A Weight-Sharing Gaussian Process Model Using Web-Based Information for Audience Rating Prediction - Technologies and Applications of Artificial Intelligence - page 206

6 Conclusion

In this paper, we present a weight-sharing Gaussian process model for the TV au-
dience rating prediction problem. Also, we extract three types of web-based features
for this task, namely Facebook Fan Page statistics, opinion polarities, and Google
Trends. A series of experiments on a dataset consisting of four popular Chinese dra-
mas are made to investigate the usefulness of these features. With the weight-sharing
kernel applied, the proposed model yields lower error rates than the other baseline
models in predicting the audience ratings.

Acknowledgement. This study is conducted under the "Social Intelligence Analysis
Service Platform" of the Institute for Information Industry which is subsidized by the
Ministry of Economy Affairs of the Republic of China.

References

1. Asur, S., Huberman, B.A.: Predicting the future with social media. In: Proceedings of the
2010 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent
Technology, WI-IAT 2010, vol. 01, pp. 492-499. IEEE Computer Society, Washington,
DC (2010), http://dx.doi.org/10.1109/WI-IAT.2010.63
2. Bollerslev, T.: Generalized autoregressive conditional heteroskedasticity. Journal of
Econometrics 31(3), 307-327 (1986)
3. Cawley, G.C., Talbot, N.L.: On over-fitting in model selection and subsequent selection
bias in performance evaluation. The Journal of Machine Learning Research 11, 2079-2107
(2010), http://dl.acm.org/citation.cfm?id=1756006.1859921
4. Cheng, Y.H., Wu, C.M., Ku, T., Chen, G.D.: A predicting model of tv audience rating
based on the facebook. In: International Conference on Social Computing (SocialCom),
pp. 1034-1037. IEEE (2013)
5. Danaher, P., Dagger, T.: Using a nested logit model to forecast television ratings.
International Journal of Forecasting 28(3), 607-622 (2012)
6. Danaher, P.J., Dagger, T.S., Smith, M.S.: Forecasting television ratings. International
Journal of Forecasting 27(4), 1215-1240 (2011)
7. Fan, R.E., Chang, K.W., Hsieh, C.J., Wang, X.R., Lin, C.J.: Liblinear: A library for large
linear classification. The Journal of Machine Learning Research 9, 1871-1874 (2008),
http://dl.acm.org/citation.cfm?id=1390681.1442794
8. Hsieh, W.T., Chou, S.C.T., Cheng, Y.H., Wu, C.M.: Predicting tv audience rating with so-
cial media. In: Proceedings of the IJCNLP 2013 Workshop on Natural Language
Processing for Social Media (SocialNLP), pp. 1-5. Asian Federation of Natural Language
Processing, Nagoya (2013), http://www.aclweb.org/anthology/W13-4201
9. Luxhøj, J.T., Riis, J.O., Stensballe, B.: A hybrid econometric-neural network modeling
approach for sales forecasting. International Journal of Production Economics 43(2),
175-192 (1996)
10. Murray, I., Adams, R.P.: Slice sampling covariance hyperparameters of latent gaussian
models. In: Advances in Neural Information Processing Systems, pp. 1723-1731 (2010)
11. Neal, R.M.: Bayesian Learning for Neural Networks. Springer-Verlag New York, Inc.,
Secaucus (1996)