Forecasting movie sales based on its trailer’s features
Development of a tool for predicting box office receipts from films sales and return on investment. Analysis of textual content used in trailers. Categorization of words into positive and negative. Building an attractive movie production model for buyers.
| Рубрика | Менеджмент и трудовые отношения |
| Вид | дипломная работа |
| Язык | английский |
| Дата добавления | 10.12.2019 |
| Размер файла | 1,8 M |
Отправить свою хорошую работу в базу знаний просто. Используйте форму, расположенную ниже
Студенты, аспиранты, молодые ученые, использующие базу знаний в своей учебе и работе, будут вам очень благодарны.
3) Actions (criminal) [crime] are valuable and make the gross increasing;
4) Wonders (miracles) [miracles] topic has a positive impact on movie sales;
5) Adventures [adventures] topic is also valuable, but mostly decreases the revenue of the move.
The linear regression model showed that sentimental division has no valuable effect on the movie's gross.
The P-value of these variables was bigger than 0.05, meaning that there is no significant correlation among them.
This result shows that the hypotheses about positive and negative words are rejected. (Table 3)
lm(formula = netgross ~ pers + sentresidualspos +
+ sentresidualsneg +spys + crime + miracles + adventures) Code in R programming for Linear Regression model (4)
where, sentresidualspos =positive words put in logarithm
sentresidualsneg = negative words put in logarithm.
Table 3
Linear Regression results
|
Min |
1Q |
Median |
3Q |
Max |
|
|
-114778610 |
-50996840 |
-23608664 |
26279984 |
565888443 |
|
|
Coefficients: |
|||||
|
Estimate |
Std. Error |
t value |
Pr(>|t|) |
||
|
(Intercept) |
72895897 |
2146504 |
33.960 |
< 2e-16 *** |
|
|
drama |
-8650639 |
12895345 |
-0.671 |
0.50244 |
|
|
spys |
-47739288 |
15592264 |
-3.062 |
0.00224 ** |
|
|
crime |
67006711 |
11005394 |
6.089 |
1.48e-09 *** |
|
|
miracles |
35438694 |
11566582 |
3.064 |
0.00223 ** |
|
|
adventures |
-31072888 |
11447911 |
-2.714 |
0.00673 ** |
|
|
sentresidualspos |
-26597902 |
119400286 |
-0.223 |
0.82375 |
|
|
sentresidualsneg |
30751374 |
116170303 |
0.265 |
0.79127 |
Residual standard error: 79650000 on 1369 degrees of freedom
Multiple R-squared: 0.04477, Adjusted R-squared: 0.03988
F-statistic: 9.166 on 7 and 1369 DF, p-value: 4.125e-11
6. Discussion of results and hypotheses
As the linear regression model reflects, R-squared equals to 0.04477. That means that only 4% of all the dependence and correlation is explained through the suggested variables. This situation might take place due to many other factors influencing the gross of the movie. For example, celebrities' power, video effects or music sounds, etc. Each of these factors has its impact on the sales of the movie, that is why the share of text is only 4%.
Although this number is not as big as it should be (, the model shows relatively significant results, that are signed with “*” letters. Moreover, P-value, which is in most cases is less than 0.05 rejects zero hypotheses. So, the results are still valuable and can be relied on during prediction.
The experiment findings were quite surprising about topics, that was proposed in the beginning. The H1 states that there is a correlation between the topic of the text and the box office revenue; the regression model approved it thought some topics.
Relying on these results, we can conclude that topics have their own role to play in the process of getting the profit of the upcoming film. And based on its context, studios together with investors may predict the outcome of the movie, just looking at the trailers' scripts only.
Turning to the topics, it is interesting to note that the H1.1, suggesting that movies, which have a criminal context in their text, truly increase the total revenue of the movie. Having this information accepted, we can conclude that H1.1 is also approved. This information is valuable for the advertising agencies as well. If they add to their posters or trailers any reminding of the crime by using the terms such as "gun", "weapon", "player", "shoot" etc., the spectators may find the film or a product attractive, making sales go up.
However, it is important to mention, that the usage of these words must be done according to the main meaning of the product itself. In other words, if the film or any product is about ballet or daily routine, the terms as "gun" must be used in an appropriate way.
Another topic concerning "spying" is turned out to be a detrimental factor for movie sales. As the regression model has demonstrated, if the trailers do use the terms evolving some agents or missions, the movie might not be favorable for viewers. That is why it is recommended to take them off from the posts or make their amount close to zero.
The possible explanation of this phenomenon could be the preference of people, who were born in the 1990s. As ST Lyons et al. (2010) in their paper about millennial generation claims, the audience at the age of 22 to 30 tends to constantly change their preferences and interests, depending on the society.
The authors underline that these generations do want to follow something extraordinary, which is frequently out of popular trends. Given the fact that movies about agents were popular since the 1990s (Barza & Memari, 2014), the generation considered them as something traditional, putting them at the end of preferences. However, this possible explanation is not exact and needs to be explored deeper in the further potential researches.
Miracles, on the contrary, act as a positive factor for the trailers. Perhaps this is due to the fact that miracles, in total, attract people due to their unreality. As Polgar (1962) in his researches about human psychology said, a person is inclined to be interested in things, that do not exist in everyday life, for example, mummies, monsters or any other wonders. (Polgar, 1962) It is considered that miracles are usually associated as something new. And this association, as it is suggested is positively accepted by millennials. Therefore, trailers have such an effect on films and advertising in general.
Adventures being another considered topic showed a positive correlation with the box office revenue. Looking at the terms used in this theme, it can be seen that all of them are mainly related to some movement, for example: “plane”, “jump”, “ship”, “water”. In this case, the terms largely explain these positive results, since according to the research by Polgar (1962) about human's cognitive perception, a moving object attracts more attention than a fixed one. Consequently, advertisements and trailers, that have any dynamic pictures are favorably accepted by spectators, increasing the attractiveness of the trailer and upcoming film itself. (Polgar, 1962)
Trailers with drama and relationship content showed no correlation and insignificance in the regression model. This is another unexpected result, as it was initially assumed that people prefer films of this genre and text. The possible explanation of such development could be a small proportion of trailers with a given context or the terms used in this topic. As it is mentioned, sometimes the vocabulary plays a huge role in the process of determining the word into a specific topic. Yet, this could act as another subject to explore in the future.
One of the most surprising parts of the research concerns sentimental analysis, where none of the hypotheses about them have been confirmed. One of the possible explanations could be that words usually can have different meanings. For example, the word "weapon"; some people may associate this word with danger, others can think of it as an instrument or a gift. Even though machine learning tries to detect the words by their frequency in the sentence, this variable is considered to be week still.
Another possible explanation relies on the vocabulary used in the analysis. For example, the vocabulary applied for this paper categorizes the word "love" into the positive word, however, there were many cases, when this term was used in the negative mood.
That might be another reason for this situation happen. Yet, this situation may act as another pull for further studies about sentiments. For example, sentiments correlation with movies themselves or negative feedbacks' influence on the authority of motion studios.
To sum up the whole study results, there is a list of hypotheses with their statuses provided below:
1) Hypothesis 1 (approved - confirmed)
2) Hypothesis 1.1 (approved - confirmed)
3) Hypothesis 2 (rejected)
4) Hypothesis 2.1 (rejected)
As it is described, not all of the hypotheses have been confirmed. Some of them require more in-depth analysis to be properly explained, and some refer to studies that have already been done. In general, the results showed valuable numbers from which the appropriate conclusions can be drawn.
Conclusion
The advertising market has been growing up significantly since the rapid development of the film industry from the 1990s. (Basuroy et al., 2003) Movies are one of the most consumed products in the cultural or entertainment sphere, have become the main object for many investors and cinemas as well. (Algesheimer et al., 2010) The players in this market before making any investment were trying to answer the question, whether the film is successful. Referring to the emerged question, many researchers came up with a solution to create various models for predicting the success of upcoming films. Each of these models was different in a set of variables, data, and the method itself. Some of them used the text of the movies' scenarios, others evolved the celebrities' authority, there was also a model based on the number of likes put for the movie poster on Facebook. (Gopinath, Chintagunta, & Venkataraman, 2013) Despite the variety and effectiveness of these models, it is noteworthy that many of them used the data obtained after the film has been released. The purpose of this work is, on the contrary, to create a predictive model based on the trailer's features, using the data before the premiere date of the movie. Following this look, the main variable to the exam was decided to be a text or words used in trailers. Since the paper explores English words only, all the data and scripts have been filtered.
According to the results of the study, there are mainly 4 different themes that have an impact on the sales of the film. Depending on the context, these topics either can increase or decrease the box office revenue. That is why advertising companies together with motion studios should consider the context of their products by checking the terms used in the trailers.
Besides, the paper has analyzed a sentiment analysis by dividing words into negative and positive categories. It was found that the films did not have any connection with the presence of positive or negative words in the trailer. All the indexes and figures in the linear regression model were insignificant. Still, this approach might be useful in other fields, for example, the influence of negative words on the brand value or how advertising agencies cope with positive and negative feedbacks, etc.
Limitations and future directions. In general, the investors and cinemas should rely on the context of the trailers expressed through the topics rather than separate words. It is due to the fact that words may have different meanings depending on their position. This act as a limitation of the research, which might be the reason for other researches to be conducted.
One more limitation of the paper is the trailer with no words at all. In this situation, the provided model cannot be used properly, except for the case, when the general content of the trailer is explored. All in all, this point might be another occasion for further studies to be held. One of the possible researches could be the analysis of music sound in trailers, where the content of the video can be identified through the music vibration.
Although there are some limitations in this paper, the whole analysis reflected that texts in advertising (trailers) can be another significant factor for the success of the product, films in particular. Since there is a lack of literature devoted to the particular topic, I hope that this study will fill the gap, being very useful and incentive for other researches to enrich more insights in this field.
Reference list
1. Abdulkhayrov, M. (2012). Methods of a research of texts of works of Alisher Navoiy. Messenger of the Chelyabinsk State University, (12), 266.
2. Algesheimer, R., Borle, S., Dholakia, U. M., & Singh, S. S. (2010). The impact of customer community participation on customer behaviors: An empirical investigation. Marketing Science, 29(4), 756-769.
3. Banerjee, S. S., & Dholakia, R. R. (2008). Mobile advertising: does location based advertising work? International Journal of Mobile Marketing.
4. Barza, S., & Memari, M. (2014). Movie genre preference and culture. Procedia-Social and Behavioral Sciences, 98, 363-368.
5. Basuroy, S., Chatterjee, S., & Ravid, S. A. (2003). How Critical are Critical Reviews? The Box Office Effects of Film Critics, Star Power, and Budgets. Journal of Marketing, 67(4), 103-117. doi: 10.1509/jmkg.67.4.103.18692
6. Berger, J., Sorensen, A. T., & Rasmussen, S. J. (2010). Positive effects of negative publicity: When negative reviews increase sales. Marketing Science, 29(5), 815-827.
7. Burgess, J., & Green, J. (2018). YouTube: Online video and participatory culture. John Wiley & Sons.
8. Cho, K.-W., Bae, S.-K., & Woo, Y.-W. (2017). Analysis on Topic Trends and Topic Modeling of KSHSM Journal Papers using Text Mining. The Korean Journal of Health Service Management, 11(4), 213-224.
9. De Vany, A. S., & Walls, W. D. (2007). Estimating the Effects of Movie Piracy on Box-office Revenue. Review of Industrial Organization, 30(4), 291-301. doi: 10.1007/s11151-007-9141-0
10. DeCarlo, T. E., Laczniak, R. N., Motley, C. M., & Ramaswami, S. (2007). Influence of Image and Familiarity on Consumer Response to Negative Word-of-Mouth Communication About Retail Entities. Journal of Marketing Theory and Practice, 15(1), 41-51. doi: 10.2753/MTP1069-6679150103
11. Deci, E. L., & Ryan, R. M. (2000). The" what" and" why" of goal pursuits: Human needs and the self-determination of behavior. Psychological Inquiry, 11(4), 227-268.
12. Dhar, T., Sun, G., & Weinberg, C. B. (2012). The long-term box office performance of sequel movies. Marketing Letters, 23(1), 13-29. doi: 10.1007/s11002-011-9146-1
13. Efron, B. (1975). The efficiency of logistic regression compared to normal discriminant analysis. Journal of the American Statistical Association, 70(352), 892-898.
14. Eliashberg, J., Hui, S. K., & Zhang, Z. J. (2007). From Story Line to Box Office: A New Approach for Green-Lighting Movie Scripts. Management Science, 53(6), 881-893. doi: 10.1287/mnsc.1060.0668
15. Eliashberg, J., Jonker, J.-J., Sawhney, M. S., & Wierenga, B. (2000). MOVIEMOD: An Implementable Decision-Support System for Prerelease Market Evaluation of Motion Pictures. Marketing Science, 19(3), 226-243. doi: 10.1287/mksc.19.3.226.11796
16. Elliott, C., & Simmons, R. (2008). Determinants of UK Box Office Success: The Impact of Quality Signals. Review of Industrial Organization, 33(2), 93-111. doi: 10.1007/s11151-008-9181-0
17. Gopinath, S., Chintagunta, P. K., & Venkataraman, S. (2013). Blogs, Advertising, and Local-Market Movie Box Office Performance. Management Science, 59(12), 2635-2654. doi: 10.1287/mnsc.2013.1732
18. Hand, D., Keim, D., & Ng, R. (2002). Proceedings of the... ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Association for Computing Machinery.
19. Joshi, A. M., & Hanssens, D. M. (2009). Movie Advertising and the Stock Market Valuation of Studios: A Case of “Great Expectations?” Marketing Science, 28(2), 239-250. doi: 10.1287/mksc.1080.0392
20. Kaimann, D., & Pannicke, J. (2015). Movie success in a genre specific contest: Evidence from the US film industry. Ilmenau Economics Discussion Papers.
21. Karray, S., & Debernitz, L. (2017). The effectiveness of movie trailer advertising. International Journal of Advertising, 36(2), 368-392. doi: 10.1080/02650487.2015.1090521
22. Lash, M. T., & Zhao, K. (2016). Early Predictions of Movie Success: The Who, What, and When of Profitability. Journal of Management Information Systems, 33(3), 874-903. doi: 10.1080/07421222.2016.1243969
23. Le, T. R. G. (1991). Trailer.
24. Lee, K.-C. (2001). Home page advertising method.
25. Lee, S., & Choeh, J. Y. (2018). The interactive impact of online word-of-mouth and review helpfulness on box office revenue. Management Decision, 56(4), 849-866. doi: 10.1108/MD-06-2017-0561
26. Liaw, A., & Wiener, M. (2002). Classification and regression by randomForest. R News, 2(3), 18-22.
27. Madigan, J. (2015). Getting gamers: The psychology of video games and their impact on the people who play them. Rowman & Littlefield.
28. Nelson, R. A., & Glotfelty, R. (2012). Movie stars and box office revenues: an empirical analysis. Journal of Cultural Economics, 36(2), 141-166. doi: 10.1007/s10824-012-9159-5
29. Oh, S., Baek, H., & Ahn, J. (2017). Predictive value of video-sharing behavior: sharing of movie trailers and box-office revenue. Internet Research, 27(3), 691-708. doi: 10.1108/IntR-01-2016-0005
30. Polgar, S. (1962). Health and human behavior: areas of interest common to the social and medical sciences. Current Anthropology, 3(2), 159-205.
31. Posner, M. I., Petersen, S. E., Fox, P. T., & Raichle, M. E. (1988). Localization of cognitive operations in the human brain. Science, 240(4859), 1627-1631.
32. Predict IMDB score with data mining algorithms | Kaggle. (n.d.). Retrieved 24 May 2019, from https://www.kaggle.com/carolzhangdc/predict-imdb-score-with-data-mining-algorithms
33. ROI Formula, Calculation, and Examples of Return on Investment. (n.d.). Retrieved 24 May 2019, from Corporate Finance Institute website: https://corporatefinanceinstitute.com/resources/knowledge/finance/return-on-investment-roi-formula/
34. Smeaton, A. F., Lehane, B., O'Connor, N. E., Brady, C., & Craig, G. (2006). Automatically selecting shots for action movie trailers. 231-238. ACM.
35. Tabibnia, G., Lieberman, M. D., & Craske, M. G. (2008). The lasting effect of words on feelings: words may facilitate exposure effects to threatening images. Emotion, 8(3), 307.
36. Treme, J., & Craig, L. A. (2013). Celebrity star power: Do age and gender effects influence box office performance? Applied Economics Letters, 20(5), 440-445.
37. Dumler, A. A. (2018). Permskiy gosudarstvennyy natsional'nyy issledovatel'skiy universitet 614990, Rossiya, g. Perm', ul. Bukireva, 15, yasn@ psu. ru. 14.
38. Nikolenko, S. (n.d.). Kategorizatsiya tekstov i model' LDA. 52.
Appendix 1
Variables of dataset
Appendix 2
List of Stop words
|
i |
those |
into |
such |
|
|
me |
am |
through |
no |
|
|
my |
is |
during |
nor |
|
|
myself |
are |
before |
not |
|
|
we |
was |
after |
only |
|
|
our |
were |
above |
own |
|
|
ours |
be |
below |
same |
|
|
ourselves |
been |
to |
so |
|
|
you |
being |
from |
than |
|
|
your |
have |
up |
too |
|
|
yours |
has |
down |
very |
|
|
yourself |
had |
in |
s |
|
|
yourselves |
having |
out |
t |
|
|
he |
do |
on |
can |
|
|
him |
does |
off |
will |
|
|
his |
did |
over |
just |
|
|
himself |
doing |
under |
don |
|
|
she |
a |
again |
should |
|
|
her |
an |
further |
now |
|
|
hers |
the |
then |
||
|
herself |
and |
once |
||
|
it |
but |
here |
||
|
its |
if |
there |
||
|
itself |
or |
when |
||
|
they |
because |
where |
||
|
them |
as |
why |
||
|
their |
until |
how |
||
|
theirs |
while |
all |
||
|
themselves |
of |
any |
||
|
what |
at |
both |
||
|
which |
by |
each |
||
|
who |
for |
few |
||
|
whom |
with |
more |
||
|
this |
about |
most |
||
|
that |
against |
other |
||
|
these |
between |
some |
Размещено на Allbest.ru
...Подобные документы
Description of the structure of the airline and the structure of its subsystems. Analysis of the main activities of the airline, other goals. Building the “objective tree” of the airline. Description of the environmental features of the transport company.
курсовая работа [1,2 M], добавлен 03.03.2013Analysis of the peculiarities of the mobile applications market. The specifics of the process of mobile application development. Systematization of the main project management methodologies. Decision of the problems of use of the classical methodologies.
контрольная работа [1,4 M], добавлен 14.02.2016Critical literature review. Apparel industry overview: Porter’s Five Forces framework, PESTLE, competitors analysis, key success factors of the industry. Bershka’s business model. Integration-responsiveness framework. Critical evaluation of chosen issue.
контрольная работа [29,1 K], добавлен 04.10.2014Evaluation of urban public transport system in Indonesia, the possibility of its effective development. Analysis of influence factors by using the Ishikawa Cause and Effect diagram and also the use of Pareto analysis. Using business process reengineering.
контрольная работа [398,2 K], добавлен 21.04.2014История возникновения Lean Production, его инструменты. Понятие и сущность бережливого производства, его принципы, цели и задачи. Возможности и результаты применения концепции Lean на практике. Развитие методов и подходов к менеджменту производства.
реферат [330,2 K], добавлен 23.05.2014Selected aspects of stimulation of scientific thinking. Meta-skills. Methods of critical and creative thinking. Analysis of the decision-making methods without use of numerical values of probability (exemplificative of the investment projects).
аттестационная работа [196,7 K], добавлен 15.10.2008The concept of transnational companies. Finding ways to improve production efficiency. International money and capital markets. The difference between Eurodollar deposits and ordinary deposit in the United States. The budget in multinational companies.
курсовая работа [34,2 K], добавлен 13.04.2013Value and probability weighting function. Tournament games as special settings for a competition between individuals. Model: competitive environment, application of prospect theory. Experiment: design, conducting. Analysis of experiment results.
курсовая работа [1,9 M], добавлен 20.03.2016Formation of intercultural business communication, behavior management and communication style in multicultural companies in the internationalization and globalization of business. The study of the branch of the Swedish-Chinese company, based in Shanghai.
статья [16,2 K], добавлен 20.03.2013Searching for investor and interaction with him. Various problems in the project organization and their solutions: design, page-proof, programming, the choice of the performers. Features of the project and the results of its creation, monetization.
реферат [22,0 K], добавлен 14.02.2016Обобщение основных концепций "Lean production" в управлении офисом, как с отечественной, так и с зарубежной точки зрения. Система бережливого производства. Особенности методологии Хаммера. Управление цепочками поставок. Всеобщий уход за оборудованием.
курсовая работа [53,0 K], добавлен 16.10.2010History of development the world leader in the production of soft drinks company "Coca-Cola". Success factors of the company, its competitors on the world market, target audience. Description of the ongoing war company the Coca-Cola brand Pepsi.
контрольная работа [17,0 K], добавлен 27.05.2015Investigation of the subjective approach in optimization of real business process. Software development of subject-oriented business process management systems, their modeling and perfection. Implementing subject approach, analysis of practical results.
контрольная работа [18,6 K], добавлен 14.02.2016The main reasons for the use of virtual teams. Software development. Areas that are critical to the success of software projects, when they are designed with the use of virtual teams. A relatively small group of people with complementary skills.
реферат [16,4 K], добавлен 05.12.2012Эволюция автоматизированных систем управления предприятием. Возможности автоматизируемых систем управления торговыми предприятиями. Back-office и Front-office. Возможности ERP-систем для автоматизации торговли, интеграция с внешним торговым оборудованием.
курсовая работа [46,8 K], добавлен 01.11.2010Organizational legal form. Full-time workers and out of staff workers. SWOT analyze of the company. Ways of motivation of employees. The planned market share. Discount and advertizing. Potential buyers. Name and logo of the company, the Mission.
курсовая работа [1,7 M], добавлен 15.06.2013Проектирование совокупности взаимосвязанных бизнес-процессов предприятия как трудоемкий процесс по их моделированию. Модели прямого и обратного реинжиниринга в рамках стандарта моделирования бизнес-процессов IDEF0 на примере компании Destiny Development.
курсовая работа [918,5 K], добавлен 22.04.2014Major factors of success of managers. Effective achievement of the organizational purposes. Use of "emotional investigation". Providing support to employees. That is appeal charisma. Positive morale and recognition. Feedback of the head with workers.
презентация [1,8 M], добавлен 15.07.2012The primary goals and principles of asset management companies. The return of bank loans. Funds that are used as a working capital. Management perfection by material resources. Planning of purchases of necessary materials. Uses of modern warehouses.
реферат [14,4 K], добавлен 13.05.2013Company’s representative of small business. Development a project management system in the small business, considering its specifics and promoting its development. Specifics of project management. Problems and structure of the enterprises of business.
реферат [120,6 K], добавлен 14.02.2016
