主管:中国科学院
主办:中国优选法统筹法与经济数学研究会
   中国科学院科技战略咨询研究院
论文

电影预告片在线投放对票房的影响——基于文本情感分析方法

展开
  • 合肥工业大学管理学院, 安徽 合肥 230009

收稿日期: 2016-08-31

  修回日期: 2017-01-05

  网络出版日期: 2017-12-15

基金资助

教育部人文社会科学研究资助项目(15YJC630111);国家自然科学基金重大研究计划资助项目(71490725);国家自然科学基金资助项目(71501057)

The Effects of Online Pre-launch Movie Trailers on the Box Office Revenue——Based on Text Sentiment Analysis Method

Expand
  • School of Management, Hefei University of Technology, Hefei 230009, China

Received date: 2016-08-31

  Revised date: 2017-01-05

  Online published: 2017-12-15

摘要

预告片是电影上映之前的一种营销方式。过去,预告片主要通过影院或者电视平台进行传播,现在,预告片更多被投放在网络视频播放平台上。本文研究预告片的在线投放策略对预告片关注数量和预告片评论情感的影响,以及预告片关注数量和预告片评论情感对影片票房的影响。基于纯暴露理论、消费者参与理论提出了研究假设,从视频网站时光网(www.mtime.com)和电影数据库网站艺恩网(www.entgroup.cn)采集了研究数据,对预告片评论文本进行了文本情感分析,建立模型并对模型参数进行了估计。研究结果表明:(1)预告片的投放时间、数量、长度对预告片关注数量有显著作用。提前投放和密集投放会提高预告片的营销效果。(2)预告片关注数量和预告片评论情感对影片票房有显著作用。关注数量越多,积极情感词汇越多,票房越高。(3)影片上映之前,预告片评论中的"乐"、"哀"词频对票房有显著作用。影片上映期间,预告片评论中的"好"、"恶"词频对影片票房有显著作用。研究结论可以为电影营销策略制定和营销资源分配提供支持。

本文引用格式

孙春华, 刘业政 . 电影预告片在线投放对票房的影响——基于文本情感分析方法[J]. 中国管理科学, 2017 , 25(10) : 151 -161 . DOI: 10.16381/j.cnki.issn1003-207x.2017.10.016

Abstract

Trailers are the most widely used method of movie advertising, with the purpose of building consumer awareness and expectations before the release of the movie. In the past, movie trailers were shown at the cinema or on television. Nowadays, trailers appear on the video websites. The effects of online pre-launch movie trailers include two periods:before the release of the movie and after the release of the movie. In the paper, the effects of movie trailers on the viewers' awareness and preference and the effects of the viewers' awareness and preference on the movies' box office revenue are studied. Based on the theories of pure exposure and consumer engagement, the research hypothesis is put forward. Data is collected from mtime.com(www.mtime.com) and entgroup.com(www.entgroup.cn) and text sentiment analysis methods are used to extract the sentiment words from the viewer comments of the movie trailers. A hurdle model is established to examine the effects of movie trailers on the viewers' awareness and preference. A cross section data model and a panel data model are established to examine the effects of the viewers' awareness and preference on the openingweek box office revenue and the weekly box office revenue. The results show that:(1) the release time, the number and the length of movie trailers have effects on the number of the viewer comments.(2) The number of viewer comments and the frequencies of sentiment words have effects on the box office revenue.(3)Before the release of the movie, the frequencies of the words about "joy" and "sadness" have effects on the box office revenue. After the release of the movie, the frequencies of the words about "like" and "dislike" have effects on the box office revenue. The conclusions of the study can provide support for movie marketing strategy development and marketing resource allocation.

参考文献

[1] Karray S, Debernitz L. The effectiveness of movie trailer advertising [J].International Journal of Advertising Research,2017,36(2):368-392.

[2] Oh S, Ahn J, Baek H. Viewer engagement in movie trailers and box office revenue[C]//Proceedings of 2015 48th Hawaii International Conference on System Sciences, Kauai,HI,USA,January, 5-8,2015.

[3] Hou Yimin, Xiao Ting, Zhang Shu, et al.Predicting movie trailer viewer’s "like/dislike" via learned shot editing patterns [J]. IEEE Transactions on Affective Computing, 2016, 7(1):29-44.

[4] Finsterwalder J, Kuppelwieser V G, Villiers M D.The effects of film trailers on shaping consumer expectations in the entertainment industry [J]. Journal of Retailing and Consumer Services, 2012, 19(6): 589-595.

[5] Sauer M. Cue-recognition effects in the assessment of movie trailers [J]. Journal of Retailing and Consumer Services,2014, 21 (3):376-382.

[6] Suckfüll M, Moellering K. The differential success of movie trailers [J]. Journal of Retailing and Consumer Services, 2015, 22:138-144.

[7] Duan Wenjing, Gu Bin, Whinston A B.Do online reviews matter? An empirical investigation of panel data [J].Decision Support Systems, 2008, 45(4):1007-1016.

[8] Gopinath S,Chintagunta P K, Venkataraman S. Blogs, advertising and local-market movie box-office performance [J]. Management Science, 2013, 59(12):2635-2654.

[9] Karniouchina E V. Impact of star and movie buzz on motion picture distribution and box office revenue [J]. International Journal of Research in Marketing, 2011, 28 (1):62-74.

[10] 郝媛媛,邹鹏,李一军,等.基于电影面板数据的在线评论情感倾向对销售收入影响的实证研究[J].管理评论,2009,21(10):95-103.

[11] 王炼,贾建民.基于网络搜索的票房预测模型——来自中国电影市场的证据[J]. 系统工程理论与实践,2014,34(12):3079-3090.

[12] Apala K R, Jose M, Motnam S, et al. Prediction of movies box office performance using social media [C]// Proceedings of 2013 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining,Niagara Falls,ON,Canada,August,25-28,2013.

[13] Oh C, Roumani Y, Nwankpa J K, et al. Beyond likes and tweets: Consumer engagement behavior and movie box office in social media [J]. Information &Management.2017,54(1):25-37.

[14] Archak N, Ghose A, Ipeirotis P G. Deriving the pricing power of product features by mining consumer reviews [J]. Management Science, 2011, 57(8): 1485-1509.

[15] Joshi M, Das D, Gimpel K, et al. Movie reviews and revenues: An experiment in text regression [C]//Proceedings of the 2010 Annual Conference of the North American Chapter of the ACL, Los Angeles,Califonia,USA,June 2-4,2010.

[16] Rui Huaxia, Liu Yizao, Whinston A. Whose and what chatter matters? The effect of tweets on movie sales [J]. Decision Support Systems, 2013, 55(4): 863-870.

[17] 史伟,王洪伟,何绍义. 基于微博情感分析的电影票房预测研究[J].华中师范大学学报(自然科学版),2015,49(1):66-72.

[18] Ehrenberg A S C. Repetitive advertising and the consumer [J]. Journal of Advertising Research,2000, 40(6): 39-48.

[19] Kalish S, A new product adoption model with price, advertising, and uncertainty[J]. Management Science, 1985, 31(12): 1569-1585.

[20] Moon S, Kim J, Bayus B L, et al. Consumers’ pre-launch awareness and preference on movie sales [J]. European Journal of Marketing, 2016, 50(5/6): 1024-1046.

[21] Cross J J, Levenson R W. Emotion elicitation using films [J]. Cognition and Emotion. 1995, 9(1): 87-108.

[22] 郝媛媛,叶强,李一军.基于影评数据的在线评论有用性影响因素研究[J].管理科学学报,2010,13(8):78-88.

[23] 王伟,王洪伟.特征观点对购买意愿的影响:在线评论的情感分析方法[J].系统工程理论与实践,2016,36(1):63-76.

[24] Divakaran P K P, Nørskov S. Are online communities on par with experts in the evaluation of new movies? Evidence from the Fandango community [J]. Information Technology & People, 2016, 29(1): 120-145.

[25] Asur S,Huberman B A. Predicting the future with social media [C]//Proceedings of the 2010 IEEE/WIC/ACM International Conference on Web Intellingence and Intelligent Agent Technology,Washington,DC,USA,August 31-September 03,2010.

[26] Liu Yong. Word-of-mouth for movies: Its dynamics and impact on box office revenue [J]. Journal of Marketing, 2006, 70(3):74-89.

[27] Ghiassi M, Lio D, Moon B. Pre-production forecasting of movie revenues with a dynamic artificial neural network [J].Expert Systems with Applications, 2015, 42(6):3176-3193.

[28] 施晓菁,梁循,孙晓蕾.基于在线评级和评论的评价者效用机制研究[J].中国管理科学,2016,24(5):149-157.

[29] 徐琳宏,林鸿飞,潘宇,等.情感词汇本体的构造[J].情报学报,2008,27(2):180-185.

[30] Hur M, Kang P, Cho S. Box-office forecasting based on sentiments of movie reviews and Independent subspace method [J].Information Sciences, 2016,372: 608-624.

[31] Niraj R, Singh J.Impact of user-generated and professional critics reviews on Bollywood movie success [J]. Australasian Marketing Journal, 2015, 23(3):179-187.

[32] Kim SH, Park N, Park SH .Exploring the effects of online word of mouth and expert reviews on theatrical movies' box office success [J]. Journal of Media Economics, 2013, 26(2):98-114.

[33] Eliashberg J, Jonker JJ, Sawhney MS, et al. MOVIEMOD: An implementable decision support system for pre-release market evaluation of motion pictures [J].Marketing Science, 2000,19(3):226-243.
文章导航

/