Deep Learning for User Comment Moderation

机译：深度学习的用户评论审核

获取原文

获取原文并翻译 | 示例

页面导航

摘要
著录项
相似文献
相关主题

摘要

Experimenting with a new dataset of 1.6M user comments from a Greek news portal and existing datasets of English Wikipedia comments, we show that an RNN outperforms the previous state of the art in moderation. A deep, classification-specific attention mechanism improves further the overall performance of the RNN. We also compare against a CNN and a word-list baseline, considering both fully automatic and semi-automatic moderation.

机译：通过试验来自希腊新闻门户网站的160万个用户评论的新数据集和英语维基百科评论的现有数据集，我们发现RNN在适度性方面优于现有技术。深入的，特定类别的关注机制进一步提高了RNN的整体性能。我们还考虑了CNN和单词列表基准，同时考虑了全自动和半自动审核。

著录项

来源
《First workshop on abusive language online 2017》|2017年|25-35|共11页
会议地点 Vancouver(CA)
作者
John Pavlopoulos; Prodromos Malakasiotis; Ion Androutsopoulos;
展开▼
作者单位

StrainTek Athens, Greece;

StrainTek Athens, Greece;

Department of Informatics Athens University of Economics and Business, Greece;

展开▼
会议组织
原文格式 PDF
正文语种 eng
中图分类
关键词

相似文献

外文文献
中文文献
专利

1. USING DEEP LEARNING TO LEARN USER RATING FROM USER COMMENTS [J] . HENDRY, RUNG-CHING CHEN, LI-HUA LI, International Journal of Innovative Computing Information and Control . 2018,第3期

机译：使用深度学习从用户评论中学习用户评级
2. Sentiment analysis of low-carbon travel APP user comments based on deep learning [J] . Lin Xing-Min, Ho Chun-Heng, Xia Lu-Ting, Sustainable Energy Technologies and Assessments . 2021,第Apra期

机译：基于深度学习的低碳旅行应用用户评论的情感分析
3. The moderation effect of user-type (educators vs. students) in learning management system continuance [J] . Islam A. K. M. Najmul Behaviour & Information Technology . 2015,第10a12期

机译：用户类型（教育者与学生）对学习管理系统持续性的调节作用
4. Deep Learning for User Comment Moderation [C] . John Pavlopoulos, Prodromos Malakasiotis, Ion Androutsopoulos Annual meeting of the Association for Computational Linguistics . 2017

机译：用户评论审核的深度学习
5. The effects of body ideal profile pictures and friends' comments on social network site users' body image: A side model approach. [D] . Flynn, Mark Allen. 2012

机译：身体理想的个人资料图片和朋友的评论对社交网站用户的身体形象的影响：一种侧面模型方法。
6. Reply to Jue et al. Value of MRI to Improve Deep Learning Model That Identifies High-Grade Prostate Cancer. Comment on Gentile et al. Optimized Identification of High-Grade Prostate Cancer by Combining Different PSA Molecular Forms and PSA Density in a Deep Learning Model. Diagnostics 2021 11 335 [O] . Francesco Gentile, Matteo Ferro, Bartolomeo Della Ventura, 2021

机译：回复jue等人。 MRI的价值改善识别高档前列腺癌的深度学习模型。评论Gentile等人。通过在深层学习模型中结合不同PSA分子形式和PSA密度来优化高级前列腺癌的优化鉴定。诊断202111335
7. Deep Learning for User Comment Moderation [O] . Pavlopoulos, John, Malakasiotis, Prodromos, Androutsopoulos, Ion 2017

机译：用户评论审核的深度学习

Deep Learning for User Comment Moderation

摘要

著录项

相似文献

相关主题

期刊订阅