arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2105.01633cs.MMcs.CL
收藏

从持续情绪特征估计在线视频用户参与度

An Estimation of Online Video User Engagement from Features of Continuous Emotions

University of Augsburg(奥格斯堡大学);Imperial College(帝国理工学院)

Lukas Stappen, Alice Baird, Michelle Lienhart, Annalena Bätz, Björn Schuller

摘要:

众所周知,描绘情感和可信度可以增加视频内容的吸引力。然而,这些信号和在线用户参与之间的因果关系还没有得到很好的理解。这种有限的理解部分是由于情感注释数据的稀缺性以及表达用户在线参与的各种形式。在这篇文章中,我们利用了一个大型的YouTube评论视频数据集,其中包括ca。600个小时的维度唤醒,效价和可信度注释。我们研究了从这些信号中提取的特征,这些特征针对各种用户参与度指标,包括视图,喜欢/不喜欢比率以及评论的情绪。在此过程中,我们确定了单个功能的积极和消极影响,以及与用户参与度相关的每个维度中的可解释模式。我们的研究结果表明,较小的边界范围和波动的唤醒导致用户参与度的增加。此外,所提取的时间序列特征揭示了每个维度的显著(p<0.05)相关性,例如低于信号平均值的计数(唤醒)、峰值的数量(效价)和绝对能量(可信度)。由此,概述了旨在自动预测几个用户参与指标的方法的功能的有效组合。在用户参与度预测范例中,我们将所有功能与半自动(跨任务)和自动(特定于任务的)特征选择方法进行比较。这些选定的特征集似乎优于所有特征的使用,例如,使用所有特征实现每天1.55个喜欢(Lp/d)与效价的平均绝对误差;这通过半自动和自动选择分别提高到1.33和1.23 Lp/d(数据平均值为9.72 Lp/d,标准差为1.25)。28.75 Lp/d)。

英文摘要:

Portraying emotion and trustworthiness is known to increase the appeal of video content. However, the causal relationship between these signals and online user engagement is not well understood. This limited understanding is partly due to a scarcity in emotionally annotated data and the varied modalities which express user engagement online. In this contribution, we utilise a large dataset of YouTube review videos which includes ca. 600 hours of dimensional arousal, valence and trustworthiness annotations. We investigate features extracted from these signals against various user engagement indicators including views, like/dislike ratio, as well as the sentiment of comments. In doing so, we identify the positive and negative influences which single features have, as well as interpretable patterns in each dimension which relate to user engagement. Our results demonstrate that smaller boundary ranges and fluctuations for arousal lead to an increase in user engagement. Furthermore, the extracted time-series features reveal significant (p<0.05) correlations for each dimension, such as, count below signal mean (arousal), number of peaks (valence), and absolute energy (trustworthiness). From this, an effective combination of features is outlined for approaches aiming to automatically predict several user engagement indicators. In a user engagement prediction paradigm we compare all features against semi-automatic (cross-task), and automatic (task-specific) feature selection methods. These selected feature sets appear to outperform the usage of all features, e.g., using all features achieves 1.55 likes per day (Lp/d) mean absolute error from valence; this improves through semi-automatic and automatic selection to 1.33 and 1.23 Lp/d, respectively (data mean 9.72 Lp/d with a std. 28.75 Lp/d).

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑