메뉴 건너뛰기
Library Notice
Institutional Access
If you certify, you can access the articles for free.
Check out your institutions.
ex)Hankuk University, Nuri Motors
Log in Register Help KOR
Subject

A Study on the Predicting Audience Rating of TV Programs Based on Machine Learning Using Online Buzz
Recommendations
Search
Questions

온라인 버즈(Buzz)를 활용한 머신러닝 기반 TV프로그램 시청률 예측에 관한 연구

논문 기본 정보

Type
Academic journal
Author
Li, Jue Ming (성균관대학교) Kweon, Sang Hee (성균관대학교)
Journal
Cybercommunication Academic Society Journal of Cybercommunication Academic Society Vol.41 No.3 KCI Accredited Journals
Published
2024.9
Pages
5 - 42 (38page)
DOI
10.36494/JCAS.2024.09.41.3.5

Usage

cover
📌
Topic
📖
Background
🔬
Method
🏆
Result
A Study on the Predicting Audience Rating of TV Programs Based on Machine Learning Using Online Buzz
Ask AI
Recommendations
Search
Questions

Abstract· Keywords

Report Errors
This study investigates an artificial intelligence-based TV ratings prediction model using online buzz data, grounded in the theoretical background of social viewing. Recently, ‘Social Viewing’, which involves watching TV and talking about it through social media, is starting to attract new attention. The study develops a TV program ratings prediction model that supplements traditional methods, evaluates the performance of the ratings prediction model based on online characteristics, analyzes important features, and discusses categorization of TV program types based on ratings and online buzz levels.
The research method involved utilizing comprehensive datasets of 2,646 TV programs collected from the RACOI system. Correlation analyses between online buzz and ratings were conducted, and machine learning techniques such as decision trees, random forests, gradient boosting, and linear regression were used to predict numerical outcomes and calculate feature importance. Multidimensional scaling was employed to classify TV program types.
In the research results, a statistically significant correlation between online buzz and TV ratings was established, with artificial neural network models displaying superior predictive accuracy compared to the 11 models tested. Furthermore, it was determined that the number of online videos significantly impacts TV ratings. Finally, the study categorizes TV programs into four dimensions based on their ratings and online buzz. As a research implication, the study suggests new directions in academia by exploring the potential of social data and the applicability of integrated ratings models.. Moreover, it provides practical guidelines for the strategic planning, production, and marketing of TV programs.

Contents

요약
1. 들어가기
2. 이론적 배경
3. 연구 방법
4. 연구 결과
5. 결론 및 함의
참고문헌
ABSTRACT

References (0)

Add References

Recommendations

It is an article recommended by DBpia according to the article similarity. Check out the related articles!

Recently viewed articles

Comments(0)

0

Write first comments.

UCI(KEPA) : I410-151-25-02-091194552