基于大规模数据的演员职业发展的统计分析与建模

在当今信息时代，影视行业中大规模的演员、影视作品以及颁奖信息被完整 地记录了下来，通过对数据进行统计分析与建模，挖掘数据中隐藏的模式，揭示其 中的潜在发展规律，可以为演员职业生涯发展、影视行业发展以及社会经济提供 指导。 演员的职业生涯常常伴随着成功与失败，但是现有研究对演员的成败机制还 未进行过深入的探讨。本文基于 2019 年之前 6160 个影视行业颁奖事件的颁奖记 录以及 IMDb 数据集，通过演员的获奖情况来定义演员职业生涯的成败，旨在研 究成败机制在演员职业发展中起到的作用。 首先，本文采用 TOPSIS+Co-HITS 的排序算法架构对颁奖事件的含金量进行 评估并筛选出了含金量排名前 100 的颁奖事件，算法综合考虑了颁奖事件的知名 度、规模、历史沉淀、专业性、群众认可度以及艺术性，筛选出的颁奖事件用于衡 量演员职业早期的成败以及未来职业的发展。 接着本文从演员的荣誉、生产力、知名度以及专业能力出发评估演员未来的 职业发展并对其进行了探索性的统计分析。结果表明，演员第一次被知名奖项提 名后的 5 年是演员职业生涯中取得荣誉和产出作品的巅峰时期，此外演员的知名 度和专业能力并不会随着年份的增长而出现显著的波动，被知名奖项提名能显著 加速演员的职业发展。 其次，本文使用倾向评分匹配的方法，估计演员职业早期成败对未来职业发 展的因果效应。研究发现，职业早期的挫败会增加演员的流失率，促使 2% 的演员 永久地离开影视行业。在演员未来的专业能力上，职业早期经历挫败的演员表现 得更好，而在演员未来的荣誉、知名度和生产力上，职业早期获得成功的演员表现 得更出色。总的来说，失败比成功更能磨砺内心，而成功更容易得到外界的关注 以及资源的倾斜。 最后，本文使用随机森林以及带 L1 正则项的广义线性模型研究影响演员未来 职业发展的重要因素。研究发现，尽管职业早期的挫败会对演员未来的荣誉、生 产力、知名度以及专业能力产生显著的影响，但是相比于演员提名前积累的知名 度和专业能力，职业早期挫败带来的影响可以忽略不计，这告诫演员不要害怕职 业早期的挫败，努力提高自己职业早期的知名度和专业能力更为重要。 本研究揭示了演员职业发展的规律，能为演员的职业规划提供建议，此外本文采用的 TOPSIS+Co-HITS 排序架构具有一定的创新性，既充分利用了原始数据 的指标信息又考虑了网络结构的信息，对颁奖事件含金量排序的思路以及结果也 能用于后续影视行业的相关研究中。

[1] WEINER B. Achievement motivation and attribution theory[M]. General Learning, 1974.
[2] KC D, STAATS B R, GINO F. Learning from my success and from others’ failure: Evidence from minimally invasive cardiac surgery[J]. Management Science, 2013, 59(11): 2435-2449.
[3] BOL T, DE VAAN M, VAN DE RIJT A. The Matthew effect in science funding[J]. Proceedings of the National Academy of Sciences, 2018, 115(19): 4887-4890.
[4] MERTON R K. The Matthew effect in science: The reward and communication systems of science are considered.[J]. Science, 1968, 159(3810): 56-63.
[5] AZOULAY P, STUART T, WANG Y. Matthew: Effect or fable?[J]. Management Science,2014, 60(1): 92-109.
[6] SALGANIK M J, DODDS P S, WATTS D J. Experimental Study of Inequality and Unpredictability in an Artificial Cultural Market[J]. Science, 2006, 311(5762): 854-856.
[7] MUCHNIK L, ARAL S, TAYLOR S J. Social Influence Bias: A Randomized Experiment[J].Science, 2013, 341(6146): 647-651.
[8] VAN DE RIJT A, KANG S M, RESTIVO M, et al. Field experiments of success-breeds-successdynamics[J]. Proceedings of the National Academy of Sciences, 2014, 111(19): 6934-6939.
[9] ELTON E J, GRUBER M J, BLAKE C R. Survivor bias and mutual fund performance[J]. The review of financial studies, 1996, 9(4): 1097-1120.
[10] BROWN S J, GOETZMANN W, IBBOTSON R G, et al. Survivorship bias in performancestudies[J]. The Review of Financial Studies, 1992, 5(4): 553-580.
[11] WANG Y, JONES B F, WANG D. Early-career setback and future career impact[J]. Nature communications, 2019, 10(1): 4331.
[12] IACUS S M, KING G, PORRO G. Causal inference without balance checking: Coarsened exactmatching[J]. Political analysis, 2012, 20(1): 1-24.
[13] BLACKWELL M, IACUS S, KING G, et al. Cem: Coarsened Exact Matching in Stata[J]. The Stata Journal, 2009, 9(4): 524-546.
[14] PRASAD J M, SHIPLEY M T, ROGERS T B, et al. National Institutes of Health (NIH) grant awards: does past performance predict future success?[J]. Palgrave Communications, 2020, 6(1): 1-7.
[15] KRAUSS A, DANÚS L, SALES-PARDO M. Early-career factors largely determine the future impact of prominent researchers: evidence across eight scientific fields[J]. Scientific Reports, 2023, 13(1): 18794.
[16] YIN Y, WANG Y, EVANS J A, et al. Quantifying the dynamics of failure across science, startups and security[J]. Nature, 2019, 575(7781): 190-194.
[17] ZHANG L, BANERJEE M, WANG S, et al. The fragility of artists’reputations from 1795 to 2020[J]. Proceedings of the National Academy of Sciences, 2023, 120(35): e2302269120.
[18] WILLIAMS O E, LACASA L, LATORA V. Quantifying and predicting success in show business[J]. Nature communications, 2019, 10(1): 2256.
[19] WASSERMAN M, ZENG X H T, AMARAL L A N. Cross-evaluation of metrics to estimate the significance of creative works[J]. Proceedings of the National Academy of Sciences, 2015, 112(5): 1281-1286.
[20] PAGE L, BRIN S, MOTWANI R, et al. The PageRank Citation Ranking: Bringing Order to the Web[R]. Stanford InfoLab, 1999.
[21] ROSENBAUM P R, RUBIN D B. The central role of the propensity score in observational studies for causal effects[J]. Biometrika, 1983, 70(1): 41-55.
[22] HWANG C L, YOON K. Multiple attribute decision making: methods and applications a stateof-the-art survey[M]. Springer Science & Business Media, 2012.
[23] KLEINBERG J M. Authoritative sources in a hyperlinked environment[J]. Journal of the ACM(JACM), 1999, 46(5): 604-632.
[24] DENG H, LYU M R, KING I. A generalized co-hits algorithm and its application to bipartite graphs[C]//Proceedings of the 15th ACM SIGKDD international conference on Knowledge discovery and data mining. 2009: 239-248.
[25] HE X, GAO M, KAN M Y, et al. BiRank: Towards Ranking on Bipartite Graphs[J]. IEEETransactions on Knowledge and Data Engineering, 2016, 29(1): 57-71.
[26] CAO L, GUO J, CHENG X. Bipartite graph based entity ranking for related entity finding[C]//2011 IEEE/WIC/ACM International Conferences on Web Intelligence and Intelligent Agent Technology: volume 1. IEEE, 2011: 130-137.
[27] RUI X, LI M, LI Z, et al. Bipartite graph reinforcement model for web image annotation[C]//Proceedings of the 15th ACM international conference on Multimedia. 2007: 585-594.
[28] BASMANN R L. A generalized classical method of linear estimation of coefficients in a structural equation[J]. Econometrica: Journal of the Econometric Society, 1957: 77-83.
[29] THEIL H. Repeated least squares applied to complete equation systems[J]. The Hague: central planning bureau, 1953.
[30] FAN J, LV J. Sure Independence Screening for Ultrahigh Dimensional Feature Space[J]. Journal of the Royal Statistical Society Series B: Statistical Methodology, 2008, 70(5): 849-911.
[31] TIBSHIRANI R. Regression Shrinkage and Selection Via the Lasso[J]. Journal of the Royal Statistical Society: Series B (Methodological), 1996, 58(1): 267-288.
[32] NELDER J A, WEDDERBURN R W. Generalized linear models[J]. Journal of the RoyalStatistical Society Series A: Statistics in Society, 1972, 135(3): 370-384.
[33] CORTES C, VAPNIK V. Support-vector networks[J]. Machine learning, 1995, 20: 273-297.
[34] QUINLAN J R. Induction of decision trees[J]. Machine learning, 1986, 1: 81-106.
[35] QUINLAN J R. C4.5 Programs for Machine Learning[J]. Morgan Kaufmann, 1993.
[36] BREIMAN L. Classification and regression trees[J]. Monterey, CA: Wadsworth and Brools, 1984.
[37] BREIMAN L. Random forests[J]. Machine learning, 2001, 45: 5-32.
[38] FRIEDMAN J H. Greedy function approximation: a gradient boosting machine[J]. Annals of statistics, 2001: 1189-1232.
[39] FRIEDMAN J, HASTIE T, TIBSHIRANI R. Additive logistic regression: a statistical view of boosting (with discussion and a rejoinder by the authors)[J]. The annals of statistics, 2000, 28(2): 337-407.
[40] BREIMAN L. Bagging predictors[J]. Machine learning, 1996, 24: 123-140.
[41] SCHAPIRE R E. The strength of weak learnability[J]. Machine learning, 1990, 5: 197-227.
[42] WOLPERT D H. Stacked generalization[J]. Neural networks, 1992, 5(2): 241-259.
[43] 李航. 统计学习方法[M]. 2 版. 清华大学出版社, 2019: 82-84.