Prediction of User Ratings of Oral Presentations using Label Relations
Prediction of User Ratings of Oral Presentations using Label Relations
复制标题
DOI：
10.1145/2813524.2813533
复制
发表时间：
2015-10
期刊：
影响因子：
--
通讯作者：
T. Yamasaki;Yusuke Fukushima;Ryosuke Furuta;Litian Sun;K. Aizawa;Danushka Bollegala
中科院分区：
文献类型：
--
作者：
T. Yamasaki;Yusuke Fukushima;Ryosuke Furuta;Litian Sun;K. Aizawa;Danushka Bollegala
预测用户对视频谈话的印象是推荐任务的重要步骤。我们提出了一种方法来准确地预测多个印象相关的用户评级为一个给定的视频通话。我们的建议考虑（a）多模态特征，包括语言以及声学特征，（B）不同用户评级（标签）之间的相关性，以及（c）不同特征类型之间的相关性。特别是，所提出的方法在一个单一的马尔可夫随机场（MRF）内的标签和特征相关性建模，并联合优化标签分配问题，以获得一个一致的和多组标签为给定的视频。我们使用14个不同标签的1，646个TED演讲视频来训练和评估所提出的方法。在该数据集上的实验结果表明，该方法获得了93.3%的统计显著的宏观平均准确率，优于几个竞争对手的基线方法。
Predicting the users' impressions on a video talk is an important step for recommendation tasks. We propose a method to accurately predict multiple impression-related user ratings for a given video talk. Our proposal considers (a) multimodal features including linguistic as well as acoustic features, (b) correlations between different user ratings (labels), and (c) correlations between different feature types. In particular, the proposed method models both label and feature correlations within a single Markov random field (MRF), and jointly optimizes the label assignment problem to obtain a consistent and multiple set of labels for a given video. We train and evaluate the proposed method using a collection of 1,646 TED talk videos for 14 different tags. Experimental results on this dataset show that the proposed method obtains a statistically significant macro-average accuracy of 93.3%, outperforming several competitive baseline methods.