Busranur Akgul, Tayfun Kucukyilmaz

Forecasting TV ratings of Turkish television series using a two-level machine learning framework

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.

PDF

___

[1] Senturk R. Televizyon dizilerinin kesfi, turk televizyon dizileri efsanesi ve gercekler. Istanbul, TR: Kaknüs İletişim, 2018 (in Turkish).
[2] Tekelioglu O. Televizyon halleri: dizi dizi Turkiye. Istanbul, TR: Habitus Yayincilik, 2017 (in Turkish).
[3] Danaher P, Dagger T. Using a nested logit model to forecast television ratings. International Journal of Forecasting 2012; 28 (3): 607–622. doi:10.1016/j.ijforecast.2012.02.008
[4] Cheng YH, Wu CM, Ku T, Chen GD. A predicting model of TV audience rating based on the Facebook. In: 2013 International Conference on Social Computing; Alexandria, VA, USA; 2013. pp. 1034–1037. doi: 10.1109/SocialCom.2013.167
[5] Sommerdijk B, Sanders E, van den Bosch A. Can tweets predict tv ratings? In: Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16); Portoroz, Slovenia; 2016. pp. 2965– 2970.
[6] Krık AM, Domaç A. Sosyal medya üzerinden televizyon reyting olcumlerinin analizi: Twitter ornegi. Akademik Sosyal Araştırmalar Dergisi 2016; 1 (5): 414–430 (in Turkish).
[7] Meyer D, Hyndman RJ. The accuracy of television network rating forecasts: The effects of data aggregation and alternative models. Model Assisted Statistics and Applications 2005; 1 (3): 147–155.
[8] Huang HL, Lee HC, Shu LS, Lai SC, Tsai TM et al. Predicting television ratings and its application to Taiwan cable TV channels. In: 2nd International Symposium on Computer, Communication, Control and Automation. Atlantis Press; 2015. pp. 189–193.doi:10.2991/3ca-13.2013.48
[9] Pagano R, Quadrana M, Cremonesi P, Bittanti S, Formwentin S et al. Prediction of tv ratings with dynamic models. In: ACM Workshop on Recommendation Systems for Television and Online Video (RecSysTV’15); Vienna, Austria; 2015.
[10] Poslodova A. Recommendation system for next generation of smart TV. MS, Griffith University, Queensland, Australia, 2017.
[11] Song L, Shi Y, Tso GKF, Lo HP (2021). Forecasting week-to-week television ratings using reduced-form and structural dynamic models. International Journal of Forecasting 2021; 37 (1): 302–321.
[12] Danaher PJ, Dagger TS, Smith MS. Forecasting television ratings. International Journal of Forecasting 2011; 27 (4): 1215–1240. doi:10.1016/j.ijforecast.2010.08.002
[13] Nan M, Patrick W, Qin H, Wenjia L, Ying Z et al. Prediction of television audience rating based on Fuzzy Cognitive Maps with Forward Stepwise Regression. International Journal of Pattern Recognition and Artificial Intelligence. 2017; 31 (7): 1–13. doi: 10.1142/S0218001417500203
[14] Sereday S, Cui J. Using machine learning to predict future tv ratings. Neilsen Journal of Measurement. 2017; 17 (1): 3–12.
[15] Nan M, Sicheng Z, Zhen S, Xiuping W, Yun Z. An improved ridge regression algorithm and its application in predicting TV ratings. Multimedia Tools and Applications 2019; 78(1): 525–536. doi: 10.1007/s11042-017-5250-4
[16] Wang L. Forecast Model of TV Show Rating Based on Convolutional Neural Network. Complexity, 2021. doi:10.1155/2021/6694538
[17] Nixon L. Predicting your future audience’s popular topics to optimize TV content marketing success. In: Proceedings of the 2nd International Workshop on AI for Smart TV Content Production, Access and Delivery. Seattle, WA, USA; 2020.
[18] Hunter III SD, Chinta R, Smith S, Shamim A, Bawazir A. Moneyball for tv: A model for forecasting the audience of new dramatic television series. Studies in Media and Communication 2016; 4 (2): 13–22.
[19] Han JPJ, Kamber M. Data mining: concepts and techniques. Waltham, MA, USA: Elsevier, 2011.
[20] Friedman J, Hastie T, Tibshirani R. The elements of statistical learning. New York, NY, USA: Springer series in statistics, 2001.
[21] Zhang T. Adaptive forward-backward greedy algorithm for sparse learning with linear models. Advances in Neural Information Processing Systems 2009; 1 (1): 1921–1928.
[22] Gelman A, Jakulin A, Pittau MG, Su YS. A weakly informative default prior distribution for logistic and other regression models. The Annals of Applied Statistics 2008; 2 (4): 1360–1383.
[23] Quinlan JR. Induction of decision trees. Machine Learning 1986; 1 (1): 81–106.
[24] Nelder J,Wedderburn R. Generalized linear models. Journal of the Royal Statistical Society 1972; 135 (3): 370–384. doi:10.2307/2344614
[25] Venables WN, Ripley BD. Modern Applied Statistics with S-Plus. New York, NY, USA: Springer-Verlag, 2002.
[26] Breiman L. Random forests. Machine Learning 2001; 45 (1): 5–32.
[27] Platt J. Sequential minimal optimization: A fast algorithm for training support vector machines. Microsoft 1998.