67.)
[8]	Li S, Deng W H. Deep Facial Expression Recognition: A Survey[J]. IEEE Transactions on Affective Computing, 2022, 13(3): 1195-1215. doi: 10.1109/TAFFC.2020.2981446
[9]	Donahue J, Jia Y Q, Vinyals O. DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition[C]// Proceedings of the 31st International Conference on Machine Learning - Volume 32. 2014: I-647-I-655.
[10]	Jia Y Q, Shelhamer E, Donahue J, et al. Caffe: Convolutional Architecture for Fast Feature Embedding[C]// Proceedings of the 22nd ACM International Conference on Multimedia. 2014: 675-678.
[11]	Yu Z D, Zhang C. Image Based Static Facial Expression Recognition with Multiple Deep Network Learning[C]// Proceedings of the 2015 ACM on International Conference on Multimodal Interaction. 2015: 435-442.
[12]	Schroff F, Kalenichenko D, Philbin J. FaceNet: A Unified Embedding for Face Recognition and Clustering[C]// Proceedings of 2015 IEEE Conference on Computer Vision and Pattern Recognition. 2015: 815-823.
[13]	Ekman P, Friesen W V. Constants Across Cultures in the Face and Emotion[J]. Journal of Personality and Social Psychology, 1971, 17(2): 124-129. doi: 10.1037/h0030377 pmid: 5542557
[14]	Ben X Y, Ren Y, Zhang J P, et al. Video-Based Facial Micro-Expression Analysis: A Survey of Datasets, Features and Algorithms[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022, 44(9): 5826-5846.
[15]	Liu Y J, Zhang J K, Yan W J, et al. A Main Directional Mean Optical Flow Feature for Spontaneous Micro-Expression Recognition[J]. IEEE Transactions on Affective Computing, 2016, 7(4): 299-310. doi: 10.1109/T-AFFC.5165369
[16]	Kim D H, Baddar W J, Ro Y M. Micro-Expression Recognition with Expression-State Constrained Spatio-Temporal Feature Representations[C]// Proceedings of the 24th ACM International Conference on Multimedia. 2016: 382-386.
[17]	Zhang K H, Huang Y Z, Du Y, et al. Facial Expression Recognition Based on Deep Evolutional Spatial-Temporal Networks[J]. IEEE Transactions on Image Processing, 2017, 26(9): 4193-4203. doi: 10.1109/TIP.2017.2689999 pmid: 28371777
[18]	Zhou E J, Cao Z M, Yin Q. Naive-Deep Face Recognition: Touching the Limit of LFW Benchmark or Not [OL]. arXiv Preprint, arXiv: 1501.04690.
[19]	Fan H Q, Cao Z M, Jiang Y N, et al. Learning Deep Face Representation[OL]. arXiv Preprint, arXiv: 1403.2802.
[20]	王琳琳. CEO情绪特质对企业战略决策影响的实证研究[D]. 合肥: 中国科学技术大学, 2018.
[20]	(Wang Linlin. An Empirical Study on the Influence of CEO’s Emotional Characteristics on Corporate Strategic Decision-Making[D]. Hefei: University of Science and Technology of China, 2018.)
[21]	Mesquita B, Boiger M. Emotions in Context: A Sociodynamic Model of Emotions[J]. Emotion Review, 2014, 6(4): 298-302. doi: 10.1177/1754073914534480
[22]	LaBar K S, Cabeza R. Cognitive Neuroscience of Emotional Memory[J]. Nature Reviews Neuroscience, 2006, 7: 54-64. doi: 10.1038/nrn1825 pmid: 16371950
[23]	Kuppens P, Verduyn P. Emotion Dynamics[J]. Current Opinion in Psychology, 2017, 17: 22-26. doi: S2352-250X(16)30201-9 pmid: 28950968
[24]	Kuppens P, Verduyn P. Looking at Emotion Regulation Through the Window of Emotion Dynamics[J]. Psychological Inquiry, 2015, 26(1): 72-79. doi: 10.1080/1047840X.2015.960505
[25]	Larsen R J. The Stability of Mood Variability: A Spectral Analytic Approach to Daily Mood Assessments[J]. Journal of Personality and Social Psychology, 1987, 52(6): 1195-1204. doi: 10.1037/0022-3514.52.6.1195
[26]	于宁莉, 易东云, 涂先勤. 时间序列中自相关与偏相关函数分析[J]. 数学理论与应用, 2007, 27(1): 54-57.
[26]	(Yu Ningli, Yi Dongyun, Tu Xianqin. Analysis of Autocorrelation and Partial Correlation Functions in Time Series[J]. Mathematical Theory and Applications, 2007, 27(1): 54-57.)
[27]	Bertrand M, Schoar A. Managing with Style: The Effect of Managers on Firm Policies[J]. The Quarterly Journal of Economics, 2003, 118(4): 1169-1208. doi: 10.1162/003355303322552775
[28]	Gomulya D, Wong E M, Ormiston M E, et al. The Role of Facial Appearance on CEO Selection after Firm Misconduct[J]. Journal of Applied Psychology, 2017, 102(4): 617-635. doi: 10.1037/apl0000172 pmid: 27991800
[29]	Sun Y J, Akansu A A, Cicon J E. The Power of Fear: Facial Emotion Analysis of CEOs to Forecast Firm Performance[C]// Proceedings of the 2014 IEEE 15th International Conference on Information Reuse and Integration. 2014: 695-702.
[30]	田敏, 李纯青, 萧庆龙. 企业社会责任行为对消费者品牌评价的影响[J]. 南开管理评论, 2014, 17(6): 19-29.
[30]	(Tian Min, Li Chunqing, Xiao Qinglong. The Impact of Corporate Social Responsibility Activities on Brand Evaluation[J]. Nankai Business Review, 2014, 17(6): 19-29.)
[31]	裴荣康. 企业微博内容对网络口碑及品牌认可度的影响及对策探析[J]. 企业改革与管理, 2022(2): 114-116.
[31]	(Pei Rongkang. The Influence of Enterprise Weibo Content on Online Word of Mouth and Brand Recognition and the Countermeasures[J]. Enterprise Reform and Management, 2022(2): 114-116.)
[32]	Pe M L, Kuppens P. The Dynamic Interplay Between Emotions in Daily Life: Augmentation, Blunting, and the Role of Appraisal Overlap[J]. Emotion, 2012, 12(6): 1320-1328. doi: 10.1037/a0028262 pmid: 22642355
[33]	Barrett L F, Gross J J, Christensen T C, et al. Knowing What You’re Feeling and Knowing What to Do about It: Mapping the Relation Between Emotion Differentiation and Emotion Regulation[J]. Cognition and Emotion, 2001, 15(6): 713-724. doi: 10.1080/02699930143000239
[34]	Nook E C, Sasse S F, Lambert H K, et al. The Nonlinear Development of Emotion Differentiation: Granular Emotional Experience is Low in Adolescence[J]. Psychological Science, 2018, 29(8): 1346-1357. doi: 10.1177/0956797618773357 pmid: 29878880
[35]	Sun Y, Wang X G, Tang X O. Deep Convolutional Network Cascade for Facial Point Detection[C]// Proceedings of 2013 IEEE Conference on Computer Vision and Pattern Recognition. 2013: 3476-3483.
[36]	Fan R, Xu K, Zhao J C. Weak Ties Strengthen Anger Contagion in Social Media[OL]. arXiv Preprint, arXiv: 2005.01924.
[37]	Chuai Y W, Zhao J C. Anger Can Make Fake News Viral Online[J]. Frontiers in Physics, 2022, 10: 970174. doi: 10.3389/fphy.2022.970174

[1]	许鑫, 李倩, 姚占雷. 基于图神经网络的技术识别链接预测方法研究^*[J]. 数据分析与知识发现, 2023, 7(6): 15-25.
[2]	刘欣然, 徐雅斌, 李继先. 网评贴文自动生成方法研究^*[J]. 数据分析与知识发现, 2023, 7(4): 101-113.
[3]	李浩君, 吕韵, 汪旭辉, 黄诘雅. 融入情感分析的多层交互深度推荐模型研究^*[J]. 数据分析与知识发现, 2023, 7(3): 43-57.
[4]	裴伟, 孙水发, 李小龙, 鲁际, 杨柳, 吴义熔. 融合领域知识的医学命名实体识别研究^*[J]. 数据分析与知识发现, 2023, 7(3): 142-154.
[5]	段宇锋, 贺国秀. 面向中文医学文本命名实体识别的神经网络模块分解分析^*[J]. 数据分析与知识发现, 2023, 7(2): 26-37.
[6]	赵蕊洁, 佟昕瑀, 刘小桦, 路永和. 基于神经网络的医药科技论文实体识别与标注研究^*[J]. 数据分析与知识发现, 2022, 6(9): 100-112.
[7]	成全, 佘德昕. 融合患者体征与用药数据的图神经网络药物推荐方法研究^*[J]. 数据分析与知识发现, 2022, 6(9): 113-124.
[8]	唐娇, 张力生, 桑春艳. 基于潜在主题分布和长、短期用户表示的新闻推荐模型^*[J]. 数据分析与知识发现, 2022, 6(9): 52-64.
[9]	游新冬, 袁梦龙, 张乐, 吕学强. CNN-SM：基于义原与多特征融合的消费品领域缺陷词识别模型^*[J]. 数据分析与知识发现, 2022, 6(9): 77-85.
[10]	杨美芳, 杨波. 基于笔画ELMo嵌入IDCNN-CRF模型的企业风险领域实体抽取研究^*[J]. 数据分析与知识发现, 2022, 6(9): 86-99.
[11]	赵鹏武, 李志义, 林小琦. 基于注意力机制和卷积神经网络的中文人物关系抽取与识别*[J]. 数据分析与知识发现, 2022, 6(8): 41-51.
[12]	周宁, 靳高雅, 石雯茜. 融合神经网络与全局推理的实体共指消解算法*[J]. 数据分析与知识发现, 2022, 6(8): 75-83.
[13]	杨文丽, 李娜娜. 基于对抗网络的文本对齐跨语言情感分类方法^*[J]. 数据分析与知识发现, 2022, 6(7): 141-151.
[14]	张若琦, 申建芳, 陈平华. 结合GNN、Bi-GRU及注意力机制的会话序列推荐^*[J]. 数据分析与知识发现, 2022, 6(6): 46-54.
[15]	郭樊容, 黄孝喜, 王荣波, 谌志群, 胡创, 谢一敏, 司博宇. 基于Transformer和图卷积神经网络的隐喻识别^*[J]. 数据分析与知识发现, 2022, 6(4): 120-129.

Viewed

Full text

Abstract

Cited

Shared

Discussed