WO2012083856A1 - 一种处理舆情话题的方法、装置和系统 - Google Patents

一种处理舆情话题的方法、装置和系统 Download PDF

Info

Publication number
WO2012083856A1
WO2012083856A1 PCT/CN2011/084381 CN2011084381W WO2012083856A1 WO 2012083856 A1 WO2012083856 A1 WO 2012083856A1 CN 2011084381 W CN2011084381 W CN 2011084381W WO 2012083856 A1 WO2012083856 A1 WO 2012083856A1
Authority
WO
WIPO (PCT)
Prior art keywords
lyric
topic
information
feature information
public opinion
Prior art date
Application number
PCT/CN2011/084381
Other languages
English (en)
French (fr)
Inventor
张丹
杨建武
梁汝锋
吴新丽
Original Assignee
北大方正集团有限公司
北京大学
北京北大方正电子有限公司
北京北大方正技术研究院有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 北大方正集团有限公司, 北京大学, 北京北大方正电子有限公司, 北京北大方正技术研究院有限公司 filed Critical 北大方正集团有限公司
Priority to US13/997,137 priority Critical patent/US20140052753A1/en
Priority to EP20110851529 priority patent/EP2657855A4/en
Priority to JP2013545028A priority patent/JP5816296B2/ja
Publication of WO2012083856A1 publication Critical patent/WO2012083856A1/zh

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90Details of database functions independent of the retrieved data types
    • G06F16/95Retrieval from the web
    • G06F16/951Indexing; Web crawling techniques
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90Details of database functions independent of the retrieved data types
    • G06F16/95Retrieval from the web
    • G06F16/958Organisation or management of web site content, e.g. publishing, maintaining pages or automatic linking

Definitions

  • the present invention relates to the field of communications, and more particularly to a method, apparatus and system for handling lyric topics. Background technique
  • Embodiments of the present invention provide a method, apparatus, and system for processing a lyric topic, and by acquiring and detecting feature information of a lyric topic, alerting a lyrical topic.
  • An embodiment of the present invention provides a method for processing a public opinion topic, the method comprising: searching a lyric topic including public opinion information in a network;
  • the lyric topic and its feature information are saved.
  • an embodiment of the present invention provides an apparatus for processing a public opinion topic, including: a retrieval module, configured to retrieve a lyric topic including public opinion information in a network;
  • An obtaining module configured to acquire feature information of the lyric topic
  • a detecting module configured to detect whether the feature information of the lyric topic meets an alarm condition
  • a storage module configured to save the lyric topic and its feature information when the alarm condition is met.
  • an embodiment of the present invention provides a system for processing a public opinion topic, including: a network side server and a device for handling lyric topics;
  • the network side server is configured to provide a lyric topic including public opinion information
  • the device for processing a lyric topic is configured to retrieve a lyric topic containing lyric information in the network; acquire feature information of the lyric topic, and detect whether the feature information of the lyric topic meets an alarm condition; when the alarm condition is met, save The lyric topic and its characteristic information.
  • An embodiment of the present invention provides a method, device, and system for processing a public opinion topic, which is used for retrieving a lyric topic containing public opinion information in a network; acquiring feature information of the lyrical topic, and detecting whether the feature information of the lyric topic matches Alarm condition; when the alarm condition is met, the lyric topic and its characteristic information are saved.
  • the method, device and system for processing lyric topics provided by the embodiments of the present invention provide early warning of lyric topics by acquiring and detecting feature information of lyric topics.
  • the saved lyric topics can be managed and continuously tracked to obtain trends in their communication, clicks, comments, etc., and to fully grasp the lyric topics. And you can analyze and sort out the lyric topics to generate a sensational report.
  • FIG. 1 is a schematic flowchart of a method for processing a public opinion topic according to an embodiment of the present invention
  • FIG. 2 is a schematic flowchart of a method for processing a public opinion topic according to another embodiment of the present invention.
  • FIG. 3 is a schematic diagram of an apparatus for processing a public opinion topic according to another embodiment of the present invention.
  • FIG. 4 is a schematic diagram of a system for processing a public opinion topic according to another embodiment of the present invention. detailed description
  • the embodiment of the present invention provides a method for processing a public opinion topic. As shown in FIG. 1, the method includes the following steps:
  • Step 101 Search for a lyric topic containing sensation information in the network
  • the user searches for the lyrical topic including the lyric information by inputting the sensation information, and can also select the lyric information stored in the database for searching, and the lyric information is pre-stored in the database and updated regularly.
  • the public opinion information of the lyrical topic stored in the database in advance may include the publisher, the publishing location, the publishing time, the title, the classification, etc., when the user searches for ⁇ When you are in a topic, you can actively provide the above information to the user.
  • Step 102 Obtain feature information of the lyric topic, and detect whether the feature information of the lyric topic meets the alarm condition.
  • the lyric topic may be obtained on a specified website or the entire network, for example, in a specified website, according to a preset.
  • the keyword rules and/or sample documents obtain the related topics and similarities of the lyric topic, and can be collected by using the web crawler technology during the specific implementation; and can also be obtained according to the whole network keyword of the lyric topic in all networks.
  • the related topics and similarities of the lyric topic can be implemented using meta-search techniques.
  • This step mainly provides raw statistics, that is, how many related topics and similarities of the lyrical topic are in the designated website or all networks.
  • the related topic includes the lyric topic itself. When conducting a full network search, you can mainly search for various types of sites, such as web pages, news, forums, and so on.
  • the above logical relationship between the keyword rule and the sample document may be "and” or "or”, wherein the keyword search adopts a complex condition of Boolean logic operation, and the sample document may adopt a single text segment or a multi-text segment.
  • relevant information can be found through different segments, and the situation of the lyric topic can be comprehensively obtained from multiple angles, and the problem of different description manners of the same event can be effectively solved.
  • the amount of change in the quantity and/or quantity of the feature information such as the sensitive information, the reload amount, the click volume, the comment volume, the duration length, and the associated topic amount in the network, and the preset alarm threshold. For comparison; if it is greater than the alarm threshold, the detection result is in accordance with the alarm condition; if it is not greater than the alarm threshold, the detection result is not in accordance with the alarm condition.
  • the above alarm threshold may be one or more, and corresponds to the feature information of the acquired lyric topic in specific use, for example, the click amount and the reply amount of the lyric topic are acquired, and the click alarm threshold and the reply amount alarm are used for detecting. Threshold.
  • the number of one or more feature information may be simultaneously used in the detection, and the quantity increase and the increase rate of the one or more feature information may be simultaneously used, and the number of one or more feature information may be used, and The amount of increase in the number of one or more feature information is used, and the like.
  • the text data of the webpage containing the lyric topic needs to be segmented, and then the sensitive information in the webpage text data is obtained according to the preset sensitive words.
  • the Chinese word segmentation technology is used to perform word segmentation processing on the webpage text data, and all words in the webpage text are analyzed in a positive order and a reverse order, and then the webpage is obtained according to the preset sensitive words.
  • the preset sensitive words are stored in the database, set according to sensitive words specified by national laws, or set by the user.
  • Step 103 When the alarm condition is met, the lyric topic and its feature information are saved.
  • the lyric topic and its feature information are saved, and the data mining technology can be used to periodically analyze and track the lyric topic, so as to know the progress of the lyric topic. For example, by periodically analyzing the reprinting of lyric topics and the changes in clicks and comments, a continuous tracking of the lyric topics is formed. The user can modify or set the timer to set or modify the specific time of the periodic analysis.
  • the analysis results can then be saved and displayed for the user to view.
  • they can be saved separately according to the analysis time, so as to view the related information of the lyric topic in a certain time period, the related information includes the distribution of the lyric topics, the amount of clicks and the amount of comments.
  • the related information includes the distribution of the lyric topics, the amount of clicks and the amount of comments.
  • a sensation report can be generated, for example, statistical analysis of the website, release time, and propagation path of the lyric topic, generating a sensation report and saving it in the analysis result, so as to assist the user better.
  • Grasp the law of lyric communication provide data basis for the development of public opinion treatment and grievances, and also check the guiding effect.
  • the sensation topic is alerted by acquiring and detecting the feature information of the lyric topic.
  • users can add topics as needed. They can also set up multiple sample texts or keywords at the same time, describe the topic from multiple angles, in order to comprehensively analyze the evolution of the topic; and choose to use the meta-search technology for Internet information. Conduct statistics to learn about the Internet's coverage of the lyrical topic.
  • the process of automatically analyzing lyric topics in the network including the reprinting, clicking, and commenting of related information in different time periods.
  • the law can be presented to the user in the form of a chart, thereby assisting the user to better grasp the law of lyric communication, and successfully complete the functions of the Internet lyric topic tracking system.
  • a detailed description, as shown in Figure 2 includes the following steps:
  • Step 201 Acquire public opinion information selected by the user
  • the user can input the public opinion information, and can also select among the provided public opinion information.
  • the grievance information includes but is not limited to: publisher, place of publication, time of publication, title, category.
  • Step 202 Search for a lyric topic that includes the public opinion information in the network
  • the search may be performed on a designated website or all networks to obtain the communication of the lyric topic.
  • the related topic may be obtained according to preset keyword rules and/or sample documents in the specified website.
  • the topic and similarity can be collected by using web crawler technology.
  • relevant topics and similarities of the lyric topic can be obtained according to the whole network keyword of the lyric topic, and the meta search can be used for specific implementation. technology.
  • the related topic includes the lyric topic itself. When searching across the web, you can search for various types of sites, such as web pages, news, forums, and more.
  • the above logical relationship between the keyword rule and the sample document may be "and” or "or”, wherein the keyword search adopts a complex condition of Boolean logic operation, and the sample document may adopt a single text segment or a multi-text segment.
  • the keyword search adopts a complex condition of Boolean logic operation
  • the sample document may adopt a single text segment or a multi-text segment.
  • Step 203 Acquire feature information of the lyric topic
  • the amount of change in the quantity and/or quantity of the characteristic information such as the sensitive information, the reload amount, the click volume, the comment volume, the duration duration, and the related topic amount in the network, and the preset alarm threshold are obtained. For comparison; if it is greater than the alarm threshold, the detection result is in accordance with the alarm condition; if it is not greater than the alarm threshold, the detection result is not in accordance with the alarm condition.
  • the alarm threshold may be one or more, and corresponds to the feature information of the acquired lyric topic in specific use, for example, when the click amount and the reply amount of the lyric topic are acquired, when the detection is performed, Use the click alert threshold and the reply alert threshold.
  • the number of one or more feature information may be simultaneously used in the detection, and the quantity increase and the increase rate of the one or more feature information may be simultaneously used, and the number of one or more feature information may be used, and The amount of increase in the number of one or more feature information is used, and the like.
  • the Chinese word segmentation technology is used to process the word segmentation of the webpage text data, and all the words in the webpage text are analyzed in a positive order and a reverse order, and then the sensitive words in the webpage are obtained according to the preset sensitive words.
  • the preset sensitive words are stored in the database, set according to sensitive words specified by national laws, or set by the user.
  • Step 204 Detect whether the feature information of the lyric topic meets the alarm condition; when one or more feature information of the lyric topic meets the alarm condition, save the lyric topic and its feature information, and perform regular analysis and tracking by using data mining technology.
  • a continuous tracking of the lyric topics is formed. The user can set or modify the specific time of the periodic analysis through the timer.
  • Step 205 When the alarm condition is met, save the lyric topic and its feature information; Step 206, periodically analyze the lyric topic, and save the analysis result; when one or more feature information of the lyric topic meets the alarm condition, the file may be saved.
  • the lyrical topic and its characteristic information can be analyzed and tracked regularly by using data mining technology to learn the progress of the lyric topic. For example, by periodically analyzing the reprint situation of the lyric topic and the change process of the click volume and the comment volume, a continuous tracking of the lyric topic is formed. The user can set or modify the specific time of the periodic analysis through the timer.
  • Step 207 Generate a sensation report according to relevant feature information of the lyric topic; perform statistical analysis on the website, release time, and propagation path of the lyric topic, and generate a sensation report, so as to assist the user to better grasp the law of public opinion communication, Provide a data basis for public opinion processing and public opinion guidance, and also view the guiding effect.
  • Step 208 View the analysis result.
  • the method for processing the lyric topic is used to obtain an early warning of the lyric topic by acquiring and detecting the feature information of the lyric topic. Moreover, it is possible to manage lyrical topics and conduct continuous tracking, analyze the trends of the spread, clicks, and comments of lyric topics, and provide early warning tips for topics that require early warning. It can also automatically analyze and analyze the public opinion information on the Internet to provide data materials for generating grievances. It further supports the comprehensive grasp of public opinion incidents, provides important support for public opinion handling and guiding decision-making, and continuously tracks and analyzes the effects of public opinion guidance.
  • users can add topics as needed. They can also set up multiple sample texts or keywords at the same time, describe the topic from multiple angles, in order to comprehensively analyze the evolution of the topic; and choose to use the meta-search technology for Internet information. Conduct statistics to learn about the Internet's coverage of the lyrical topic. Through the process of automatically analyzing the lyric topics in the network, including the information of the reprint, click, and comment of the relevant information in different time periods, and can be presented to the user in the form of a chart, thereby helping the user to better grasp the sensation The law of communication has successfully completed the functions of the Internet lyric topic tracking system.
  • the embodiment of the present invention further provides a device for processing a public opinion topic, as shown in FIG. 3, including:
  • a retrieval module 301 configured to retrieve a lyric topic containing lyric information in the network
  • an obtaining module 302 configured to acquire feature information of the lyric topic
  • the detecting module 303 is configured to detect whether the feature information of the lyric topic meets an alarm condition
  • the storage module 304 is configured to save the lyric topic and its characteristic information when the alarm condition is met.
  • the obtaining module 302 is configured to obtain an associated topic and similarity of the lyric topic according to preset keyword rules and/or sample documents in a specified website; and/or in all networks. Obtaining an associated topic and similarity of the lyric topic according to the whole network keyword of the lyric topic.
  • the obtaining module 302 is configured to perform word segmentation processing on the webpage text data including the lyric topic, and acquire sensitive information in the webpage text data according to the preset sensitive words.
  • the detecting module 303 is configured to obtain the quantity and/or the change amount of the feature information, and compare with a preset alarm threshold; if the alarm threshold is greater than the alarm threshold, the detection result is an alarm condition; If the alarm threshold is greater than the alarm threshold, the detection result is that the alarm condition is not met.
  • the device further includes: an analysis module 305, configured to periodically analyze the lyric topic and its feature information by using a data mining technology; save the analysis result and display.
  • the device further includes: a generating module 306, configured to generate a public opinion report according to the feature information of the lyric topic.
  • a generating module 306 configured to generate a public opinion report according to the feature information of the lyric topic.
  • the sensation topic is alerted by acquiring and detecting the feature information of the lyric topic.
  • users can add topics as needed. They can also set up multiple sample texts or keywords at the same time, describe the topic from multiple angles, in order to comprehensively analyze the evolution of the topic; and choose to use the meta-search technology for Internet information. Conduct statistics to learn about the Internet's coverage of the lyrical topic. Through the process of automatically analyzing the lyric topics in the network, including the information of the reprint, click, and comment of the relevant information in different time periods, and can be presented to the user in the form of a chart, thereby helping the user to better grasp the sensation The law of communication has successfully completed the functions of the Internet lyric topic tracking system.
  • the embodiment of the present invention further provides a system for processing a public opinion topic, as shown in FIG. 4, including: a network side server 401 and a device 402 for processing a public opinion topic;
  • the network side server 401 is configured to provide a public opinion including the public opinion information; the device 402 for processing the public opinion topic is configured to retrieve the public opinion including the public opinion information in the network; acquire the feature information of the public opinion topic, and detect the location Whether the characteristic information of the lyric topic meets the alarm condition; when the alarm condition is met, the lyric topic and its characteristic information are saved.
  • the method, the device and the system for processing the lyric topic provide an early warning to the lyric topic by acquiring and detecting the feature information of the lyric topic.
  • the newspaper provides data materials. It further supports the comprehensive grasp of public opinion incidents, provides important support for public opinion handling and guiding decision-making, and continuously tracks and analyzes the effects of public opinion guidance.
  • users can add topics as needed. They can also set up multiple sample texts or keywords at the same time, describe the topic from multiple angles, in order to comprehensively analyze the evolution of the topic; and choose to use the meta-search technology for Internet information. Conduct statistics to learn about the Internet's coverage of the lyrical topic. Through the process of automatically analyzing the lyric topics in the network, including the information of the reprint, click, and comment of the relevant information in different time periods, and can be presented to the user in the form of a chart, thereby helping the user to better grasp the sensation The law of communication has successfully completed the functions of the Internet lyric topic tracking system. It is within the spirit and scope of the invention. Therefore, it is intended that the present invention cover the modifications and variations of the invention and the scope of the invention.

Landscapes

  • Engineering & Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
  • Information Transfer Between Computers (AREA)

Description

一种处理舆情话题的方法、 装置和系统 技术领域
本发明涉及通信领域技术, 尤其涉及一种处理舆情话题的方法、 装 置和系统。 背景技术
随着互联网的迅猛发展, 其作为一块正在加速膨胀的思想阵地, 已 成为舆情事件的重要发生地和扩散地。新闻网站不断转载各种媒体报道 的事件; 再加上互联网的虚拟性、 隐蔽性、 发散性和渗透性等特点, 越 来越多的人愿意通过各种互动社区表达个人对舆情事件的看法。互联网 信息传播的速度极快, 网络舆情的爆发将以 "内容威胁" 的形式逐渐对 社会公共安全形成威胁, 对舆情话题的传播、 扩散、 网民评论情况越来 越难以全面掌握, 舆情事件的发展趋势难以控制。 发明内容
本发明实施例提供了一种处理舆情话题的方法、 装置和系统, 通过 获取并检测舆情话题的特征信息, 对舆情话题进行预警。
本发明实施例提供了一种处理舆情话题的方法, 该方法包括: 在网络中检索包含舆情信息的舆情话题;
获取所述舆情话题的特征信息, 检测所述舆情话题的特征信息是否 符合报警条件;
当符合报警条件时, 保存所述舆情话题及其特征信息。
相应的, 本发明实施例提供了一种处理舆情话题的装置, 包括: 检索模块, 用于在网络中检索包含舆情信息的舆情话题;
获取模块, 用于获取所述舆情话题的特征信息;
检测模块, 用于检测所述舆情话题的特征信息是否符合报警条件; 存储模块, 用于当符合报警条件时, 保存所述舆情话题及其特征信 息。
相应的, 本发明实施例提供了一种处理舆情话题的系统, 包括: 网 络侧服务器和处理舆情话题的装置;
所述网络侧服务器, 用于提供包含舆情信息的舆情话题;
所述处理舆情话题的装置, 用于在网络中检索包含舆情信息的舆情 话题; 获取所述舆情话题的特征信息, 检测所述舆情话题的特征信息是 否符合报警条件; 当符合报警条件时,保存所述舆情话题及其特征信息。
本发明实施例提供了一种处理舆情话题的方法、 装置及系统, 用于 在网络中检索包含舆情信息的舆情话题;获取所述舆情话题的特征信息, 检测所述舆情话题的特征信息是否符合报警条件; 当符合报警条件时, 保存所述舆情话题及其特征信息。 使用本发明实施例提供的处理舆情话 题的方法、 装置及系统, 通过获取并检测舆情话题的特征信息, 对舆情 话题进行预警。 而且, 可以对保存的舆情话题进行管理, 并持续追踪, 获取其传播、 点击、 评论等的变化趋势, 全面掌握舆情话题。 并且可以 对舆情话题进行分析整理, 生成舆情筒报。 附图说明
图 1为本发明实施例中处理舆情话题的方法流程示意图;
图 2为本发明另一实施例中处理舆情话题的方法流程示意图;
图 3为本发明另一实施例中处理舆情话题的装置示意图;
图 4为本发明另一实施例中处理舆情话题的系统示意图。 具体实施方式
下面结合各个附图对本发明实施例技术方案的主要实现原理、具体 实施方式及其对应能够达到的有益效果进行详细地阐述。
为了解决现有技术存在的问题,本发明实施例提供了一种处理舆情 话题的方法, 如图 1所示, 包括以下步骤:
步骤 101、 在网络中检索包含舆情信息的舆情话题;
具体的,用户通过输入舆情信息,检索包含该舆情信息的舆情话题, 还可以选择数据库中存储的舆情信息进行检索,该舆情信息预先保存在 数据库中并定期更新。 该预先在数据库中存储的舆情话题的舆情信息, 可以包括发布人、 发布地点、 发布时间、 标题、 分类等, 当用户检索舆 情话题时, 可以主动将上述舆情信息提供给用户。
步骤 102、 获取舆情话题的特征信息, 检测舆情话题的特征信息是 否符合报警条件; 具体的, 可以在指定网站或全网中获取舆情话题的传 播情况, 例如可以在指定的网站中, 根据预置的关键词规则和 /或样本 文档, 获取该舆情话题的相关联话题及相似度, 具体实现时可以使用网 络爬虫技术进行采集; 还可以在全部网络中, 根据舆情话题的全网关键 词, 获取该舆情话题的相关联话题及相似度, 具体实现时可以使用元搜 索技术。该步骤主要提供原始统计数据,即在指定网站或者全部网络中, 具有多少该舆情话题的相关联话题及相似度, 当然, 该相关联话题包括 舆情话题本身。 进行全网搜索时, 可以主要搜索各种类型的站点, 如网 页类、 新闻类、 论坛类博客类等。
上述在关键词规则和样本文档之间的逻辑关系可以是 "与", 也可 以是 "或", 其中关键词搜索采用布尔逻辑运算的复杂条件, 样本文档 可采用单一文本片段或多文本片段。 而且使用多样本文档方式时, 可以 通过不同片段找到相关信息, 多角度综合获知舆情话题的情况, 有效的 解决同一事件不同描述方式的问题。
还可以获取该舆情话题在网络中的敏感信息、 转载量、 点击量、 评 论量、 持续时间长度和相关联话题量等特征信息的数量和 /或数量的变 化量, 并与预置的报警阈值进行比较; 若大于报警阈值, 则检测结果为 符合报警条件; 若不大于报警阈值, 则检测结果为不符合报警条件。 上 述报警阈值可以为一项或者多项,具体使用时与获取的舆情话题的特征 信息相对应, 例如获取了舆情话题的点击量、 回复量, 则进行检测时使 用点击量报警阈值和回复量报警阈值。 而且, 检测时可以同时使用某一 个或多个特征信息的数量,还可以同时使用某一个或多个特征信息的数 量增加量、 增加率, 还可以既使用一个或多个特征信息的数量, 又使用 一个或多个特征信息的数量增加量等。
其中, 获取敏感信息时, 需要对包含舆情话题的网页文本数据进行 分词处理, 然后根据预置的敏感词, 获取网页文本数据中的敏感信息。 具体的, 运用中文分词技术对网页文本数据进行分词处理, 正序及倒序 的分析网页文本中的所有词, 然后根据预置的敏感词, 获取该网页中具 有的敏感词。 该预置的敏感词存储在数据库中, 根据国家法律规定的敏 感词进行设置, 或者用户自行设置。
步骤 103、 当符合报警条件时, 保存舆情话题及其特征信息。
具体的, 当该舆情话题的一个或多个特征信息符合报警条件时, 保 存该舆情话题及其特征信息,可以采用数据挖掘技术定期进行对其分析 及追踪, 以便获知该舆情话题的进展。 例如通过周期性分析舆情话题的 转载情况及点击量、评论量的变化过程,形成对该舆情话题的连续追踪。 用户可以通过修改定时器来设定或修改定期分析的具体时间。
然后,可以保存分析结果并展示, 以便用户查看。保存分析结果时, 可以按照分析时间的不同分别保存, 以便查看某个时间段中该舆情话题 的相关信息, 该相关信息包括舆情话题分布情况、 点击量及评论量等。 管理保存的多个舆情话题时, 还可以按照相似度进行分类, 查看时可以 在某类话题下查找相应的舆情话题的分析结果, 例如相关信息、 变化趋 势、 是否报警等。
此外, 还可以根据舆情话题的特征信息, 生成舆情筒报, 例如对舆 情话题的所属网站、 发布时间、 传播路径等进行统计分析, 生成舆情筒 报并保存在分析结果中, 以便辅助用户更好的把握舆情传播规律, 为制 定舆情处理和舆情 ^ )导提供数据依据, 还可以查看引导效果。
通过上述描述, 可以看出, 使用本发明实施例提供的处理舆情话题 的方法, 通过获取并检测舆情话题的特征信息, 对舆情话题进行预警。 而且能够对舆情话题进行管理,并进行持续追踪,分析舆情话题的传播、 点击、 评论的变化趋势, 对需要预警的话题进行预警提示。 还可以自动 对互联网上的舆论信息进行综合分析整理,为生成舆情筒报提供数据材 料。 进一步支撑全面掌握舆情事件, 为舆论处理和引导决策提供重要支 持, 持续追踪分析舆论引导的效果。
检索舆情话题时, 用户可以按照需要添加话题, 还可以同时设置多 篇样例文本或关键词, 多角度描述该话题, 以便全面分析话题的传播演 化趋势; 并可以选择通过元搜索技术对互联网信息进行统计, 了解互联 网中关于该舆情话题的报道情况。通过自动分析舆情话题在网络中传播 的过程, 包括其相关信息的转载、 点击、 评论等信息在不同时间段的变 化规律, 并可以以图表的方式展现给用户, 从而辅助用户更好地把握舆 情传播规律, 艮好的完成了互联网舆情话题追踪系统的各项功能。 进行详细说明, 如图 2所示, 包括以下步骤:
步骤 201、 获取用户选择的舆情信息;
具体的, 用户可以输入舆情信息, 也可以在提供的舆情信息中进行 选择。 该舆情信息包括但不限于: 发布人、发布地点、发布时间、 标题、 分类。
步骤 202、 在网络中检索包含该舆情信息的舆情话题;
具体的, 可以在指定的网站或全部网络中进行检索, 以便获取舆情 话题的传播情况, 例如可以在指定的网站中, 根据预置的关键词规则和 /或样本文档, 获取该舆情话题的相关联话题及相似度, 具体实现时可 以使用网络爬虫技术进行采集; 可以在全部网络中, 根据舆情话题的全 网关键词, 获取该舆情话题的相关话题及相似度, 具体实现时可以使用 元搜索技术。 这样, 可以获知在指定网站或者全部网络中, 具有多少该 舆情话题的相关话题联及相似度,还可以知道该话题的传播路径,当然, 该相关联话题包括舆情话题本身。 进行全网搜索时, 可以主要搜索各种 类型的站点, 如网页类、 新闻类、 论坛类博客类等。
上述在关键词规则和样本文档之间的逻辑关系可以是 "与", 也可 以是 "或", 其中关键词搜索采用布尔逻辑运算的复杂条件, 样本文档 可采用单一文本片段或多文本片段。 使用多样本文档方式时, 还可以通 过不同片段找到相关信息, 多角度综合获知舆情话题的情况, 有效的解 决同一事件不同描述方式的问题。
步骤 203、 获取该舆情话题的特征信息;
具体的, 获取该舆情话题在网络中的敏感信息、 转载量、 点击量、 评论量、 持续时间长度和相关话题量等特征信息的数量和 /或数量的变 化量, 并与预置的报警阈值进行比较; 若大于报警阈值, 则检测结果为 符合报警条件; 若不大于报警阈值, 则检测结果为不符合报警条件。 上 述报警阈值可以为一项或者多项,具体使用时与获取的舆情话题的特征 信息相对应, 例如获取了舆情话题的点击量、 回复量, 则进行检测时, 使用点击量报警阈值和回复量报警阈值。 而且, 检测时可以同时使用某 一个或多个特征信息的数量,还可以同时使用某一个或多个特征信息的 数量增加量、 增加率, 还可以既使用一个或多个特征信息的数量, 又使 用一个或多个特征信息的数量增加量等。
其中, 运用中文分词技术对网页文本数据进行分词处理, 正序及倒 序的分析网页文本中的所有词, 然后根据预置的敏感词, 获取该网页中 具有的敏感词。 该预置的敏感词存储在数据库中, 根据国家法律规定的 敏感词进行设置, 或者用户自行设置。
步骤 204、 检测舆情话题的特征信息是否符合报警条件; 当该舆情 话题的一个或多个特征信息符合报警条件时,保存该舆情话题及其特征 信息, 并可以采用数据挖掘技术定期进行分析及追踪, 以便获知该舆情 话题的进展。 例如通过周期性分析舆情话题的转载情况及点击量、 评论 量的变化过程, 形成对该舆情话题的连续追踪。 用户可以通过定时器设 定或修改定期分析的具体时间。
步骤 205、 当符合报警条件时, 保存该舆情话题及其特征信息; 步骤 206、 定期分析该舆情话题, 并保存分析结果; 当该舆情话题 的一个或多个特征信息符合报警条件时,可以保存该舆情话题及其特征 信息, 以便可以采用数据挖掘技术定期进行分析及追踪, 以便获知该舆 情话题的进展。 例如通过周期性分析舆情话题的转载情况及点击量、 评 论量的变化过程, 形成对该舆情话题的连续追踪。 用户可以通过定时器 设定或修改定期分析的具体时间。
步骤 207、 根据舆情话题的相关特征信息, 生成舆情筒报; 对舆情 话题的所属网站、发布时间、传播路径等进行统计分析,生成舆情筒报, 以便辅助用户更好的把握舆情传播规律,为制定舆情处理和舆情引导提 供数据依据, 还可以查看引导效果。
步骤 208、 查看分析结果。 管理保存的多个舆情话题时, 可以按照 相似度进行分类,查看时可以在某类话题下查找相应的舆情话题的分析 结果, 例如相关信息、 变化趋势、 是否报警等。
通过上述描述, 可以看出, 使用本发明实施例提供的处理舆情话题 的方法, 通过获取并检测舆情话题的特征信息, 对舆情话题进行预警。 而且能够对舆情话题进行管理,并进行持续追踪,分析舆情话题的传播、 点击、 评论的变化趋势, 对需要预警的话题进行预警提示。 还可以自动 对互联网上的舆论信息进行综合分析整理,为生成舆情筒报提供数据材 料。 进一步支撑全面掌握舆情事件, 为舆论处理和引导决策提供重要支 持, 持续追踪分析舆论引导的效果。
检索舆情话题时, 用户可以按照需要添加话题, 还可以同时设置多 篇样例文本或关键词, 多角度描述该话题, 以便全面分析话题的传播演 化趋势; 并可以选择通过元搜索技术对互联网信息进行统计, 了解互联 网中关于该舆情话题的报道情况。通过自动分析舆情话题在网络中传播 的过程, 包括其相关信息的转载、 点击、 评论等信息在不同时间段的变 化规律, 并可以以图表的方式展现给用户, 从而辅助用户更好地把握舆 情传播规律, 艮好的完成了互联网舆情话题追踪系统的各项功能。
相应的, 本发明实施例还提供了一种处理舆情话题的装置, 如图 3 所示, 包括:
检索模块 301 , 用于在网络中检索包含舆情信息的舆情话题; 获取模块 302, 用于获取所述舆情话题的特征信息;
检测模块 303 , 用于检测所述舆情话题的特征信息是否符合报警条 件;
存储模块 304, 用于当符合报警条件时, 保存所述舆情话题及其特 征信息。
较佳的, 该获取模块 302, 用于在指定的网站中, 根据预置的关键 词规则和 /或样本文档, 获取所述舆情话题的相关联话题及相似度; 和 / 或在全部网络中, 根据所述舆情话题的全网关键词, 获取所述舆情话题 的相关联话题及相似度。
较佳的, 该获取模块 302, 用于对包含所述舆情话题的网页文本数 据进行分词处理, 根据预置的敏感词, 获取所述网页文本数据中的敏感 信息。
较佳的, 该检测模块 303 , 用于获取所述特征信息的数量和 /或变化 量, 与预置的报警阈值进行比较; 若大于所述报警阈值, 则检测结果为 符合报警条件;若不大于所述报警阈值,则检测结果为不符合报警条件。 较佳的, 该装置还包括: 分析模块 305 , 用于采用数据挖掘技术, 定期分析所述舆情话题及其特征信息; 保存分析结果并展示。
较佳的, 该装置还包括: 生成模块 306, 用于根据所述舆情话题的 特征信息, 生成舆情筒报。
通过上述描述, 可以看出, 使用本发明实施例提供的处理舆情话题 的装置, 通过获取并检测舆情话题的特征信息, 对舆情话题进行预警。 而且能够对舆情话题进行管理,并进行持续追踪,分析舆情话题的传播、 点击、 评论的变化趋势, 对需要预警的话题进行预警提示。 还可以自动 对互联网上的舆论信息进行综合分析整理,为生成舆情筒报提供数据材 料。 进一步支撑全面掌握舆情事件, 为舆论处理和引导决策提供重要支 持, 持续追踪分析舆论引导的效果。
检索舆情话题时, 用户可以按照需要添加话题, 还可以同时设置多 篇样例文本或关键词, 多角度描述该话题, 以便全面分析话题的传播演 化趋势; 并可以选择通过元搜索技术对互联网信息进行统计, 了解互联 网中关于该舆情话题的报道情况。通过自动分析舆情话题在网络中传播 的过程, 包括其相关信息的转载、 点击、 评论等信息在不同时间段的变 化规律, 并可以以图表的方式展现给用户, 从而辅助用户更好地把握舆 情传播规律, 艮好的完成了互联网舆情话题追踪系统的各项功能。
相应的, 本发明实施例还提供了一种处理舆情话题的系统, 如图 4 所示, 包括: 网络侧服务器 401和处理舆情话题的装置 402;
所述网络侧服务器 401 , 用于提供包含舆情信息的舆情话题; 所述处理舆情话题的装置 402, 用于在网络中检索包含舆情信息的 舆情话题; 获取所述舆情话题的特征信息, 检测所述舆情话题的特征信 息是否符合报警条件; 当符合报警条件时, 保存所述舆情话题及其特征 信息。
通过上述描述, 可以看出, 使用本发明实施例提供的处理舆情话题 的方法、 装置和系统, 通过获取并检测舆情话题的特征信息, 对舆情话 题进行预警。 而且能够对舆情话题进行管理, 并进行持续追踪, 分析舆 情话题的传播、 点击、 评论的变化趋势, 对需要预警的话题进行预警提 示。 还可以自动对互联网上的舆论信息进行综合分析整理, 为生成舆情 筒报提供数据材料。 进一步支撑全面掌握舆情事件, 为舆论处理和引导 决策提供重要支持, 持续追踪分析舆论引导的效果。
检索舆情话题时, 用户可以按照需要添加话题, 还可以同时设置多 篇样例文本或关键词, 多角度描述该话题, 以便全面分析话题的传播演 化趋势; 并可以选择通过元搜索技术对互联网信息进行统计, 了解互联 网中关于该舆情话题的报道情况。通过自动分析舆情话题在网络中传播 的过程, 包括其相关信息的转载、 点击、 评论等信息在不同时间段的变 化规律, 并可以以图表的方式展现给用户, 从而辅助用户更好地把握舆 情传播规律, 艮好的完成了互联网舆情话题追踪系统的各项功能。 离本发明的精神和范围。 这样, 倘若本发明的这些修改和变型属于本发 明权利要求及其等同技术的范围之内,则本发明也意图包含这些改动和 变型在内。

Claims

权利要求:
1、 一种处理舆情话题的方法, 其特征在于, 该方法包括: 在网络中检索包含舆情信息的舆情话题;
获取所述舆情话题的特征信息,检测所述舆情话题的特征信息是否 符合报警条件;
当符合报警条件时, 保存所述舆情话题及其特征信息。
2、 如权利要求 1所述的方法, 其特征在于, 所述舆情信息包括: 选择的在数据库中保存并定期更新的舆情信息和 /或输入的舆情信 息。
3、 如权利要求 1所述的方法, 其特征在于, 所述获取所述舆情话 题的特征信息, 包括:
在指定的网站中, 根据预置的关键词规则和 /或样本文档, 获取所 述舆情话题的相关联话题及相似度; 和 /或
在全部网络中, 根据所述舆情话题的全网关键词, 获取所述舆情话 题的相关联话题及相似度。
4、 如权利要求 3所述的方法, 其特征在于, 所述舆情话题的特征 信息, 包括但不限于: 敏感信息、 转载量、 点击量、 评论量和相关联话 题量。
5、 如权利要求 4所述的方法, 其特征在于, 对包含所述舆情话题 的网页文本数据进行分词处理, 根据预置的敏感词, 获取所述网页文本 数据中的敏感信息。
6、 如权利要求 4所述的方法, 其特征在于, 所述检测所述舆情话 题的特征信息是否符合报警条件, 包括:
获取所述特征信息的数量和 /或变化量, 与预置的报警阈值进行比 较;
若大于所述报警阈值, 则检测结果为符合报警条件;
若不大于所述报警阈值, 则检测结果为不符合报警条件。
7、 如权利要求 1所述的方法, 其特征在于, 所述保存所述舆情话 题及其特征信息之后, 还包括:
采用数据挖掘技术, 定期分析所述舆情话题及其特征信息; 保存分析结果并展示。
8、 如权利要求 1所述的方法, 其特征在于, 所述保存所述舆情话 题及其特征信息之后, 还包括:
根据所述舆情话题的特征信息, 生成舆情筒报。
9、 一种处理舆情话题的装置, 其特征在于, 包括:
检索模块, 用于在网络中检索包含舆情信息的舆情话题; 获取模块, 用于获取所述舆情话题的特征信息;
检测模块, 用于检测所述舆情话题的特征信息是否符合报警条件; 存储模块, 用于当符合报警条件时, 保存所述舆情话题及其特征信 息。
10、 如权利要求 9所述的装置, 其特征在于, 所述获取模块, 用于 在指定的网站中, 根据预置的关键词规则和 /或样本文档, 获取所述舆 情话题的相关联话题及相似度; 和 /或在全部网络中, 根据所述舆情话 题的全网关键词, 获取所述舆情话题的相关联话题及相似度。
11、 如权利要求 9所述的装置, 其特征在于, 所述获取模块, 用于 对包含所述舆情话题的网页文本数据进行分词处理, 根据预置的敏感 词, 获取所述网页文本数据中的敏感信息。
12、 如权利要求 9所述的装置, 其特征在于, 检测模块, 用于获取 所述特征信息的数量和 /或变化量, 与预置的报警阈值进行比较; 若大 于所述报警阈值,则检测结果为符合报警条件;若不大于所述报警阈值, 则检测结果为不符合报警条件。
13、 如权利要求 9所述的装置, 其特征在于, 还包括: 分析模块, 用于采用数据挖掘技术, 定期分析所述舆情话题及其特征信息; 保存分 析结果并展示。
14、 如权利要求 9所述的装置, 其特征在于, 还包括: 生成模块, 用于根据所述舆情话题的特征信息, 生成舆情筒报。
15、 一种处理舆情话题的系统, 其特征在于, 包括: 网络侧服务器 和处理舆情话题的装置;
所述网络侧服务器, 用于提供包含舆情信息的舆情话题;
所述处理舆情话题的装置,用于在网络中检索包含舆情信息的舆情 话题; 获取所述舆情话题的特征信息, 检测所述舆情话题的特征信息是 否符合报警条件;当符合报警条件时,保存所述舆情话题及其特征信息。
PCT/CN2011/084381 2010-12-21 2011-12-21 一种处理舆情话题的方法、装置和系统 WO2012083856A1 (zh)

Priority Applications (3)

Application Number Priority Date Filing Date Title
US13/997,137 US20140052753A1 (en) 2010-12-21 2011-12-21 Method, device and system for processing public opinion topics
EP20110851529 EP2657855A4 (en) 2010-12-21 2011-12-21 METHOD, DEVICE AND SYSTEM FOR PROCESSING THEMES OF PUBLIC OPINION
JP2013545028A JP5816296B2 (ja) 2010-12-21 2011-12-21 世論トピックの処理方法、装置及びシステム

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201010614703.5 2010-12-21
CN2010106147035A CN102567393A (zh) 2010-12-21 2010-12-21 一种处理舆情话题的方法、装置和系统

Publications (1)

Publication Number Publication Date
WO2012083856A1 true WO2012083856A1 (zh) 2012-06-28

Family

ID=46313176

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2011/084381 WO2012083856A1 (zh) 2010-12-21 2011-12-21 一种处理舆情话题的方法、装置和系统

Country Status (5)

Country Link
US (1) US20140052753A1 (zh)
EP (1) EP2657855A4 (zh)
JP (1) JP5816296B2 (zh)
CN (1) CN102567393A (zh)
WO (1) WO2012083856A1 (zh)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111611464A (zh) * 2020-05-22 2020-09-01 河南智慧云大数据有限公司 一种基于大数据的舆情监测平台
CN112711651A (zh) * 2020-12-30 2021-04-27 上海金仕达软件科技有限公司 一种舆情监测方法及系统
CN113076737A (zh) * 2021-03-26 2021-07-06 三亚中科遥感研究所 一种融合公众情感的生态环境感知网络构建方法
CN113626717A (zh) * 2021-09-16 2021-11-09 平安国际智慧城市科技股份有限公司 一种舆情监测的方法、装置、电子设备和存储介质

Families Citing this family (40)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102968452A (zh) * 2012-10-25 2013-03-13 北京腾逸科技发展有限公司 网络舆情信息统计方法及系统
CN103854063B (zh) * 2012-11-29 2017-04-05 中国科学院计算机网络信息中心 一种基于互联网开放信息的事件发生风险预测并预警方法
CN103092950B (zh) * 2013-01-15 2016-01-06 重庆邮电大学 一种网络舆情地理位置实时监控系统和方法
CN104462096B (zh) * 2013-09-13 2017-11-14 北大方正集团有限公司 舆情监测分析方法和装置
CN104462118A (zh) * 2013-09-21 2015-03-25 郑建锋 控制信息传播风险的方法及系统
CN104657393A (zh) * 2013-11-25 2015-05-27 深圳市至高通信技术发展有限公司 一种舆情分析方法及相应的装置
CN105302844B (zh) * 2014-08-01 2019-07-16 腾讯科技(深圳)有限公司 互联网监测方法、装置及系统
CN105335422B (zh) * 2014-08-06 2019-02-22 阿里巴巴集团控股有限公司 舆情信息的告警方法及装置
CN105468990A (zh) * 2014-09-04 2016-04-06 中国移动通信集团安徽有限公司 一种敏感信息的管理控制方法和装置
CN104268194A (zh) * 2014-09-19 2015-01-07 国家电网公司 一种动态生成舆情简报的方法
CN104346735A (zh) * 2014-10-25 2015-02-11 廖学文 一种app食品安全鉴别系统
CN105653527A (zh) * 2014-11-11 2016-06-08 江苏威盾网络科技有限公司 一种基于网络爬虫技术的舆情处置及信息投放方法
CN104484359B (zh) * 2014-12-02 2018-03-23 北京锐安科技有限公司 一种基于社交图谱的舆情分析方法及装置
CN104834737A (zh) * 2015-05-19 2015-08-12 无锡天脉聚源传媒科技有限公司 一种基于电视报道的舆情处理方法和装置
US10430442B2 (en) 2016-03-09 2019-10-01 Symantec Corporation Systems and methods for automated classification of application network activity
CN107229609B (zh) 2016-03-25 2021-08-13 佳能株式会社 用于分割文本的方法和设备
CN106126558B (zh) * 2016-06-16 2019-09-20 东软集团股份有限公司 一种舆情监控方法及装置
CN107544988B (zh) * 2016-06-27 2021-03-19 百度在线网络技术(北京)有限公司 一种获取舆情数据的方法和装置
CN106302455A (zh) * 2016-08-16 2017-01-04 成都鼎昊科技有限公司 一种网络安全防护方法
US10666675B1 (en) 2016-09-27 2020-05-26 Ca, Inc. Systems and methods for creating automatic computer-generated classifications
CN106503209A (zh) * 2016-10-26 2017-03-15 Tcl集团股份有限公司 一种话题热度预测方法及系统
CN108053230A (zh) * 2017-11-29 2018-05-18 无锡雅座在线科技股份有限公司 舆情管理方法及装置
WO2019132648A1 (en) 2017-12-26 2019-07-04 Mimos Berhad System and method for identifying concern evolution within temporal and geospatial windows
CN108667842A (zh) * 2018-05-12 2018-10-16 苏州华必讯信息科技有限公司 一种处理舆情话题的方法、装置和系统
CN109033072A (zh) * 2018-06-27 2018-12-18 广东省新闻出版广电局 一种基于互联网的视听节目监管系统
CN110750636A (zh) * 2018-07-04 2020-02-04 百度在线网络技术(北京)有限公司 网络舆情信息处理方法及其装置
CN109446394A (zh) * 2018-09-27 2019-03-08 武汉大学 针对网络舆情事件的基于模块化的舆情监测方法及系统
CN108900219B (zh) * 2018-09-30 2023-06-23 郑州航空工业管理学院 一种网络舆情信息预警系统
CN109903176B (zh) * 2019-02-03 2020-04-10 内蒙古工业大学 一种基于流式云平台的实时舆情分析方法
CN110263233B (zh) * 2019-05-06 2023-04-07 平安科技(深圳)有限公司 企业舆情库构建方法、装置、计算机设备及存储介质
CN110389945A (zh) * 2019-06-05 2019-10-29 上海黑桃互动网络科技股份有限公司 一种游戏监控系统及监控方法
CN110705288A (zh) * 2019-09-29 2020-01-17 武汉海昌信息技术有限公司 一种基于大数据的舆情分析系统
US20210406484A1 (en) * 2020-06-25 2021-12-30 Seam Social Labs System and Method for a Natural Language Processing Tool
CN114386394A (zh) * 2020-10-16 2022-04-22 电科云(北京)科技有限公司 平台舆论数据主题的预测模型训练方法、预测方法及装置
CN112650947A (zh) * 2020-12-31 2021-04-13 安徽不如信息科技有限公司 一种便于携带的舆情收集处理系统
CN112711691B (zh) * 2021-01-08 2024-04-30 深圳市网联安瑞网络科技有限公司 网络舆情引导效果数据信息处理方法、系统、终端及介质
CN112818234B (zh) * 2021-02-02 2022-09-02 霍尔果斯大颜色信息科技有限公司 一种网络舆情信息分析处理方法及系统
CN112929235B (zh) * 2021-02-06 2022-02-11 珠海市鸿瑞信息技术股份有限公司 一种基于互联网的网络监测系统
CN113220533B (zh) * 2021-05-21 2024-05-31 南京诺迈特网络科技有限公司 一种网络舆情监控方法及系统
CN113282841B (zh) * 2021-07-19 2022-03-22 中国传媒大学 基于建模的公众话题传播评估方法及系统

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20090048997A (ko) * 2007-11-12 2009-05-15 주식회사 비즈모델라인 키워드를 통한 여론 자료 수집 방법 및 시스템과 이를 위한기록매체
CN101751458A (zh) * 2009-12-31 2010-06-23 暨南大学 一种网络舆情监控系统及方法
CN101763401A (zh) * 2009-12-30 2010-06-30 暨南大学 一种网络舆情的热点预测和分析方法
CN101819573A (zh) * 2009-09-15 2010-09-01 电子科技大学 一种自适应的网络舆情识别方法
CN101853261A (zh) * 2009-11-23 2010-10-06 电子科技大学 一种基于社会网络的网络舆情行为分析方法

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20060253421A1 (en) * 2005-05-06 2006-11-09 Fang Chen Method and product for searching title metadata based on user preferences
CN101408883B (zh) * 2008-11-24 2010-09-01 电子科技大学 一种网络舆情观点收集方法
CN101661513B (zh) * 2009-10-21 2011-04-06 上海交通大学 网络热点和舆情的检测方法

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20090048997A (ko) * 2007-11-12 2009-05-15 주식회사 비즈모델라인 키워드를 통한 여론 자료 수집 방법 및 시스템과 이를 위한기록매체
CN101819573A (zh) * 2009-09-15 2010-09-01 电子科技大学 一种自适应的网络舆情识别方法
CN101853261A (zh) * 2009-11-23 2010-10-06 电子科技大学 一种基于社会网络的网络舆情行为分析方法
CN101763401A (zh) * 2009-12-30 2010-06-30 暨南大学 一种网络舆情的热点预测和分析方法
CN101751458A (zh) * 2009-12-31 2010-06-23 暨南大学 一种网络舆情监控系统及方法

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111611464A (zh) * 2020-05-22 2020-09-01 河南智慧云大数据有限公司 一种基于大数据的舆情监测平台
CN112711651A (zh) * 2020-12-30 2021-04-27 上海金仕达软件科技有限公司 一种舆情监测方法及系统
CN113076737A (zh) * 2021-03-26 2021-07-06 三亚中科遥感研究所 一种融合公众情感的生态环境感知网络构建方法
CN113076737B (zh) * 2021-03-26 2023-01-31 三亚中科遥感研究所 一种融合公众情感的生态环境感知网络构建方法
CN113626717A (zh) * 2021-09-16 2021-11-09 平安国际智慧城市科技股份有限公司 一种舆情监测的方法、装置、电子设备和存储介质

Also Published As

Publication number Publication date
US20140052753A1 (en) 2014-02-20
JP2014511513A (ja) 2014-05-15
EP2657855A1 (en) 2013-10-30
EP2657855A4 (en) 2014-08-13
JP5816296B2 (ja) 2015-11-18
CN102567393A (zh) 2012-07-11

Similar Documents

Publication Publication Date Title
WO2012083856A1 (zh) 一种处理舆情话题的方法、装置和系统
Song et al. Temporally evolving graph neural network for fake news detection
Hasan et al. Real-time event detection from the Twitter data stream using the TwitterNews+ Framework
US11138378B2 (en) Intelligently summarizing and presenting textual responses with machine learning
Alzanin et al. Detecting rumors in social media: A survey
US8782033B2 (en) Entity following
Hasan et al. TwitterNews+: a framework for real time event detection from the Twitter data stream
Qian et al. On detecting business event from the headlines and leads of massive online news articles
US11803600B2 (en) Systems and methods for intelligent content filtering and persistence
Boididou et al. Learning to detect misleading content on twitter
Chen et al. Proactive discovery of fake news domains from real-time social media feeds
Yao et al. Comparing tweet sentiments in megacities using machine learning techniques: In the midst of COVID-19
Kokkinogenis et al. Mobility network evaluation in the user perspective: Real-time sensing of traffic information in twitter messages
Alsaedi et al. A combined classification-clustering framework for identifying disruptive events
Yang et al. Task-oriented keyphrase extraction from social media
Ramachandran et al. Event detection from Twitter–a survey
Berendt Text Mining for News and Blogs Analysis.
Pandya et al. Mated: metadata-assisted twitter event detection system
Chua et al. Problem Understanding of Fake News Detection from a Data Mining Perspective
Kalra et al. Multimodal fake news detection on fakeddit dataset using transformer-based architectures
Lee et al. Event evolution tracking from streaming social posts
CN108667842A (zh) 一种处理舆情话题的方法、装置和系统
Xie et al. Tracking large-scale video remix in real-world events
Afyouni et al. E-ware: a big data system for the incremental discovery of spatio-temporal events from microblogs
Liu et al. RoseMatcher: Identifying the impact of user reviews on app updates

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 11851529

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2013545028

Country of ref document: JP

Kind code of ref document: A

NENP Non-entry into the national phase

Ref country code: DE

REEP Request for entry into the european phase

Ref document number: 2011851529

Country of ref document: EP

WWE Wipo information: entry into national phase

Ref document number: 2011851529

Country of ref document: EP

WWE Wipo information: entry into national phase

Ref document number: 13997137

Country of ref document: US