Toward Multimodal Cyberbullying Detection
Toward Multimodal Cyberbullying Detection
复制标题
迈向多模式网络欺凌检测
DOI：
--
复制
发表时间：
2017
期刊：
影响因子：
--
通讯作者：
Christin Jose
中科院分区：
文献类型：
--
作者：
Vivek K. Singh;Souvick Ghosh;Christin Jose
随着人类利用计算技术来调节生活的多个方面，网络欺凌已成为一项重要的社会挑战。网络欺凌可能会导致受影响者出现严重的精神和情感障碍。因此，迫切需要设计用于网络欺凌检测和预防的自动化方法。虽然最近的网络欺凌检测工作已经定义了用于网络欺凌检测的复杂文本处理方法，但目前还很少有利用视觉数据处理来自动检测网络欺凌的工作。根据对公开的、标记的网络欺凌数据集的早期分析，我们报告说，视觉特征补充了网络欺凌检测中的文本特征，有助于改善预测结果。
As human beings utilize computing technologies to mediate multiple aspects of their lives, cyberbullying has grown as an important societal challenge. Cyberbullying may lead to deep psychiatric and emotional disorders for those affected. Hence, there is an urgent need to devise automated methods for cyberbullying detection and prevention. While recent cyberbullying detection efforts have defined sophisticated text processing methods for cyberbullying detection, there are as yet few efforts that leverage visual data processing to automatically detect cyberbullying. Based on early analysis of a public, labeled cyberbullying dataset, we report that visual features complement textual features in cyberbullying detection and can help improve predictive results.