期刊文献+

基于“用户画像”的阅读疗法模式研究——以抑郁症为例 被引量:73

Research on Bibliotherapy Model Based on User Profile——Take Depression as an Example
下载PDF
导出
摘要 针对目前抑郁症阅读疗法施治对象的选取样本过于单一,私密性差,不能及时发现潜在患者,及时治疗的现状,提出了在大数据背景下基于"用户画像"的抑郁症阅读疗法新模式。该模式首先根据"伯恩斯抑郁症清单(BDC)"的内容来构造抑郁情绪的种子词,然后基于机器学习的方法,综合提炼用户网上行为和抑郁情绪的主观表露,构建用户抑郁情感词典。根据抑郁情感词典分析用户微博文本,计算其抑郁情感指数,得到"用户画像",进而推送相应的阅读治疗资源。基于"用户画像"的阅读疗法模式大大突破了受众范围,便于准确把握诊断、治疗时机,使患者在无意识状态下接受阅读治疗,减轻了患者经济和精神的双重压力,具有较高的社会价值和重要的现实意义。 In this paper, a new mode of bibliotherapy for depression based on user profile is put forward in view of the current situation of depression bibliotherapy with weakness such as samples selected too sim- ple, poor in privacy, and unable to detect and treat potential patients in a timely manner. This mode first constructed the seed words of depressive mood according to "The Burns Depression Checklist (BDC)", and then based on the machine learning method, comprehensively refined the subjective revealing of user's on- line behavior and depressive mood to construct the user's depressed emotional dictionary. According to the depressed emotional dictionary to analyze user's blog, calculate the depression emotional index, get the us- er profile, and then push the corresponding bibliotherapy resources. The bibliotherapy mode based on the user profile exceeded the audience scope, accurately grasp the timing of diagnosis and treatment, so that patients could accept bibliotherapy in an unconscious state, so as to reduce the patient's double pressure of economic and spirit.
出处 《大学图书馆学报》 CSSCI 北大核心 2017年第6期105-110,共6页 Journal of Academic Libraries
基金 2016年度校级哲学社会科学研究规划项目"新媒体环境下齐鲁传统文化经典藏读模式研究"(编号:XSK201615)的研究成果之一
关键词 阅读疗法 大数据 抑郁症 “用户画像” 情绪分析 Bibliotherapy Big Data Depression User Profile Emotional Analysis
  • 相关文献

参考文献7

二级参考文献51

  • 1朱嫣岚,闵锦,周雅倩,黄萱菁,吴立德.基于HowNet的词汇语义倾向计算[J].中文信息学报,2006,20(1):14-20. 被引量:326
  • 2李峰,李芳.中文词语语义相似度计算——基于《知网》2000[J].中文信息学报,2007,21(3):99-105. 被引量:105
  • 3Kindleberger, C. Manias, Panics, and Crashes: A History of Financial Crises 同 Wiley Investment Classic, New York, John Wiley & Sons, 2001.
  • 4Lakonishk, J., Lee, I. and Poteshman, A. , Investor behavior in the option market[C]//NBER Working Papers 10264, Cambridge, Mass: National Bureau of Economic Research, 2004.
  • 5Ahmad, K. and Almas, Y. Visualising sentiments in financial texts? [C]//Proceedings of the Ninth International Conference on Information Visualisation, 00: 363- 368.
  • 6Chaovalit, P. and Zhou, L. Movie review mining: a comparison between supervised and unsupervised classification approaches[C]//Proceedings of the 38th Hawaii International Conference on System Sciences, 2005.
  • 7Turney, P.D. Mining the web for synonyms: PMI-IR versus LSA on TOEFL[C]//Proceedings of the Twelfth European Conference on Machine Learning, Berlin: Springer-Verlag, 2001: 491-502.
  • 8Turney, P.D. Thumbs up or thumbs down? Semantic orientation applied to unsupervised classification of reviews[R]. presented at the Association for Computational Linguistics 40th Anniversary Meeting, New Brunswick, N.J., 2002.
  • 9Turney, P.D. and Littman, M.L. Measuring praise and criticism: inference of semantic orientation from association[J]. Transactions on Information Systems, 21:315 346.
  • 10Ye, Q., Lin, B. and Li, Y.J. Sentiment classification for Chinese reviews: a comparison between SVM and semantic approaehes[C]//Proceedings of 2005 Interna tional Conference on Machine Learning and Cybernet ies, Aug. 18-21,2005, 4: 2341-2346.

共引文献234

同被引文献687

引证文献73

二级引证文献802

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部