面向微博文本的自杀风险识别模型
作者:
基金项目:

杭州市科技计划(20170533B04); 福建省中青年教师教育研究项目(JT180459); 杭州师范大学星光计划


Suicide Risk Identification Model Based on Microblog Text
Author:
  • 摘要
  • | |
  • 访问统计
  • |
  • 参考文献 [16]
  • |
  • 相似文献
  • | | |
  • 文章评论
    摘要:

    自杀是当今社会严重的公共卫生问题, 对自杀预防工作进行深入研究有着极大的社会意义. 该文对基于微博文本的自杀风险评估方法进行了研究. 针对微博文本的特点, 为解决当前神经网络单一结构在预测精度提升上的瓶颈问题, 本文提出了一种混合架构的神经网络模型nC-BiLSTM, 并将其应用于微博文本自杀风险识别. 该模型利用多路不同卷积核的卷积层提取局部特征信息, 同时使用双向长短期记忆网络层提取句子的上下文语义特征信息, 实验表明nC-BiLSTM模型的识别精准率、召回率、F值均优于其它模型. 该研究成果可应用到自杀预防的早期干预中.

    Abstract:

    Suicide is a serious public health problem in today’s society. It is of great social significance to conduct in-depth research on suicide prevention. This work studies the suicide risk assessment method based on Microblog text. According to Microblog text features, in order to solve the bottleneck problem of the current neural network single structure in the prediction accuracy improvement, this study proposes a hybrid architecture neural network model nC-BiLSTM and applies it to the Microblog text suicide risk identification. The model extracts local feature information by using multiple convolutional layers of different convolution kernels, and extracts contextual semantic feature information of sentences by using Bidirectional Long Short-Term Memory (BiLSTM) network layer. The experimental results show that the recognition accuracy, recall rate, and F value of the nC-BiLSTM model are better than other models. The results of this study can be applied to the early intervention of suicide prevention.

    参考文献
    [1] 中国互联网络信息中心, 李静. 第41次《中国互联网络发展状况统计报告》发布. 中国广播, 2018, (3): 96
    [2] Barak A, Miron O. Writing characteristics of suicidal people on the internet: A psychological investigation of emerging social environments. Suicide and Life-Threatening Behavior, 2005, 35(5): 507-524. [doi: 10.1521/suli.2005.35.5.507
    [3] Cheng QJ, Chang SS, Yip PSF. Opportunities and challenges of online data collection for suicide prevention. The Lancet, 2012, 379(9830): e53-e54
    [4] Chang SS, Kwok SSM, Cheng QJ, et al. The association of trends in charcoal-burning suicide with Google search and newspaper reporting in Taiwan: A time series analysis. Social Psychiatry and Psychiatric Epidemiology, 2015, 50(9): 1451-1461. [doi: 10.1007/s00127-015-1057-7
    [5] Kaljahi R, Foster J. Any-gram kernels for sentence classification: A sentiment analysis case study. arXiv: 1712.07004v1, 2017.
    [6] Li BF, Zhao Z, Liu T, et al. Weighted neural bag-of-n-grams model: New baselines for text classification. Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics. Osaka, Japan. 2016. 1591-1600.
    [7] Kim Y. Convolutional neural networks for sentence classification. arXiv: 1408.5882v2, 2014.
    [8] Zhou P, Qi ZY, Zheng SC, et al. Text classification improved by integrating bidirectional LSTM with two-dimensional max pooling. arXiv: 1611.06639, 2016.
    [9] 牛雪莹, 赵恩莹. 基于Word2Vec的微博文本分类研究. 计算机系统应用, 2019, 28(8): 256-261. [doi: 10.15888/j.cnki.csa.007030
    [10] 张金伟. 微博情感分析的心理预警模型与识别研究[硕士学位论文]. 合肥: 合肥工业大学, 2013.
    [11] Wang XY, Zhang CH, Ji Y, et al. A depression detection model based on sentiment analysis in micro-blog social network. Proceedings of PAKDD 2013 International Workshops: DMApps, DANTH, QIMIE, BDM, CDA, CloudSD. Gold Coast, QLD, Australia. 2013. 201-213.
    [12] Jashinsky J, Burton SH, Hanson CL, et al. Tracking suicide risk factors through Twitter in the US. Crisis, 2014, 35(1): 51-59. [doi: 10.1027/0227-5910/a000234
    [13] Li TMH, Chau M, Yip PSF, et al. Temporal and computerized psycholinguistic analysis of the blog of a Chinese adolescent suicide. Crisis, 2014, 35(3): 168-175. [doi: 10.1027/0227-5910/a000248
    [14] 田玮, 朱廷劭. 基于深度学习的微博用户自杀风险预测. 中国科学院大学学报, 2018, 35(1): 131-136
    [15] 梁军, 柴玉梅, 原慧斌, 等. 基于极性转移和LSTM递归网络的情感分析. 中文信息学报, 2015, 29(5): 152-159. [doi: 10.3969/j.issn.1003-0077.2015.05.020
    [16] 刘飞龙, 郝文宁, 陈刚, 等. 基于双线性函数注意力Bi-LSTM模型的机器阅读理解. 计算机科学, 2017, 44(S1): 92-96, 122
    相似文献
    引证文献
    网友评论
    网友评论
    分享到微博
    发 布
引用本文

章宣,赵宝奇,孙军梅,葛青青,肖蕾,尉飞.面向微博文本的自杀风险识别模型.计算机系统应用,2020,29(11):121-127

复制
分享
文章指标
  • 点击次数:1380
  • 下载次数: 2379
  • HTML阅读次数: 1920
  • 引用次数: 0
历史
  • 收稿日期:2019-11-23
  • 最后修改日期:2019-12-09
  • 在线发布日期: 2020-10-30
文章二维码
您是第11200515位访问者
版权所有:中国科学院软件研究所 京ICP备05046678号-3
地址:北京海淀区中关村南四街4号 中科院软件园区 7号楼305房间,邮政编码:100190
电话:010-62661041 传真: Email:csa (a) iscas.ac.cn
技术支持:北京勤云科技发展有限公司

京公网安备 11040202500063号