«上一篇/Previous Article|本期目录/Table of Contents|下一篇/Next Article»

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:

32

期数:

2022年04期

页码:

134-139

栏目:

应用前沿与综合

出版日期:

2022-04-10

文章信息/Info

Title:

Public Safety Crisis Recognition Based on Bi-LSTM+Attention

文章编号:

1673-629X(2022)04-0134-06

作者:

王志晓¹; 2 ; 李卓淳¹ ; 闫文耀³

1. 西安理工大学 计算机科学与工程学院,陕西 西安 710048;

2. 陕西省网络计算与安全技术重点实验室,陕西 西安 710048;

3. 延安大学 西安创新学院,陕西 西安 710100

Author(s):

WANG Zhi-xiao1; 2 ; LI Zhuo-chun1 ; YAN Wen-yao3

1. School of Computer Science and Engineering,Xi’an University of Technology,Xi’an 710048,China;

2. Shaanxi Key Laboratory of Network Computing and Security,Xi’an 710048,China;

3. School of Xi’an Innovation,Yan’an University,Xi’an 710100,China

关键词:

公共安全; 社交媒体; 家庭暴力; 深度学习; 文本挖掘

Keywords:

public safety; social media; domestic violence ( DV) ; deep learning; text mining

分类号:

TP391

DOI:

10. 3969 / j. issn. 1673-629X. 2022. 04. 023

摘要:

公共安全危机对社会稳定和人权构成威胁,令人担忧。 社交媒体上帖子的可用性使得公共安全危机更容易被探测。 然而, 手动浏览和分析大量可用 帖子耗时且效率低下。 鉴于深度学习技术在自然语言处理方面的优势,采用深度学习技术自动识别潜在的公共安全危机成为当前的迫切需求。文中 以家庭暴力危机为例,将社交媒体 Facebook 上有关家庭暴力的英文帖子作为研究对象, 通过 Facebook GraphAPI 获取后进行文本预处理。 采用 Word2vec 方法构建词向量模型,使用 Bi-LSTM+self-Attention(SA-BiLSTM) 深度学习模型完成了家庭暴力危机识别任务,并与 CNN、RNN( recurrent neuralnetwork,循环神经网络)、LSTM 三个神经网络模型进行了比较。 实验结果显示,CNN 和 LSTM 模型表现明显好于 RNN,与SA-BiLSTM 模型表现相接近;同时,使用 self-Attention 机制后 Bi-LSTM 模型综合表现最好, F1 值、召回率、准确率均最高,其中召回率和准确率超过 90% 。 该研究成果将为使用深度学习技术自动探测公共安全危机问题提供参考和帮助。

Abstract:

Public safety crisis is a cause of great concern due to the threat toward social stability and human rights. The availability of posts on social media has allowed public safety crisis to be detected more easily. However, it is time consuming and inefficient to manually browse through a massive number of available posts. Therefore, considering the advantages of deep learning technology in natural language processing,adopting deep learning as an approach for automatic identification of public safety crisis is in critical need.We consider domestic violence ( DV) crisis as the example,take Facebook English posts about DV as the research object and implement text processing after getting them by GraphAPI. Then we use Word2Vec to build word vector model and Bi-LSTM+self-Attention (SA-BiLSTM) deep learning model to accomplish DV crisis recognition task,compare it with CNN, RNN and LSTM. The experiment show sthat the performances of CNN and LSTM are close to SA-BiLSTM,which is better than RNN. And the performance of SA-BiLSTM is the best with the highest F1,recall and accuracy,both of recall and accuracy values are above 90% . The research results will provide reference and help for the use of deep learning technology to automatically identify public safety crisis issues.

常用功能

更新日期/Last Update: 2022-04-10