论文标题
预测活动探索社会影响
Predicting event attendance exploring social influence
论文作者
论文摘要
预测人们参与现实世界事件的问题受到了极大的关注，因为它为人类行为分析和与事件相关的广告提供了宝贵的见解。今天，社交网络（例如Twitter）广泛反映了人们与朋友讨论他们的兴趣的大型流行活动。活动参与者通常会刺激朋友加入活动，从而传播网络中的社会影响力。在本文中，我们建议建模朋友对活动出席的社会影响。除了社会群体的结构以外，我们考虑了非秘密的帖子，以推断用户的出勤率。为了利用网络拓扑的信息，我们应用了一些最新的图形嵌入技术，例如Node2Vec，Harp和Poincar`E。我们描述了设计特征空间并将其馈送到神经网络之后的方法。性能评估是使用两个大型音乐节数据集进行的，即Vfestival和Creamfields。实验结果表明，我们的分类器的表现优于最先进的基线，对于Vfestival数据集观察到了89％的精度。
The problem of predicting people's participation in real-world events has received considerable attention as it offers valuable insights for human behavior analysis and event-related advertisement. Today social networks (e.g. Twitter) widely reflect large popular events where people discuss their interest with friends. Event participants usually stimulate friends to join the event which propagates a social influence in the network. In this paper, we propose to model the social influence of friends on event attendance. We consider non-geotagged posts besides structures of social groups to infer users' attendance. To leverage the information on network topology we apply some of recent graph embedding techniques such as node2vec, HARP and Poincar`e. We describe the approach followed to design the feature space and feed it to a neural network. The performance evaluation is conducted using two large music festivals datasets, namely the VFestival and Creamfields. The experimental results show that our classifier outperforms the state-of-the-art baseline with 89% accuracy observed for the VFestival dataset.
