Online abuse directed towards women on the social media platform Twitter has attracted considerable attention in recent years. An automated method to effectively identify misogynistic abuse could improve our understanding of the patterns, driving factors, and effectiveness of responses associated with abusive tweets over a sustained time period. However, training a neural network (NN) model with a small set of labelled data to detect misogynistic tweets is difficult. This is partly due to the complex nature of tweets which contain misogynistic content, and the vast number of parameters needed to be learned in a NN model. We have conducted a series of experiments to investigate how to train a NN model to detect misogynistic tweets effectively. In particular, we have customised and regularised a Convolutional Neural Network (CNN) architecture and shown that the word vectors pre-trained on a task-specific domain can be used to train a CNN model effectively when a small set of labelled data is available. A CNN model trained in this way yields an improved accuracy over the state-of-the-art models.
CovidMis20: COVID-19 Misinformation Detection System on Twitter Tweets using Deep Learning Models
Saginaw Valley State University(萨吉诺谷州立大学);The Hashemite University(哈希姆大学);Western Michigan University(西密歇根大学);University of Nebraska at Kearney(内布拉斯加大学卡尼尔分校)
QutNocturnal@HASOC'19: CNN for Hate Speech and Offensive Content Identification in Hindi Language
Queensland University of Technology(昆士兰科技大学)
我们描述了我们在FIRE 2019组织的HASOC竞赛中为印地语任务1提供的顶级团队解决方案。任务是识别印地语中的仇恨言论和攻击性语言。更具体地说,这是一个二元分类问题,其中需要系统将推文分类为两类:(a)\emph{Hate and Offensive (HOF)}和(b)\emph{Not Hate or Offensive (NOT)}。与流行的预训练词向量(也称为词嵌入)与来自维基百科等通用领域的大型语料库,我们使用相对较小的相关推文集合(即印地语和印度英语的随机和讽刺推文)进行预训练。我们在预训练的词向量之上训练了一个卷积神经网络(CNN)。这种方法使我们在所有团队中排名第一。我们的方法可以很容易地适应其他应用程序的目标是预测类的文本时,所提供的上下文是有限的。
BERT-Deep CNN: State-of-the-Art for Sentiment Analysis of COVID-19 Tweets
University of Birjand(比尔詹德大学);Dibrugarh University(迪布鲁加尔大学);Fasa University(法萨大学);Ferdowsi University of Mashhad(马什菲尔德大学);Deakin University(迪肯大学);Shahid Beheshti University(沙希德·贝赫什提大学);Khulna University(库尔纳大学)
Convolutional Neural Networks for Sentiment Analysis on Weibo Data: A Natural Language Processing Approach
College Of Computing And Information Technologies(计算与信息技术学院);National University Manila(马尼拉国立大学);School of Information Engineering(信息工程学院);Jiangxi College of Applied Technology(江西应用技术职业学院)
Enhanced Offensive Language Detection Through Data Augmentation
Dartmouth College(达特茅斯学院)
检测社交媒体上的攻击性语言是一项重要任务。ICWSM-2020数据挑战任务2旨在使用包含10万条标记推文的众包数据集识别攻击性内容。然而,数据集存在类别不平衡,与其他类别相比,某些标签非常罕见(例如,仇恨类仅占数据的5%)。在这项工作中,我们提出了Dager(数据增强器),一个基于生成的数据增强方法,提高了不平衡和低资源数据,如攻击性语言数据集的分类性能。Dager提取给定类的词法特征,并使用这些特征来指导生成基于GPT-2的条件生成器。然后,可以将生成的文本作为增强数据添加到训练集中。我们表明,当我们使用整个数据集的1%进行训练(使用BERT进行分类)时,应用Dager可以将数据挑战的F1得分提高11%;此外,生成的数据也很好地保留了原始标签。我们在四种不同的分类器(BERT,CNN,Bi-LSTM with attention和Transformer)上测试了Dager,观察到检测的普遍改进,表明我们的方法是有效的,并且与分类器无关。