【摘要】 [目的/意义]为了从海量财经新闻中快速、准确识别与特定股票相关的重要信息，充分挖掘其潜在价值，文章开展面向股票的财经新闻关联度研究。[方法/过程]利用自然语言处理与机器学习方法实现新闻全文本分析，细化到词语粒度挖掘并量化股票-财经新闻关联关系。在此基础上，基于新闻价值量化理论，建立“面向股票的财经新闻关联度测度体系”。[结果/结论]构建了融入新闻价值评价的股票-财经新闻关联度测度体系，实现了个性化、自动化的股票-财经新闻关联程度测量；进一步分析了各个维度指标对关联度测度的影响。更多还原

【Abstract】 [Purpose/significance]To identify crucial financial news information and tap its potential value related to specific stocks more quickly and accurately, we conduct financial news correlation measurement research in terms of stocks.[Method/process]Natural Language Processing and Machine Learning are used to measure the correlation by text analysis in the word’s dimension. Then, the theory of quantifying news is applied to construct a stock-oriented evaluation index system for financial news correlation. [Result/conclusion]This paper realizes a personalized and automatic measurement of news correlation with the index system. Further, the influence of each index is also be analyzed.更多还原