Using Academy Awards to Predict Success of Bollywood Movies using Machine Learning Algorithms

Masih, Salman; Ihsan, Imran

doi:10.14569/ijacsa.2019.0100257

Cited by 9 publications

(9 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Lu and Xing (2019) use conjoint analysis to predict box office success. Focusing on Bollywood movies, Masih and Ihsan (2019) use Academy Awards to understand determinants of successful movies. Chen, Chen, and Weinberg (2013) consider how the types of movie releases impact on their box offices.…”

Section: Related Literaturementioning

confidence: 99%

Improving productivity in Hollywood with data science: Using emotional arcs of movies to drive product and service innovation in entertainment industries

Vecchio

Kharlamov

Parry

et al. 2020

Journal of the Operational Research Society

View full text Add to dashboard Cite

Improving productivity in the entertainment industry is a very challenging task as it heavily depends on generating attractive content for the consumers. The consumer-centric design (putting the consumers at the centre of the content development and production) focuses on ways in which businesses can design customized services and products which accurately reflect consumer preferences. We propose a new framework which allows to use data science to optimize content-generation in entertainment and test this framework for the motion picture industry. We use the natural language processing methodology combined with econometric analysis to explore whether and to what extent emotions shape consumer preferences for media and entertainment content, which, in turn, affect revenue streams. By analyzing 6,174 movie scripts, we generate the emotional trajectory of each motion picture. We then combine the obtained mappings into clusters which represent groupings of consumer emotional journeys. These clusters are then plugged into an econometric model to predict overall success parameters of the movies including box office revenues, viewer satisfaction levels (captured by IMDb ratings), awards, as well as the number of viewers' and critics' reviews. We find that emotional arcs in movies can be partitioned into 6 basic shapes. The highest box offices are associated with the Man in a Hole shape which is characterized by an emotional fall followed by an emotional rise. This U-shaped emotional arc results in financially successful movies irrespective of genre and production budget. Implications of this analysis for generating on-demand content and improving productivity in entertainment industries are discussed.

show abstract

Section: Related Literaturementioning

confidence: 99%

Improving productivity in Hollywood with data science: Using emotional arcs of movies to drive product and service innovation in entertainment industries

Vecchio

Kharlamov

Parry

et al. 2020

Journal of the Operational Research Society

View full text Add to dashboard Cite

show abstract

“…Bae and Kim (2019) investigated relationship between movie titles and box office success. Masih and Ihsan (2019) analyzed effects of genre, leading actor, director, awards and budget on a movie's box office revenue. Steininger and Gatzemeier (2019) studied impacts of the overall affective response, the need to re-experience on success of new music.…”

Section: Methods To Mine Attribute Relationship Patternmentioning

confidence: 99%

“…First type of Table 3 shows that movies or scripts are used for similarity calculation. Commercial and artistic star power Genre, age limit, country of origin, sequel, online ratings, box office performance, holdback Lee and Choeh (2018) Volume of reviews, valence of reviews, depth of reviews, review helpfulness Bae and Kim (2019) Movie titles Masih and Ihsan (2019) Genre, leading actor, director, Zee cine awards, IIFA awards, budget Steininger and Gatzemeier (2019) Overall affective response, the need to re-experience Nam and Kim (2020) Genre, awareness of IP, name value of publishers, monetization option, preregistration, seasonal release, TV advertisements and media coverage, official online forums, online videos, platform ratings, platform's market power Second type of Table 3 shows that user data is used for similarity calculation. Barbosu (2016) identified similarity between movies based on users' rental data.…”

Section: Methods To Measure Similaritymentioning

confidence: 99%

“…This attribute relationship pattern, consisting of product attributes associated and association relationships among attributes, may reflect the characteristics of consumer demand. Extant studies have focused on impacts of such attributes on the TSV of EPSLC (Karniouchina, 2011; Nelson and Glotfelty, 2012; Hofmann et al , 2017; Kim and Kim, 2017; Lee and Choeh, 2018; Bae and Kim, 2019; Masih and Ihsan, 2019; Steininger and Gatzemeier, 2019; Nam and Kim, 2020). However, no study has attempted to mine attribute relationship patterns of products with different TSV intervals.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Predicting total sales volume interval of an experiential product with short life cycle before production: similarity comparison in attribute relationship patterns

Tang

Wang

Cui³

et al. 2021

View full text Add to dashboard Cite

PurposeBecause of short life cycle and fluctuating greatly in total sales volumes (TSV), it is difficult to accumulate enough sales data and mine an attribute set reflecting the common needs of all consumers for a kind of experiential product with short life cycle (EPSLC). Methods for predicting TSV of long-life-cycle products may not be suitable for EPSLC. Furthermore, point prediction cannot obtain satisfactory prediction results because information available before production is inadequate. Thus, this paper aims at proposing and verifying a novel interval prediction method (IPM).Design/methodology/approachBecause interval prediction may satisfy requirements of preproduction investment decision-making, interval prediction was adopted, and then the prediction difficult was converted into a classification problem. The classification was designed by comparing similarities in attribute relationship patterns between a new EPSLC and existing product groups. The product introduction may be written or obtained before production and thus was designed as primary source information. IPM was verified by using data of crime movies released in China from 2013 to 2017.FindingsThe IPM is valid, which uses product introduction as input, classifies existing products into three groups with different TSV intervals, mines attribute relationship patterns using content and association analyses and compares similarities in attribute relationship patterns – to predict TSV interval of a new EPSLC before production.Originality/valueDifferent from other studies, the IPM uses product introduction to mine attribute relationship patterns and compares similarities in attribute relationship patterns to predict the interval values. It has a strong applicability in data content and structure and may realize rolling prediction.

show abstract

“…Due to the diverse tastes of the audiences, focusing solely on a few aspects of a film, such as its genre, casting, and stars, may not be sufficient. A film's popularity is influenced by both conventional and unconventional elements, including the director, well-known actors/actresses, genre, and budget [2]. Nonconventional factors include number of people that watched the movie clips on YouTube, likes on social media, and number of fans following the movie.…”

Section: Open Accessmentioning

confidence: 99%

Machine Learning Methods for Predicting the Popularity of Movies

Oyewola¹,

Dada²

2022

AIS

View full text Add to dashboard Cite

The movie industry has grown into a several billion-dollar enterprise, and there is now a ton of information online about it. Numerous machine learning techniques have been created by academics and can produce effective classification models. In this study, different machine learning classification techniques are applied to our own movie dataset for multiclass classification. This paper's main objective is to compare the effectiveness of various machine learning techniques. This study examined five methods: Multinomial Logistic Regression (MLR), Support Vector Machine (SVM), Bagging (BAG), Naive Bayes (NBS) and K-Nearest Neighbor (KNN), while noise was removed using All K-Edited Nearest Neighbors (AENN). These techniques all utilize previous IMDb dataset to predict a movie's net profit value. The algorithms predict the profit at the box office for each of these five techniques. Based on the dataset used in this paper, which consists of 5043 rows and 14 columns of movies, this study evaluates the performance of all seven machine learning techniques. Bagging outperformed other machine learning techniques with a 99.56% accuracy rate.

show abstract

Using Academy Awards to Predict Success of Bollywood Movies using Machine Learning Algorithms

Cited by 9 publications

References 15 publications

Improving productivity in Hollywood with data science: Using emotional arcs of movies to drive product and service innovation in entertainment industries

Improving productivity in Hollywood with data science: Using emotional arcs of movies to drive product and service innovation in entertainment industries

Predicting total sales volume interval of an experiential product with short life cycle before production: similarity comparison in attribute relationship patterns

Machine Learning Methods for Predicting the Popularity of Movies

Contact Info

Product

Resources

About