...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Iranian journal of public health. >Automatic Identification of Messages Related to Adverse Drug Reactions from Online User Reviews using Feature-based Classification
【24h】

Automatic Identification of Messages Related to Adverse Drug Reactions from Online User Reviews using Feature-based Classification

机译：使用基于特征的分类从在线用户评论中自动识别与药物不良反应有关的消息

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Background: User-generated medical messages on Internet contain extensive information related to adverse drug reactions (ADRs) and are known as valuable resources for post-marketing drug surveillance. The aim of this study was to find an effective method to identify messages related to ADRs automatically from online user reviews. Methods: We conducted experiments on online user reviews using different feature set and different classification technique. Firsdy, the messages from three communities, allergy community, schizophrenia community and pain management community, were collected, the 3000 messages were annotated. Secondly, the N-gram-based features set and medical domain-specific features set were generated. Thirdly, three classification techniques, SYM, C4.5 and Naive Bayes, were used to perform classification tasks separately. Finally, we evaluated the performance of different method using different feature set and different classification technique by comparing the metrics including accuracy and F- measure. Results: In terms of accuracy, the accuracy of SVM classifier was higher than 0.8, the accuracy of C4.5 classifier or Naive Bayes classifier was lower than 0.8; meanwhile, the combination feature sers including n-gram-based feature set and domain-specific feature set consistendy outperformed single feature set. In terms of F-measure, the highest F- measure is 0.895 which was achieved by using combination feature sets and a SYM classifier. In all, we can get the best classification performance by using combination feature sets and SVM classifier. Conclusion: By using combination feature sets and SVM classifier, we can get an effective method to identify messages related to ADRs automatically from online user reviews.
机译：背景：互联网上用户生成的医疗消息包含与药物不良反应（ADR）相关的大量信息，被称为上市后药物监视的宝贵资源。这项研究的目的是找到一种有效的方法，该方法可以从在线用户评论中自动识别与ADR相关的消息。方法：我们使用不同的功能集和不同的分类技术对在线用户评论进行了实验。 Firsdy收集了来自三个社区（过敏性社区，精神分裂症社区和疼痛管理社区）的消息，并注释了3000条消息。其次，生成了基于N元语法的特征集和特定于医学领域的特征集。第三，使用三种分类技术SYM，C4.5和朴素贝叶斯分别执行分类任务。最后，我们通过比较包括准确性和F量度在内的指标，评估了使用不同特征集和不同分类技术的不同方法的性能。结果：就准确性而言，SVM分类器的准确性高于0.8，C4.5分类器或Naive Bayes分类器的准确性低于0.8;同时，包括基于n元语法的特征集和特定于域的特征集在内的组合特征序列在性能上优于单个特征集。就F量度而言，最高的F量度为0.895，这是通过使用组合特征集和SYM分类器实现的。总之，通过使用组合功能集和SVM分类器，我们可以获得最佳的分类性能。结论：通过使用组合功能集和SVM分类器，我们可以获得从在线用户评论中自动识别与ADR相关的消息的有效方法。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号