Hate Speech Detection in Indonesian Language on Instagram Comment Section Using Deep Neural Network Classification Method

B.B Sakti Putra Perdana, Budhi Irawan, C. Setianingsih
{"title":"Hate Speech Detection in Indonesian Language on Instagram Comment Section Using Deep Neural Network Classification Method","authors":"B.B Sakti Putra Perdana, Budhi Irawan, C. Setianingsih","doi":"10.1109/APWiMob48441.2019.8964197","DOIUrl":null,"url":null,"abstract":"Instagram is the second social media that is often used by people, especially in Indonesia. Instagram has a function to comment on photos or videos uploaded by users. Comments that submitted by a community, some of them are positive, some of them are negative. Which one is hate speech. Based on ITE constitution that prohibited acts are intentionally and without rights to disseminate information intended to incite hatred or hostility of certain individuals and/or groups of people based on ethnicity, religion, race, and intergroup. Authorities find it difficult to handle the hate speech because there are many variations of hate speech. Therefore, the system is made to detect hate speech using Deep Neural Network method. With this system, it can be to help the authorities to handle this case, especially on Instagram comment section. From the research results of this final task in classifying a hate speech from Instagram column comment section obtained accuracy with an average 97.19%.","PeriodicalId":286003,"journal":{"name":"2019 IEEE Asia Pacific Conference on Wireless and Mobile (APWiMob)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"5","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2019 IEEE Asia Pacific Conference on Wireless and Mobile (APWiMob)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/APWiMob48441.2019.8964197","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 5

Abstract

Instagram is the second social media that is often used by people, especially in Indonesia. Instagram has a function to comment on photos or videos uploaded by users. Comments that submitted by a community, some of them are positive, some of them are negative. Which one is hate speech. Based on ITE constitution that prohibited acts are intentionally and without rights to disseminate information intended to incite hatred or hostility of certain individuals and/or groups of people based on ethnicity, religion, race, and intergroup. Authorities find it difficult to handle the hate speech because there are many variations of hate speech. Therefore, the system is made to detect hate speech using Deep Neural Network method. With this system, it can be to help the authorities to handle this case, especially on Instagram comment section. From the research results of this final task in classifying a hate speech from Instagram column comment section obtained accuracy with an average 97.19%.
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
基于深度神经网络分类的Instagram评论区印尼语仇恨语音检测
Instagram是人们经常使用的第二大社交媒体,尤其是在印度尼西亚。Instagram有对用户上传的照片或视频进行评论的功能。社区提交的评论,有些是正面的,有些是负面的。哪一个是仇恨言论。根据ITE宪法,禁止故意和没有权利传播旨在煽动基于民族、宗教、种族和群体的某些个人和/或群体的仇恨或敌意的信息。当局很难处理仇恨言论,因为仇恨言论有很多变化。因此,采用深度神经网络方法对仇恨言论进行检测。有了这个系统,它可以帮助当局处理这种情况,特别是在Instagram评论区。从最后的研究结果来看,从Instagram专栏评论区对仇恨言论进行分类的准确率平均为97.19%。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
Design and Performance Analysis of Multilayer On-Chip Band Pass Filter for RF Circuits Classification of Diabetic Retinopathy using Statistical Region Merging and Convolutional Neural Network Integration of Digital Modulation and Power Amplifier Using Switching Power Converter Development of IoT Server on Electricity Mapping System Performance Analysis of Radio over Fiber Network for Indoor Telecommunication Application
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1