用NLP方法从企业疫情响应中提炼政策决策关键信息
Investigating Corporate Social Responsibility Initiatives: Examining the case of corporate Covid-19 response
- 用LDA、TextRank等NLP技术分析企业疫情公关稿
- 从海量文本中提取出政策制定所需的核心议题
- 方法可复用于其他社会决策场景的信息提炼
在信息泛滥的时代，政策制定者需处理海量文本以做出影响利益相关方的决策。本文展示如何应用主流自然语言处理技术——隐含狄利克雷分配（LDA）、深度分布式表示、文本摘要、基于词的句子排序（Word Based Sentence Ranking）和TextRank——对大量文档进行内容提炼，以理解信息洪流中的核心要义。研究以新冠疫情早期和后期的企业新闻稿为对象，这些文件记录了全球前所未有的健康与经济社会危机期间的公司应对措施，凸显了政策规范企业行为、保障员工与社会福祉的重要性。本研究的方法流程可复制至其他社会决策场景，实现从冗长文本中高效获取洞察。
原文摘要 · Abstract (English)
In todays age of freely available information, policy makers have to take into account a huge amount of information while making decisions affecting relevant stakeholders. While increase in the amount of information sources and documents increases credibility of decisions based on the corpus of available text, it is challenging for policymakers to make sense of this information. This paper demonstrates how policy makers can implement some of the most popular topic recognition methods, Latent Dirichlet Allocation, Deep Distributed Representation method, text summarization approaches, Word Based Sentence Ranking method and TextRank for sentence extraction method, to sum up the content of large volume of documents to understand the gist of the overload of information. We have applied popular NLP methods to corporate press releases during the early period and advanced period of Covid-19 pandemic which has resulted in a global unprecedented health and socio-economic crisis, when policymaking and regulations have become especially important to standardize corporate practices for employee and social welfare in the face of similar future unseen crises. The steps undertaken in this study can be replicated to yield insights from relevant documents in any other social decision-making context.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。