ABSTRACT
In the new era of the rapid development of the film and television industry, audience rating, as an important indicator for evaluating film and television works, and an important reference for program production, arrangement, adjustment, plays a significant role in the film and television industry. Therefore, it is necessary to predict the audience rating of TV series to assist the production and arrangement of TV series. This paper selects relevant information about popular TV series in 2019 to analyze the influences of six factors, including broadcast time period, score on Douban.com, main actors, directors, and broadcasting platform, on TV series ratings through two different decision tree models. On this basis, this paper compares the experimental results of the two models through many experiments, and chooses ID3 decision tree algorithm as the prediction model of TV series ratings. The results show that the prediction model constructed in this paper has a good effect, and the accuracy rate can reach 84.05%, which can be used to predict TV series audience rating.
- Wei Du, Xingsheng Dong.TV series 2019: Recorded TV series shrank by 22%, the total investment hit a new low in nearly 5 years, Economic News Daily.Google Scholar
- Guishu Ji, Peiling Chen, Hang Song. Research on decision tree classification algorithm. Science Mosaic. (2007(1):9-12).Google Scholar
- Mengmeng Cai, Weiwei Zhang, Honglin Wang. Overview of Data Mining in the era of Big data. Value Engineering)2019:155-157(Google Scholar
- Xin Tian. Summary of decision tree algorithm. Management (2017(1):36)Google Scholar
- Yuanyuan Shen, Jinwen Wu, Xindong Liu. Rural informatization level measurement Model based on CART decision tree regression. Science and Technology Management Research. (2020(14):92-98).Google Scholar
- Qiang He. Analysis on the construction of marketization operation Mode of TV Series audience rating forecast. Chinese cable TV. (2019(1): 93-95)Google Scholar
Recommendations
ShapeShifting TV: interactive screen media narratives
This paper presents a paradigm, called ShapeShifting TV, for the realisation of interactive TV narratives or, more generally, of interactive screen-media narratives. These are productions whose narrations respond on the fly (i.e. in real time) to ...
Interactive TV narratives: Opportunities, progress, and challenges
This article is motivated by the question whether television should do more than simply offer interactive services alongside (and separately from) traditional linear programs, in the context of its dominance being seriously challenged and threatened by ...
An improved ridge regression algorithm and its application in predicting TV ratings
Ridge regression is a biased estimated regressive method, which is traditionally used in collinearity data analysis. It is actually a modified Least Square method, which gains more rational and reliable regression coefficient by giving up the ...
Comments