Collaborative detection of cyberbullying behavior in Twitter data
Collaborative detection of cyberbullying behavior in Twitter data
复制标题
Twitter 数据中网络欺凌行为的协同检测
DOI：
--
复制
发表时间：
2015
期刊：
影响因子：
--
通讯作者：
M. Tuceryan
中科院分区：
文献类型：
--
作者：
M. Tuceryan
随着 Twitter© 数据规模的不断增加，用户的不良行为也随之增加。其中一种不良行为是网络欺凌，这甚至可能导致灾难性后果。因此，如果可能的话，通过实时分析推文来有效检测网络欺凌行为至关重要。识别网络欺凌的流行方法主要是独立的，因此非常耗时。这项研究利用协作计算的原理改进了检测任务。本文提出并讨论了不同的协作范式。初步结果表明，与独立范例相比，检测机制在时间和准确性方面都有所改进。
As the size of Twitter© data is increasing, so are undesirable behaviors of its users. One of such undesirable behavior is cyberbullying, which may even lead to catastrophic consequences. Hence, it is critical to efficiently detect cyberbullying behavior by analyzing tweets, if possible in realtime. Prevalent approaches to identify cyberbullying are mainly stand-alone and thus, are time-consuming. This research improves detection task using the principles of collaborative computing. Different collaborative paradigms are suggested and discussed in this paper. Preliminary results indicate an improvement in time and accuracy of the detection mechanism over the stand-alone paradigm.