面向互联网舆情的热词分析技术.pdfVIP

面向互联网舆情的热词分析技术* 1 2 李渝勤 ，孙丽华 北京信息科技大学，北京100101 北京拓尔思信息技术股份有限公司,北京 100101 E-mail: li.yuqin@ 摘 要：热词是一种网络词汇现象，反映了某一特定时空范围内人们普遍关注的问题。该文对热词分析的 两项关键技术热词发现和热词关联技术进行了深入的研究。在热词发现阶段，首先采用命名实体识别 技术和高频串统计技术进行短语串的挖掘，继而采用基础权值和波动权值两项指标进行热度权值的计算。 在热词关联阶段，按热词权值高低进行热词类的划分，通过同现率的原则确定热词类之间的关联计算。该 文所采用的方法已经成功应用到TRS 舆情监测系统的热点发现模块。 关键词：热词；命名实体识别；热度计算；波动权值；词群关系 Hot-word technology based on Internet public sentiment Li yuqin, Sun lihua Beijing Information Science Technology University Beijing 100101 Beijing TRS Information Technology Co.,Ltd Beijing 100101 E-mail: li.yuqin@ Abstract: Hot-word is a network phenomenon, which reflects some popular feelings and topics at a particular time and space. In this paper, the two key technologies of hot-word analyzing is deeply discussed, including hot-word discovering and associating technique. In the phase of word discovering, firstly, we get named entity recognition techniques and statistical techniques for high frequency phrase to do string excavation. Then, we take the basis of weight and weight fluctuations to compute hot-word weight. Up to the hot-word association, they are derided from the difference of the weight value of hot-word, and hot-word relationship was computed from the principle of co-occurrence rate .The technology has been successfully applied to hot-word discovering module, which is a part of TRS public sentiment monitoring system. Keywords: Hot Words; Named Entity Identification; Hot Degree Computing; Weight fluctuations; Words Relationship 1 概论 随着互联网的普及，中国网民超过3.38 亿人，已经成为世界第一大网民国家。Web2.0 时代，网络具有传播快、成本低、联动性强等特点，使得传播环境与传播者都发生了天翻 地覆的变化。网络论坛、博客、SNS 等给人们提