Towards SMP Challenge: Stacking of Diverse Models for Social Image Popularity Prediction

	Towards SMP Challenge: Stacking of Diverse Models for Social Image Popularity Prediction
	Xiaowen Huang; Yuqi Gao; Quan Fang; Sang JT(桑基韬); Changsheng Xu
	2017
会议名称	ACM Multimedia
会议录名称	ACM Multimedia
期号	1
页码	1895-1900
会议日期	2017
会议地点	Mountain View, California, United States
摘要	Popularity prediction on social media has attracted extensive attention nowadays due to its widespread applications, such as online marketing and economical trends. In this paper, we describe a solution of our team CASIA-NLPR-MMC for Social Media Prediction (SMP) challenge. This challenge is designed to predict the popularity of social media posts. We present a stacking framework by combining a diverse set of models to predict the popularity of images on Flickr using user-centered, image content and image context features. Several individual models are employed for scoring popularity of an image at earlier stage, and then a stacking model of Support Vector Regression (SVR) is utilized to train a meta model of different individual models trained beforehand. The Spearman’s Rho of this Stacking model is 0.88 and the mean absolute error is about 0.75 on our test set. On the official final-released test set, the Spearman’s Rho is 0.7927 and mean absolute error is about 1.1783. The results on provided dataset demonstrate the effectiveness of our proposed approach for image popularity prediction.
关键词	Popularity Prediction Social Media Image Flickr
文献类型	会议论文
条目标识符	http://ir.ia.ac.cn/handle/173211/17722
专题	多模态人工智能系统全国重点实验室_多媒体计算
推荐引用方式 GB/T 7714	Xiaowen Huang,Yuqi Gao,Quan Fang,et al. Towards SMP Challenge: Stacking of Diverse Models for Social Image Popularity Prediction[C],2017:1895-1900.

条目包含的文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
p1895-huang.pdf（2327KB）	会议论文		开放获取	CC BY-NC-SA	浏览