GroupUs: Smartphone Proximity Data and Human Interaction Type Mining
GroupUs: Smartphone Proximity Data and Human Interaction Type Mining
复制标题
GroupUs：智能手机接近数据和人类交互类型挖掘
DOI：
10.1109/iswc.2011.28
复制
发表时间：
2011
期刊：
影响因子：
--
通讯作者：
D. Gática
中科院分区：
文献类型：
--
作者：
T. Do;D. Gática
人们对从移动传感器数据分析社交互动的兴趣与日俱增，智能手机正迅速成为最具吸引力的传感选择。我们提出了一种新的概率关系模型来分析由于人们的物理接近而产生的长期动态社会网络。我们的模型可以从网络中推断出不同的交互类型，揭示给定群体交互的参与者，并发现各种社交上下文。我们的分析是在一年多的时间里用智能手机感应到的蓝牙数据进行的，涉及40个与职业或个人联系相关的人的生活。我们通过研究我们的模型的预测性能来客观地验证我们的模型，显示出比最近提出的模型显著的优势。
There is an increasing interest in analyzing social interaction from mobile sensor data, and smart phones are rapidly becoming the most attractive sensing option. We propose a new probabilistic relational model to analyze long-term dynamic social networks created by physical proximity of people. Our model can infer different interaction types from the network, revealing the participants of a given group interaction, and discovering a variety of social contexts. Our analysis is conducted on Bluetooth data sensed with smart phones for over one year on the life of 40 individuals related by professional or personal links. We objectively validate our model by studying its predictive performance, showing a significant advantage over a recently proposed model.
DOI：
10.1073/pnas.0307752101
发表时间：
2004-04-06
影响因子：
11.1
作者：
Griffiths, TL;Steyvers, M
通讯作者：
Steyvers, M