博士生申晨论文被Neural Computing and Applications录用
新闻来源:IR实验室       发布时间:2018/9/10 16:01:51

  接到编辑部通知,博士生申晨的论文,Detecting Adverse Drug Reactions from Social Media Based on Multi-channel Convolutional Neural Networks,被Neural Computing and Applications录用。Neural Computing and Applications 其MedSci指数为:4.5959。

  论文中英文摘要如下:

Abstract:

  As one of the most important medical field subjects, adverse drug reaction seriously affects the patient's life, health, and safety. Although many meth-ods have been proposed, there are still plenty of important adverse drug reac-tions unknown, due to the complexity of the detection process. Social me-dia, such as medical forums and social networking services, collects a large amount of drug use information from patients, and so is important for ad-verse drug reaction mining. However, most of the existing studies only in-volved a single source of data. This study automatically crawls the infor-mation published by users of the MedHelp Medical Forum. Then combining it with disease-related user posts which obtained from Twitter. We combine different word embeddings and utilize a multi-channel convolutional neural network to deal with the challenge that encountered in data representation of multiple sources, and further identify text containing adverse drug reac-tion information. Especially, in this process, to enable the model to take ad-vantage of the morphological and shape information of words, we use a con-volutional channel to learn the features from character-level embeddings of words. The experiment results show that the proposed method improved the representation of words and thus effectively detects adverse drug reactions from text.

摘要:

  药物不良反应是医学研究领域的重要课题之一,它严重影响着患者的生命安全和健康。尽管已提出许多方法,但由于检测过程的复杂性,仍然存在许多重要且未知的药物不良反应。社会网络,如医学论坛和社交网络服务,从患者那里收集了大量的药物使用信息,因此对于药物不良反应挖掘非常重要。然而,大多数现有的研究仅仅是用单一的数据来源。我们的研究自动地爬了由MedHelp医学论坛的用户发布的信息,然后将其与来自Twitter的与疾病相关的用户帖子相结合。我们融合不同的单词向量表示,并利用多通道卷积神经网络来处理在多源数据表示中遇到的挑战,进一步识别包含不良药物反应的文本。特别地,在这个过程中,为了使模型能够充分利用词的形态信息,我们使用额外的卷积通道来从词的字符级向量中学习特征。实验结果表明,该方法改善了词的表示,从而能有效地检测文本中的药物不良反应。