基于话题结构特性的话题跟踪系统设计  

Design of Topic Tracking System Based on Topic Structure Characteristics

作　　者：李胜东 张海川 石俊涛 吴建伟 王元 LI Shengdong;ZHANG Haichuan;SHI Juntao;WU Jianwei;WANG Yuan(Department of Computer Engineering,Langfang Yanjing Vocational Technical College,Langfang Hebei 065200,China;Department of Mechanical and Electrical Engineering,Langfang Yanjing Vocational Technical College,Langfang Hebei 065200,China)

机构地区：[1]廊坊燕京职业技术学院计算机工程系,河北廊坊065200 [2]廊坊燕京职业技术学院机电工程系,河北廊坊065200

出　　处：《信息与电脑》2022年第7期4-6,共3页Information & Computer

基　　金：廊坊市科技支撑计划项目(项目编号:2021011024)。

摘　　要：话题跟踪任务用于跟踪话题的发展和变化,是舆情监控的关键模块之一。而话题/报道表示模型是话题跟踪任务的基础,用于对话题和报道进行建模,会从根本上影响话题跟踪性能。现有的话题/报道表示模型没有考虑话题和报道的结构特性,严重影响话题跟踪系统的性能。为了更好地表示话题和报道,提高话题跟踪性能,笔者在传统话题/报道表示模型的基础上加入话题结构特性,设计基于话题结构特性的话题/报道表示模型,用于构建话题结构特性融合话题/报道表示模型的话题跟踪系统。Topic tracking task is used to track the development and change of topics, and is one of key modules of public opinion monitoring. Topic/report representation model is the basis of topic tracking task, and is used to model topics and reports,which fundamentally affects topic tracking performance. Existing topic/report representation models fail to consider the structural characteristics of topic and report, which seriously affects the performance of topic tracking system. To better represent topics and reports and improve topic tracking performance, we adds topic structure characteristics to the traditional topic/report representation model, and design topic/report representation model based on topic structure characteristics, which is used to build topic tracking system of fusing topic structure characteristics into topic/report representation model.

关 键 词：话题跟踪 话题 报道 话题结构特性 话题检测与跟踪 

分 类 号：TP391.3[自动化与计算机技术—计算机应用技术]