Analysis of Social Value of TV Dramas Based on Audience Comments

Analysis of Social Value of TV Dramas Based on Audience Comments

Xinye Liu (Tianjin University, China), Xiaotong Zhang (Tianjin University, China), Tao Wang (Tianjin University, China), Kun Cheng (Tianjin University, China), Shangbing Jiao (Tianjin University, China), Diqing Liu (Tianjin University, China), Jia Su (Tianjin University, China) and Xiaoqian Wang (Tianjin University, China)
DOI: 10.4018/978-1-7998-0357-7.ch004

Abstract

This chapter analyzes the social value of the TV drama Entrepreneurial Age through the mining of the audience's comments, so as to provide reference for the TV drama producers in topic selection, casting, and script design. Design/methodology/approach: The research is based on a three-step approach including data crawling, two-dimension data tags, and the random forest algorithm design. Findings: This chapter finds that there are three factors related to demand of TV drama:1) the appearance and acting skill of actors; 2) the closeness between TV plays and real life; 3) whether the topic of TV plays has high attention. Value: Based on the big data of audience comments, this chapter explores the factors that influence the number of TV plays. It provides an important reference for TV drama producers on how to design the plot of TV drama, how to choose actors, and how to create topics.
Chapter Preview
Top

Introduction

Today, human society is entering the era of big data and it is affecting all fields of society. Especially, big data analysis is changing the TV dramas in essence.

In terms of the audience, with the popularity of the Internet, more and more people are watching on the mobile terminal instead of televisions. The audience’s online watching behavior forms a huge data source. Every click, search, and comments of the users will leave traces on the Internet. Audience’s comments have its social value. From the comments, the people’s attitude towards some popular phenomena and their preference for artistic expression can be shown. By analyzing the data, the TV dramas can be produced more specifically.

In terms of the producers of TV drama, in recent years, many platforms have tried to produce and broadcast homemade dramas and customized dramas. The essential difference between the traditional media and new platforms is that the latter adopt a data-driven program to make production, price and distribution decision. For example, Nexfilx analyzed the watching behavior of nearly 60 million registered users. The results showed that users who like BBC dramas, the director David Fincher and the actor Kevin Spacey have something in common. Therefore, House of Cards, which meet the three elements, came into being. Big data analysis is more detailed, more comprehensive and more advanced than traditional ratings survey in the aspect of audience analysis. It also can be applied in TV theme selection, topic setting, casting formation, distribution selection, marketing strategies and rating forecasting.

Connecting the above two aspects, the authors raise the following questions: What social value can we dig from the audience's comments on TV drama? How can we use that information to guide the production process of TV drama?

To solve the questions, the authors carry out this study. Based on the audience’ comments of the popular TV drama named Entrepreneurial Age, the authors expect to explore the social value behind it and provide the TV producer with reference to the subject selection, casting selection and script design. The authors plan to crawl the data of related websites and conduct deep data mining and text analysis. Then the authors will design an algorithm to analyze the users’ watching or click habits and their emotional polarity, reducing the blindness in theme selection, actor matching, shooting production and broadcast arrangement in TV drama production. Finally, the implications for practitioners and academia are discussed and conclusions drawn.

The authors collaborate in the following ways: Liu Xinyun and Jiao Shangbing are responsible for designing algorithms. Wang Tao and Cheng Kun are responsible for data mining and processing. Zhang Xiaotong, Liu Diqing and Wang Xiaoqian are responsible for the remaining working.

Complete Chapter List

Search this Book:
Reset