A Predicting Model of TV Audience Rating Based on the Facebook

Cheng, Yu-Hsuan; Wu, Chenming; Ku, Tsun; Chen, Gwo-Dong

doi:10.1109/socialcom.2013.167

Cited by 11 publications

(7 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With the advent of new technologies, especially in data mining and machine learning, many studies apply the emerging techniques to the TV rating forecast problem. After 2000s, most studies focus on individual rating behavior while only a select few focus on social media such as Facebook [4] and Twitter [5,6] in order to forecast the TV ratings of a program or a channel. An objective of this study is to integrate data collected via the social media to the TV rating forecast problem in a successful manner.…”

Section: Related Workmentioning

confidence: 99%

“…Studies on TV rating forecast can be categorized into two groups based on the type of the data that is used to evaluate TV ratings: individual [7][8][9][10][11] and aggregated data of the all households' people-meter [3,4,[12][13][14][15][16] values. Meyer & Hyndman's work [7] is unique in the sense that it uses personalized attributes of the users, such as exact viewing times.…”

Section: Related Workmentioning

confidence: 99%

“…Another alternative categorization of the past studies is based on the objective of the forecast. The TV rating forecast can focus on the ratings of a channel [3,9,[12][13][14]16], a program [4,8,11,15], or an individual episode of a program [7,9].…”

Section: Related Workmentioning

confidence: 99%

“…[6] also showed that social media ratings based on twitter is not in direct correlation with actual TV ratings in Turkey due to the fact that users can interact with Twitter feeds before and after the air of a TV show rather than only during the air time. On the other hand, [4] find out that using Facebook posts has favorable results for forecasting the TV ratings of a program. The authors used 10 features which are obtained from both social media posts and TV companies.…”

Section: Related Workmentioning

confidence: 99%

See 3 more Smart Citations

Forecasting TV Ratings of Turkish Television Series Using a Two-Level Machine Learning Framework

2021

Turk J Elec Eng & Comp Sci

View full text Add to dashboard Cite

TV rating is a numeric estimate of the popularity of television programs. Forecasting TV ratings is considered an important asset for investment planning of media due to its potential of reducing the risks of future ventures. The aim of this study is to develop a machine learning model capable of efficiently forecasting the TV ratings of Turkish TV series in a practical manner. To this end, two prediction models were proposed for forecasting the TV ratings of television series, facilitating an extensive set of features. A contribution of this study is the inclusion of social media-based features using search trends around television series and exploration of the viability of using these features in place of temporal features.The study presents an extensive evaluation of the forecast performance of the proposed models. The performance of the proposed models were evaluated using a data collection composed of ratings and various attributes of series and their episodes aired at prime-time Turkish broadcast during 2014 and 2018. In the experiments, a theoretical forecast performance was first established with the inclusion of temporal features. Next, a set of practical models were proposed, replacing temporal attributes with social media-based attributes, relating to internet popularity and visibility of the series. The experiments show that, the proposed models achieve up to 1.65% error rate for the theoretical setting and 7.06% error rate for the practical setting.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

Forecasting TV Ratings of Turkish Television Series Using a Two-Level Machine Learning Framework

2021

Turk J Elec Eng & Comp Sci

View full text Add to dashboard Cite

show abstract

“…It is well known that watching television can influence people's behavior [1]- [3] but this impact cannot be measured by viewership figures. In reverse, some previous studies have aimed to predict TV viewership from user behavior [4], [5]. We wanted to understand the influence of television on the web; if the influence is strong, a viral effect may be expected.…”

Section: Introductionmentioning

confidence: 99%