arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2008.13012cs.CLcs.CY
收藏

SocCogCom在SemEval-2020的任务11:使用句子级情绪显著性特征表征和检测宣传

SocCogCom at SemEval-2020 Task 11: Characterizing and Detecting Propaganda using Sentence-Level Emotional Salience Features

Institute of High Performance Computing (IHPC)(高性能计算研究所);Agency for Science, Technology and Research (A*STAR)(新加坡科技研究局)

Gangeshwar Krishnamurthy, Raj Kumar Gupta, Yinping Yang

摘要:

本文介绍了一个系统开发的检测宣传技巧,从新闻文章。我们专注于研究如何从新闻片段中提取的情感显着性特征可以帮助描述和预测宣传技术的存在。相关性分析显示出有趣的模式,例如,“加载语言”和“口号”技术与效价和快乐强度呈负相关,但与愤怒,恐惧和悲伤强度呈正相关。相比之下,“挥舞旗帜”和“诉诸恐惧偏见”的模式正好相反。通过预测实验,结果进一步表明,而BERT的功能获得F1分数为0.548,情绪强度功能和BERT混合功能能够获得F1分数为0.570,当一个简单的前馈网络被用作在两种设置中的分类器。在黄金测试数据上,我们的系统在14种宣传技术的总体检测效率上获得了0.558的微平均F1分数。它在检测“装语言”(F1 = 0.772)、“名称呼叫和标记”(F1 = 0.673)、“怀疑”(F1 = 0.604)和“挥舞旗帜”(F1 = 0.543)方面表现相对较好。

英文摘要:

This paper describes a system developed for detecting propaganda techniques from news articles. We focus on examining how emotional salience features extracted from a news segment can help to characterize and predict the presence of propaganda techniques. Correlation analyses surfaced interesting patterns that, for instance, the "loaded language" and "slogan" techniques are negatively associated with valence and joy intensity but are positively associated with anger, fear and sadness intensity. In contrast, "flag waving" and "appeal to fear-prejudice" have the exact opposite pattern. Through predictive experiments, results further indicate that whereas BERT-only features obtained F1-score of 0.548, emotion intensity features and BERT hybrid features were able to obtain F1-score of 0.570, when a simple feedforward network was used as the classifier in both settings. On gold test data, our system obtained micro-averaged F1-score of 0.558 on overall detection efficacy over fourteen propaganda techniques. It performed relatively well in detecting "loaded language" (F1 = 0.772), "name calling and labeling" (F1 = 0.673), "doubt" (F1 = 0.604) and "flag waving" (F1 = 0.543).

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑