One of the main purposes for which people use Twitter is to share emotions with others. Users can easily post a message as a short text when they experience emotions such as pleasure or sadness. Such tweet serves to a...One of the main purposes for which people use Twitter is to share emotions with others. Users can easily post a message as a short text when they experience emotions such as pleasure or sadness. Such tweet serves to acquire empathy from followers, and can possibly influence others' emotions. In this study, we analyze the influence of emotional behaviors to user relationships based on Twitter data using two dictionaries of emotional words. Emotion scores are calculated via keyword matching. Moreover, we design three experiments with different settings: calculate the average emotion score of a user with random sampling, calculate the average emotion score using all emotional tweets, and calculate the average emotion score using emotional tweets, excluding users of few emotional tweets. We evaluate the influence of emotional behaviors to user relationships through the Brunner-Munzel test. The result shows that a positive user is more active than a negative user in constructing user relationships in a specific condition.展开更多
低压台区拓扑信息的准确记录是进行台区线损分析、三相不平衡治理等工作的基础。针对目前拓扑档案排查成本高且效率低的问题,提出一种基于自适应k近邻(adaptive k nearest neighbor,AKNN)异常检验和自适应密度峰值(adaptive density pea...低压台区拓扑信息的准确记录是进行台区线损分析、三相不平衡治理等工作的基础。针对目前拓扑档案排查成本高且效率低的问题,提出一种基于自适应k近邻(adaptive k nearest neighbor,AKNN)异常检验和自适应密度峰值(adaptive density peaks clustering,ADPC)聚类的低压台区拓扑识别方法。该方法利用动态时间弯曲(dynamic time warping,DTW)距离度量低压台区用户间电压序列的相似性,通过AKNN异常检验算法检验并校正异常的用户与变压器之间的关系(简称“户变关系”),在得到正确户变关系的基础上,采用ADPC聚类算法对台区内用户进行相位识别;最后,通过实际台区算例分析验证了该方法不需要人为设置参数,能有效实现低压台区的拓扑识别,具有较高的适用性与准确性。展开更多
为打破现存研究普遍以网络拓扑一致性假设为前提的限制,弱化锚节点数量和质量对链接任务的影响,提出一种基于跨网络语义表征的用户链接算法CSRMA(cross-network semantic representation link algorithm based on mask attention mechan...为打破现存研究普遍以网络拓扑一致性假设为前提的限制,弱化锚节点数量和质量对链接任务的影响,提出一种基于跨网络语义表征的用户链接算法CSRMA(cross-network semantic representation link algorithm based on mask attention mechanism)。该算法框架包含3个模块:多视角采样与注意力机制相结合的跨网络表征模块、不同网络共性特征学习的语义空间映射模块、基于k-d树改进Gale-Shapley算法的用户身份精准链接模块。通过4个公开数据集上的实验验证了所提算法的有效性。与多个身份链接算法对比,CSRMA具有更高的精确率。展开更多
文摘One of the main purposes for which people use Twitter is to share emotions with others. Users can easily post a message as a short text when they experience emotions such as pleasure or sadness. Such tweet serves to acquire empathy from followers, and can possibly influence others' emotions. In this study, we analyze the influence of emotional behaviors to user relationships based on Twitter data using two dictionaries of emotional words. Emotion scores are calculated via keyword matching. Moreover, we design three experiments with different settings: calculate the average emotion score of a user with random sampling, calculate the average emotion score using all emotional tweets, and calculate the average emotion score using emotional tweets, excluding users of few emotional tweets. We evaluate the influence of emotional behaviors to user relationships through the Brunner-Munzel test. The result shows that a positive user is more active than a negative user in constructing user relationships in a specific condition.
基金This work is supported by the National Natural Science Foundation of China (61070109) and Opening Project of Beijing Key Laboratory of Mobile Computing and Pervasive Device.
文摘低压台区拓扑信息的准确记录是进行台区线损分析、三相不平衡治理等工作的基础。针对目前拓扑档案排查成本高且效率低的问题,提出一种基于自适应k近邻(adaptive k nearest neighbor,AKNN)异常检验和自适应密度峰值(adaptive density peaks clustering,ADPC)聚类的低压台区拓扑识别方法。该方法利用动态时间弯曲(dynamic time warping,DTW)距离度量低压台区用户间电压序列的相似性,通过AKNN异常检验算法检验并校正异常的用户与变压器之间的关系(简称“户变关系”),在得到正确户变关系的基础上,采用ADPC聚类算法对台区内用户进行相位识别;最后,通过实际台区算例分析验证了该方法不需要人为设置参数,能有效实现低压台区的拓扑识别,具有较高的适用性与准确性。
文摘为打破现存研究普遍以网络拓扑一致性假设为前提的限制,弱化锚节点数量和质量对链接任务的影响,提出一种基于跨网络语义表征的用户链接算法CSRMA(cross-network semantic representation link algorithm based on mask attention mechanism)。该算法框架包含3个模块:多视角采样与注意力机制相结合的跨网络表征模块、不同网络共性特征学习的语义空间映射模块、基于k-d树改进Gale-Shapley算法的用户身份精准链接模块。通过4个公开数据集上的实验验证了所提算法的有效性。与多个身份链接算法对比,CSRMA具有更高的精确率。