• Proceedings of the Korean Operations and Management Science Society Conference
• /
• /
• pp.414-421
• /
• 2005

시청률은 각 방송사의 주요 수입원인 광고비 책정의 중요한 변수이다. 따라서 프로그램 편성자(Program Planner)는 경쟁 방송사의 편성을 고려한 시청률 최대화 전략을 수립하려 하며, 시청률 예측 모델을 사용하여 그 목적을 달성할 수 있다. 나아가 시청률 예측모델이 정확할수록 현재의 임의적인 광고비 책정 방식보다 정확한 광고비의 가격 책정이 가능해져 보다 합리적인 광고 및 미디어 시장 환경을 성립할 수 있다. 본 연구에서는 최근의 국내 TV 시청률 자료를 이용하여 국내 공중파 방송에 대한 시청률 예측 모델을 성립하고, 이를 이용한 시청률 최대화 전략을 제시한다.

• The Korean Journal of Applied Statistics
• /
• v.28 no.5
• /
• pp.933-949
• /
• 2015

Audience rating competition in the domestic drama market has increased recently due to the introduction of commercial broadcasting and diversification of channels. There is now a need for thorough studies and analysis on audience rating. Especially, a drama rating is an important measure to estimate advertisement costs for producers and advertisers. In this paper, we study the drama rating prediction models using various data mining techniques such as linear regression, LASSO regression, random forest, and gradient boosting. The analysis results show that initial drama ratings are affected by structural elements such as broadcasting station and broadcasting time. Average drama ratings are also influenced by earlier public opinion such as the number of internet searches about the drama.

• Proceedings of the Korea Contents Association Conference
• /
• /
• pp.127-128
• /
• 2019

최근 TV 드라마의 장르 혼합 현상이 빈번하게 일어나고 있다. 현상의 원인으로 매번 비슷한 소재의 드라마에 익숙해져 버린 시청자들이 새로운 것을 원하게 된 것이다. 2017년 종영한 드라마 "쓸쓸하고 찬란하신(神)-도깨비"의 시청률은 성공적인 드라마로 평가되며, 더불어 그 해 발매된 드라마 OST까지 높은 순위를 기록함으로써 시청률과 드라마 OST의 상관관계에 대한 연구의 필요성을 인지하게 되었다. 연구 결과 첫 번째, 초반부 시청률과 OST 순위는 비례적이지 않다. 두 번째는 시청률이 높아지는 후반부로 갈수록 OST의 삽입 횟수가 증가했다. 마지막으로 드라마 장면에서 갈등의 최고조에 삽입된 곡은 시청률과 사용횟수에 상관없이 높은 순위를 차지했다.

• The Journal of the Korea Contents Association
• /
• v.14 no.4
• /
• pp.379-388
• /
• 2014

This study analyzed the status of Korean professional baseball as TV contents utilizing ratings. For the purpose of the study, Korea professional baseball's relative status to other genres though ratings is investigated. For this study, ratings per minute for the whole cable TV channel viewer ratings in 2010 were analyzed, and the following is the result of comparing and analyzing ratings per genre and channel of cable TV. Among 11 genres, drama showed the highest rating, and entertainment, movies, kids, news/reports, sports, music, etc followed. Drama and entertaining channels showed the highest ratings and sports did not show any high ranking. However, when analyzing times for broadcasting Korean professional baseball separately, Korean professional baseball in both genre and channel showed the highest r ratings and it was significant statistically. Thus, it is considered that Korean professional baseball is the most valuable contents for the related cable TV times.

• The Journal of the Korea Contents Association
• /
• v.18 no.8
• /
• pp.315-325
• /
• 2018

The purpose of this study is to search the correlation between real-time viewing and OTT VOD usage. The study is based on the ratings and VOD download data, collected from TNmS and pooq. And this study focused on the ratings, 2049 ratings, OTT VOD download over the past 7 days, OTT VOD download over the past 30 days. The results showed that there were positive correlation in all genres(drama, entertainment, current affairs). First, there was a correlation between ratings and OTT VOD download over the past 7 days, between 2049 ratings and OTT VOD download over the past 7 days. Next, there was a correlation between ratings and OTT VOD download over the past 30 days, between 2049 ratings and OTT VOD download over the past 30 days. Finally, there was somewhat different among rankings of the ratings and VOD download.

• Proceedings of the Korea Contents Association Conference
• /
• /
• pp.113-114
• /
• 2019

불확실성이 큰 콘텐츠 산업의 특성상 방송 콘텐츠는 막대한 투자에 비해 그 효과 예측이 매우 어려우며 아직까지 출연진과 제작진에 대한 합리적인 평가지표도 존재하지 않는다. 방송용 드라마의 경쟁력을 평가하는 수단으로 현재까지 가장 유용한 지표는 시청률이다. 비록 스마트폰과 같은 매체를 통한 시청이 늘어남에 따라 TV 시청률의 절대 수치는 지속적으로 감소하고 있지만 TV 시청률을 대체할 만한 유용한 지표는 아직까지 없다. 본 연구에서는 방송용 드라마에 참여하는 인적자원의 평가지표와 시청률의 비교 우위를 활용하여 드라마의 흥행성을 과학적으로 예측하려고 한다.

• The Korean Journal of Applied Statistics
• /
• v.30 no.6
• /
• pp.809-825
• /
• 2017

The number of TV entertainment shows is increasing. Competition among programs in the entertainment market is intensifying since cable channels air many entertainment TV shows. There is now a need for research on program ratings and the number of episodes. This study presents predictive models for entertainment TV show ratings and number of episodes. We use various data mining techniques such as linear regression, logistic regression, LASSO, random forests, gradient boosting, and support vector machine. The analysis results show that the average program ratings before the first broadcast is affected by broadcasting company, average ratings of the previous season, starting year and number of articles. The average program ratings after the first broadcast is influenced by the rating of the first broadcast, broadcasting company and program type. We also found that the predicted average ratings, starting year, type and broadcasting company are important variables in predicting of the number of episodes.

• The Journal of the Korea Contents Association
• /
• v.8 no.9
• /
• pp.66-73
• /
• 2008

Under the changing circumstances of broadcasting, this study aims at the corelation of television drama's rating and television image production techniques, analyzing TV image production techniques and TV rating of drama, the highest rating genre. For this research, 6 dramas were selected as samples except the dramas about history and violence on the basis of the TNS media korea's top 100 of the year 2007. This study analyzed camerawork, shot size, shot duration and scene duration with the contents of replay and manuscript viewing of broadcasting companys' homepages. As the result of the analysis of corelation, TV rating is inverse proportionate to multiple camerawork and shot average duration with a very close relationship, showing no relationship with other variables. The result of this study shows that multiple cameraworks and long durated shots should be avoided for higher TV rating.

• The Journal of the Korea Contents Association
• /
• v.10 no.3
• /
• pp.157-165
• /
• 2010

As the result of correlation, the viewing rate of terrestrial broadcasting programs has a little bit affect on online VOD use. In addition, WOM(word of mouth) and online referral importantly influences to the picking with online VOD drama. The great popularity of main actors on drama affect a little bit the viewing of VOD drama but doesn't perfectly affect on it. However, the drama which is performed by great popular actors has positive affect on VOD use. This study result shows that the using of video depends on the effect of WOM, referral and commercial. The casting of a great popular actors plays role of the safeguard which affects viewing rate and add-value. That means the casting of a great popular actors doesn't connect with the success of release but the tool of defense from loss of profit.

• 한국정보기술학회논문지
• /
• v.15 no.1
• /
• pp.1-10
• /
• 2017

The prediction and factor analysis of terrestrial television soap opera ratings has become the broadcasting station's, producer's and advertiser's center of attention. However, the prediction of average ratings carries a risk regarding propriety due to the degree of perfection in works that should be considered. Therefore, this paper suggests a model for predicting the ratings for the first installment of terrestrial television soap operas as an indicator of judging the average ratings, and grasps a factor having an effect on the prediction of the ratings. In order to predict the ratings for the first installment, a model was created by using data mining techniques such as multiple linear regression analysis and decision trees (CART, random forest). The model using multiple regression analysis showed the best predictive power among three methods. As a result of the analysis, it was verified that structural factors such as the 25% ratings for the second half of a previous soap opera, the broadcasting station and day of the week when the soap opera was broadcast, and human factors such as producers, writers, actors and actresses had an effect on the ratings for the first installment. It is expected that the results of this study can be usefully utilized by broadcasting stations, producers and advertisers in making decisions.