CN105447081A - Cloud platform-oriented government affair and public opinion monitoring method - Google Patents
Cloud platform-oriented government affair and public opinion monitoring method Download PDFInfo
- Publication number
- CN105447081A CN105447081A CN201510746977.2A CN201510746977A CN105447081A CN 105447081 A CN105447081 A CN 105447081A CN 201510746977 A CN201510746977 A CN 201510746977A CN 105447081 A CN105447081 A CN 105447081A
- Authority
- CN
- China
- Prior art keywords
- data
- text
- node
- analysis
- task
- Prior art date
- Legal status (The legal status 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 status listed.)
- Withdrawn
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/951—Indexing; Web crawling techniques
Abstract
The present invention relates to the technical field of cloud computing, and particularly relates to a cloud platform-oriented government affair and public opinion monitoring method. The method disclosed by the present invention comprises data collection, data pre-processing, data analysis and early warning. A system is installed on a distributed cluster and consists of a crawler server used as a main node and a plurality of crawler clients used as slave nodes, wherein the main mode is in charge of distributing tasks, the slave nodes are in charge of executing the tasks and communication is performed by an encrypted heartbeat packet between the main node and the slave nodes; each slave node comprises a data acquisition module, a data pre-processing module, a data analysis and early warning module; the data acquisition module captures data in a forum, news, a post bar, a blog and the like according to a user configuration and a knowledge base, and automatically filters the repeated data to form a subject database; the data pre-processing module extracts body text data based on rules and an automatic mixing manner; and the data analysis module and the early warning module perform clustering, sentiment analysis and hot spot analysis on a cleaned text by using a machine learning method and perform early warning on an analysis result. The method provided by the present invention solves problems of network public opinion monitoring and the like of users and can be used for monitoring government affairs and public opinions.
Description
Technical field
The present invention relates to field of cloud computer technology, especially a kind of government affairs public sentiment method for supervising of facing cloud platform.
Background technology
Based on the distributed real-time intelligent method for supervising of cloud database, integrate internet information acquisition technology and information intelligent treatment technology, by to internet mass information automatic capturing, automatic classification cluster, topic detection, focus on special topic, realize network public-opinion monitoring and the information requirement such as Special Topics in Journalism tracking of user, form the analysis results such as bulletin, report, chart, for client grasps masses' thought dynamically comprehensively, make right opinion and guide, analysis foundation is provided.
Summary of the invention
The technical matters that the present invention solves is a kind of government affairs public sentiment method for supervising providing facing cloud platform.
The technical scheme that the present invention solves the problems of the technologies described above is:
Described method comprises data acquisition, data prediction, data analysis and early warning; Described system is mounted on distributed type assemblies, by a crawler server as host node with multiplely to form as the reptile client from node, host node is responsible for task matching, and child node is responsible for tasks carrying, adopts the heartbeat packet of encryption to communicate between main and subordinate node; Data acquisition, pre-service, analysis and warning module is comprised from node; Described acquisition module captures the data such as forum, news, mhkc, blog according to user's configuration and knowledge base, and automatic fitration repeating data, build subject data base; Data preprocessing module mode that is rule-based and automatic mixing extracts textual data; Data analysis and warning module utilize the method for machine learning to carry out cluster, sentiment analysis, analysis of central issue to the text after cleaning, and carry out early warning to analysis result.
Communication between described main and subordinate node, comprises the steps:
The first step, user opens acquisition tasks;
Second step, host node preserves mission bit stream to metadata information storehouse;
3rd step, host node carries out task initialization according to user configuration information;
4th step, host node carries out task matching according to the index such as CPU, internal memory, current task number of Cong Jiedian;
5th step, receives task from node;
6th step, sends from node and successfully receives task message to host node;
7th step, host node writing task information is to metadatabase;
8th step, executes the task from node;
9th step, if host node does not receive for N time from nodes heart beat bag, is then considered as Cong Jiedian and delays machine be recorded to log system, and allocating task gives other nodes again.
The concrete treatment scheme of described acquisition module is:
The first step, obtains URL to be collected;
Second step, is filtered URL by data router;
3rd step, captures page data;
4th step, carries out text extraction, linkage extraction to the data captured, and the link extracted is added URL to be collected and gathers;
5th step, aspects for automatic text are extracted, generating web page fingerprint;
Whether the 6th step, detect for there being identical article;
7th step, if existing identical article, abandons crawl and returns the first step, otherwise carry out participle operation to body text;
8th step, extracts N number of keyword with TF_IDF algorithm;
9th step, finds the m section article the highest with its registration;
Tenth step, if its registration is greater than c, is classified as corresponding subject data base;
11 step, sets up inverted index and uses for other modules.
Described data analysis and the concrete treatment scheme of warning module are:
The first step, is reconstructed subject data base, selects representational data;
Second step, carries out sentiment analysis to every section of document and calculates score value Tendency ∈ [-1,1];
3rd step, charges to warning data storehouse to above-mentioned analysis result;
4th step, calculates warning level,
wherein degree
irepresent the temperature of i-th section of document, its computing formula is:
degree
i＝(praise
i×0.3+comment
i×0.7)/(hour
i+2)
Wherein: praise
irepresentative praises number, comment
irepresentative comment number, hour
irepresentative is posted the time difference till now time;
5th step, gives the corresponding early warning information such as email or note according to prediction policy and warning level.
Described aspects for automatic text are extracted, and the step of generating web page fingerprint is:.
The first step, extracts the main feature of each paragraph of text first sentence keyword (removing stop words) as article;
Second step, extracts the punctuation mark of each paragraph of text as secondary feature;
3rd step, uses SimHash to the secondary feature of main characteristic sum respectively, then splices two sections of condition codes, obtain the fingerprint of whole article;
4th step, stored in cache database.
The present invention adopts the mode of distributed multithreading to improve grasp speed, improves the ageing of news; Detect text repeatability by URL duplicate removal and use text similarity measurement algorithm, thus save disk space, also improve grasp speed simultaneously; Speed and the accuracy of the detection of webpage repeatability is improve by web page fingerprint algorithm.
Accompanying drawing explanation
Below in conjunction with accompanying drawing, the present invention is further described:
Fig. 1 is that the present invention uses frame diagram;
Fig. 2 is main and subordinate node Organization Chart;
Fig. 3 is heart data grabber process flow diagram;
Fig. 4 is data analysis flowcharts.
Embodiment
As shown in Figures 1 to 4, the inventive method comprises data acquisition, data prediction, data analysis and early warning; Described system is mounted on distributed type assemblies, by a crawler server as host node with multiplely to form as the reptile client from node, host node is responsible for task matching, and child node is responsible for tasks carrying, adopts the heartbeat packet of encryption to communicate between main and subordinate node; Data acquisition, pre-service, analysis and warning module is comprised from node; Described acquisition module captures the data such as forum, news, mhkc, blog according to user's configuration and knowledge base, and automatic fitration repeating data, build subject data base; Data preprocessing module mode that is rule-based and automatic mixing extracts textual data; Data analysis and warning module utilize the method for machine learning to carry out cluster, sentiment analysis, analysis of central issue to the text after cleaning, and carry out early warning to analysis result.
As shown in Figure 2: a described host node and multiple from node composition, host node is responsible for task matching, and child node is responsible for tasks carrying, adopts the heartbeat packet of encryption to communicate, comprise the steps: between main and subordinate node
The first step, user opens acquisition tasks;
Second step, host node preserves mission bit stream to metadata information storehouse;
3rd step, host node carries out task initialization according to user configuration information;
4th step, host node carries out task matching according to the index such as CPU, internal memory, current task number of Cong Jiedian;
5th step, receives task from node;
6th step, sends from node and successfully receives task message to host node;
7th step, host node writing task information is to metadatabase;
8th step, executes the task from node;
9th step, if host node does not receive for N time from nodes heart beat bag, is then considered as Cong Jiedian and delays machine be recorded to log system, and allocating task gives other nodes again.
As shown in Figure 3: described acquisition module captures the data such as forum, news, mhkc, blog according to user's configuration and knowledge base, and filters repeating data, builds subject data base, comprises following flow process:
The first step, obtains URL to be collected;
Second step, is filtered URL by data router;
3rd step, captures page data;
4th step, carries out text extraction, linkage extraction to the data captured, and the link extracted is added URL to be collected and gathers;
5th step, aspects for automatic text are extracted, generating web page fingerprint;
Whether the 6th step, detect for there being identical article;
7th step, if existing identical article, abandons crawl and returns the first step, otherwise carry out participle operation to body text;
8th step, extracts N number of keyword with TF_IDF algorithm;
9th step, finds the m section article the highest with its registration;
Tenth step, if its registration is greater than c, is classified as corresponding subject data base;
11 step, sets up inverted index and uses for other modules.
As shown in Figure 4, data analysis module utilizes the method for machine learning to carry out cluster, sentiment analysis, analysis of central issue to the text after cleaning, and carries out early warning to analysis result, comprises the steps:
The first step, is reconstructed subject data base, selects representational data;
Second step, carries out sentiment analysis to every section of document and calculates score value Tendency ∈ [-1,1];
3rd step, charges to warning data storehouse to above-mentioned analysis result;
4th step, calculates warning level,
wherein degree
irepresent the temperature of i-th section of document, its computing formula is:
degree
i＝(praise
i×0.3+comment
i×0.7)/(hour
i+2)
Wherein: praise
irepresentative praises number, comment
irepresentative comment number, hour
irepresentative is posted the time difference till now time;
5th step, gives the corresponding early warning information such as email or note according to prediction policy and warning level.
As shown in Figure 1, adopt the inventive method to obtain information to show in WEB front-end.
Claims (7)
1., towards a kind of public sentiment method for real-time monitoring of government affairs, it is characterized in that: described method comprises data acquisition, data prediction, data analysis and early warning; Described system is mounted on distributed type assemblies, by a crawler server as host node with multiplely to form as the reptile client from node, host node is responsible for task matching, and child node is responsible for tasks carrying, adopts the heartbeat packet of encryption to communicate between main and subordinate node; Data acquisition, pre-service, analysis and warning module is comprised from node; Described acquisition module captures the data such as forum, news, mhkc, blog according to user's configuration and knowledge base, and automatic fitration repeating data, build subject data base; Data preprocessing module mode that is rule-based and automatic mixing extracts textual data; Data analysis and warning module utilize the method for machine learning to carry out cluster, sentiment analysis, analysis of central issue to the text after cleaning, and carry out early warning to analysis result.
2. a kind of public sentiment method for real-time monitoring towards government affairs according to claim 1, is characterized in that: the communication between described main and subordinate node, comprises the steps:
The first step, user opens acquisition tasks;
Second step, host node preserves mission bit stream to metadata information storehouse;
3rd step, host node carries out task initialization according to user configuration information;
4th step, host node carries out task matching according to the index such as CPU, internal memory, current task number of Cong Jiedian;
5th step, receives task from node;
6th step, sends from node and successfully receives task message to host node;
7th step, host node writing task information is to metadatabase;
8th step, executes the task from node;
9th step, if host node does not receive for N time from nodes heart beat bag, is then considered as Cong Jiedian and delays machine be recorded to log system, and allocating task gives other nodes again.
3. a kind of public sentiment method for real-time monitoring towards government affairs according to claim 1, is characterized in that: the concrete treatment scheme of described acquisition module is:
The first step, obtains URL to be collected;
Second step, is filtered URL by data router;
3rd step, captures page data;
4th step, carries out text extraction, linkage extraction to the data captured, and the link extracted is added URL to be collected and gathers;
5th step, aspects for automatic text are extracted, generating web page fingerprint;
Whether the 6th step, detect for there being identical article;
7th step, if existing identical article, abandons crawl and returns the first step, otherwise carry out participle operation to body text;
8th step, extracts N number of keyword with TF_IDF algorithm;
9th step, finds the m section article the highest with its registration;
Tenth step, if its registration is greater than c, is classified as corresponding subject data base;
11 step, sets up inverted index and uses for other modules.
4. a kind of public sentiment method for real-time monitoring towards government affairs according to claim 2, is characterized in that: the concrete treatment scheme of described acquisition module is:
The first step, obtains URL to be collected;
Second step, is filtered URL by data router;
3rd step, captures page data;
4th step, carries out text extraction, linkage extraction to the data captured, and the link extracted is added URL to be collected and gathers;
5th step, aspects for automatic text are extracted, generating web page fingerprint;
Whether the 6th step, detect for there being identical article;
7th step, if existing identical article, abandons crawl and returns the first step, otherwise carry out participle operation to body text;
8th step, extracts N number of keyword with TF_IDF algorithm;
9th step, finds the m section article the highest with its registration;
Tenth step, if its registration is greater than c, is classified as corresponding subject data base;
11 step, sets up inverted index and uses for other modules.
5. a kind of public sentiment method for real-time monitoring towards government affairs according to any one of Claims 1-4, is characterized in that: described data analysis and the concrete treatment scheme of warning module are:
The first step, is reconstructed subject data base, selects representational data;
Second step, carries out sentiment analysis to every section of document and calculates score value Tendency ∈ [-1,1];
3rd step, charges to warning data storehouse to above-mentioned analysis result;
4th step, calculates warning level,
wherein degree
irepresent the temperature of i-th section of document, its computing formula is:
degree
i＝(praise
i×0.3+comment
i×0.7)/(hour
i+2)
Wherein: praise
irepresentative praises number, comment
irepresentative comment number, hour
irepresentative is posted the time difference till now time;
5th step, gives the corresponding early warning information such as email or note according to prediction policy and warning level.
6. a kind of public sentiment method for real-time monitoring towards government affairs according to claim 3 or 4, is characterized in that: described aspects for automatic text are extracted, and the step of generating web page fingerprint is:
The first step, extracts the main feature of each paragraph of text first sentence keyword (removing stop words) as article;
Second step, extracts the punctuation mark of each paragraph of text as secondary feature;
3rd step, uses SimHash to the secondary feature of main characteristic sum respectively, then splices two sections of condition codes, obtain the fingerprint of whole article;
4th step, stored in cache database.
7. a kind of public sentiment method for real-time monitoring towards government affairs according to claim 5, is characterized in that: described aspects for automatic text are extracted, and the step of generating web page fingerprint is:
The first step, extracts the main feature of each paragraph of text first sentence keyword (removing stop words) as article;
Second step, extracts the punctuation mark of each paragraph of text as secondary feature;
3rd step, uses SimHash to the secondary feature of main characteristic sum respectively, then splices two sections of condition codes, obtain the fingerprint of whole article;
4th step, stored in cache database.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510746977.2A CN105447081A (en) | 2015-11-04 | 2015-11-04 | Cloud platform-oriented government affair and public opinion monitoring method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510746977.2A CN105447081A (en) | 2015-11-04 | 2015-11-04 | Cloud platform-oriented government affair and public opinion monitoring method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105447081A true CN105447081A (en) | 2016-03-30 |
Family
ID=55557259
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510746977.2A Withdrawn CN105447081A (en) | 2015-11-04 | 2015-11-04 | Cloud platform-oriented government affair and public opinion monitoring method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105447081A (en) |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106302455A (en) * | 2016-08-16 | 2017-01-04 | 成都鼎昊科技有限公司 | A kind of network safety protection method |
| CN106934014A (en) * | 2017-03-10 | 2017-07-07 | 山东省科学院情报研究所 | A kind of network data excavation based on Hadoop and analysis platform and its method |
| CN107169143A (en) * | 2017-06-15 | 2017-09-15 | 易联众信息技术股份有限公司 | A kind of efficient magnanimity public sentiment data message trunking matching process |
| CN107580036A (en) * | 2017-08-28 | 2018-01-12 | 成都融微软件服务有限公司 | The method of the adaptive single-point acquiring of industry information service |
| CN107800789A (en) * | 2017-10-24 | 2018-03-13 | 麦格创科技（深圳）有限公司 | The distribution method and system of task manager in distributed reptile system |
| CN107818130A (en) * | 2017-09-15 | 2018-03-20 | 深圳市电陶思创科技有限公司 | The method for building up and system of a kind of search engine |
| CN108021582A (en) * | 2016-11-04 | 2018-05-11 | 中国移动通信集团湖南有限公司 | Internet public feelings monitoring method and device |
| CN109739849A (en) * | 2019-01-02 | 2019-05-10 | 山东省科学院情报研究所 | A kind of network sensitive information of data-driven excavates and early warning platform |
| CN110046132A (en) * | 2019-04-15 | 2019-07-23 | 苏州浪潮智能科技有限公司 | A kind of metadata request processing method, device, equipment and readable storage medium storing program for executing |
| CN110413863A (en) * | 2019-08-01 | 2019-11-05 | 信雅达系统工程股份有限公司 | A kind of public sentiment news duplicate removal and method for pushing based on deep learning |
| CN110533212A (en) * | 2019-07-04 | 2019-12-03 | 西安理工大学 | Urban waterlogging public sentiment monitoring and pre-alarming method based on big data |
| CN110781236A (en) * | 2019-10-29 | 2020-02-11 | 山西云时代技术有限公司 | Method for constructing government affair big data management system |
| CN111428176A (en) * | 2020-03-04 | 2020-07-17 | 北京明略软件系统有限公司 | User behavior acquisition method and device |
| CN112100474A (en) * | 2020-11-02 | 2020-12-18 | 成都智元汇信息技术股份有限公司 | Passenger service quality public opinion supervision system and method |
| CN113609424A (en) * | 2021-06-22 | 2021-11-05 | 深圳市网联安瑞网络科技有限公司 | Computing and early warning system and method for network public sentiment popularity |
| CN116862455A (en) * | 2023-09-01 | 2023-10-10 | 中国标准化研究院 | Multi-mode-based government service complaint early warning method and device |
| CN116861058A (en) * | 2023-09-04 | 2023-10-10 | 浪潮软件股份有限公司 | Public opinion monitoring system and method applied to government affair field |
| CN116861058B (en) * | 2023-09-04 | 2024-04-12 | 浪潮软件股份有限公司 | Public opinion monitoring system and method applied to government affair field |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101499098A (en) * | 2009-03-04 | 2009-08-05 | 阿里巴巴集团控股有限公司 | Web page assessed value confirming and employing method and system |
| CN102194001A (en) * | 2011-05-17 | 2011-09-21 | 杭州电子科技大学 | Internet public opinion crisis early-warning method |
| CN104899324A (en) * | 2015-06-19 | 2015-09-09 | 成都国腾实业集团有限公司 | Sample training system based on IDC (internet data center) harmful information monitoring system |
| CN104951539A (en) * | 2015-06-19 | 2015-09-30 | 成都艾尔普科技有限责任公司 | Internet data center harmful information monitoring system |
-
2015
- 2015-11-04 CN CN201510746977.2A patent/CN105447081A/en not_active Withdrawn
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101499098A (en) * | 2009-03-04 | 2009-08-05 | 阿里巴巴集团控股有限公司 | Web page assessed value confirming and employing method and system |
| US20100228718A1 (en) * | 2009-03-04 | 2010-09-09 | Alibaba Group Holding Limited | Evaluation of web pages |
| CN102194001A (en) * | 2011-05-17 | 2011-09-21 | 杭州电子科技大学 | Internet public opinion crisis early-warning method |
| CN104899324A (en) * | 2015-06-19 | 2015-09-09 | 成都国腾实业集团有限公司 | Sample training system based on IDC (internet data center) harmful information monitoring system |
| CN104951539A (en) * | 2015-06-19 | 2015-09-30 | 成都艾尔普科技有限责任公司 | Internet data center harmful information monitoring system |
Cited By (23)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106302455A (en) * | 2016-08-16 | 2017-01-04 | 成都鼎昊科技有限公司 | A kind of network safety protection method |
| CN108021582B (en) * | 2016-11-04 | 2020-12-04 | 中国移动通信集团湖南有限公司 | Internet public opinion monitoring method and device |
| CN108021582A (en) * | 2016-11-04 | 2018-05-11 | 中国移动通信集团湖南有限公司 | Internet public feelings monitoring method and device |
| CN106934014A (en) * | 2017-03-10 | 2017-07-07 | 山东省科学院情报研究所 | A kind of network data excavation based on Hadoop and analysis platform and its method |
| CN106934014B (en) * | 2017-03-10 | 2021-03-19 | 山东省科学院情报研究所 | Hadoop-based network data mining and analyzing platform and method thereof |
| CN107169143A (en) * | 2017-06-15 | 2017-09-15 | 易联众信息技术股份有限公司 | A kind of efficient magnanimity public sentiment data message trunking matching process |
| CN107169143B (en) * | 2017-06-15 | 2020-06-16 | 易联众信息技术股份有限公司 | Efficient mass public opinion data information cluster matching method |
| CN107580036A (en) * | 2017-08-28 | 2018-01-12 | 成都融微软件服务有限公司 | The method of the adaptive single-point acquiring of industry information service |
| CN107818130A (en) * | 2017-09-15 | 2018-03-20 | 深圳市电陶思创科技有限公司 | The method for building up and system of a kind of search engine |
| CN107800789A (en) * | 2017-10-24 | 2018-03-13 | 麦格创科技（深圳）有限公司 | The distribution method and system of task manager in distributed reptile system |
| CN109739849A (en) * | 2019-01-02 | 2019-05-10 | 山东省科学院情报研究所 | A kind of network sensitive information of data-driven excavates and early warning platform |
| CN109739849B (en) * | 2019-01-02 | 2021-06-29 | 山东省科学院情报研究所 | Data-driven network sensitive information mining and early warning platform |
| CN110046132A (en) * | 2019-04-15 | 2019-07-23 | 苏州浪潮智能科技有限公司 | A kind of metadata request processing method, device, equipment and readable storage medium storing program for executing |
| CN110046132B (en) * | 2019-04-15 | 2022-04-22 | 苏州浪潮智能科技有限公司 | Metadata request processing method, device, equipment and readable storage medium |
| CN110533212A (en) * | 2019-07-04 | 2019-12-03 | 西安理工大学 | Urban waterlogging public sentiment monitoring and pre-alarming method based on big data |
| CN110413863A (en) * | 2019-08-01 | 2019-11-05 | 信雅达系统工程股份有限公司 | A kind of public sentiment news duplicate removal and method for pushing based on deep learning |
| CN110781236A (en) * | 2019-10-29 | 2020-02-11 | 山西云时代技术有限公司 | Method for constructing government affair big data management system |
| CN111428176A (en) * | 2020-03-04 | 2020-07-17 | 北京明略软件系统有限公司 | User behavior acquisition method and device |
| CN112100474A (en) * | 2020-11-02 | 2020-12-18 | 成都智元汇信息技术股份有限公司 | Passenger service quality public opinion supervision system and method |
| CN113609424A (en) * | 2021-06-22 | 2021-11-05 | 深圳市网联安瑞网络科技有限公司 | Computing and early warning system and method for network public sentiment popularity |
| CN116862455A (en) * | 2023-09-01 | 2023-10-10 | 中国标准化研究院 | Multi-mode-based government service complaint early warning method and device |
| CN116861058A (en) * | 2023-09-04 | 2023-10-10 | 浪潮软件股份有限公司 | Public opinion monitoring system and method applied to government affair field |
| CN116861058B (en) * | 2023-09-04 | 2024-04-12 | 浪潮软件股份有限公司 | Public opinion monitoring system and method applied to government affair field |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105447081A (en) | Cloud platform-oriented government affair and public opinion monitoring method | |
| CN104537097B (en) | Microblogging public sentiment monitoring system | |
| CN104504150B (en) | News public sentiment monitoring system | |
| Papadopoulou et al. | A corpus of debunked and verified user-generated videos | |
| Salloum et al. | Mining text in news channels: a case study from Facebook | |
| CN101814083A (en) | Automatic webpage classification method and system | |
| CN104899324B (en) | One kind monitoring systematic sample training system based on IDC harmful informations | |
| CN104077377A (en) | Method and device for finding network public opinion hotspots based on network article attributes | |
| CN103116605A (en) | Method and system of microblog hot events real-time detection based on detection subnet | |
| CN107885793A (en) | A kind of hot microblog topic analyzing and predicting method and system | |
| Bansal et al. | Towards deep semantic analysis of hashtags | |
| CN104750704A (en) | Webpage uniform resource locator (URL) classification and identification method and device | |
| CN110543595B (en) | In-station searching system and method | |
| CN104504151B (en) | WeChat public sentiment monitoring system | |
| Psomakelis et al. | Big IoT and social networking data for smart cities: Algorithmic improvements on Big Data Analysis in the context of RADICAL city applications | |
| CN106980651B (en) | Crawling seed list updating method and device based on knowledge graph | |
| CN102609407A (en) | Fine-grained semantic detection method of harmful text contents in network | |
| CN104615627A (en) | Event public sentiment information extracting method and system based on micro-blog platform | |
| CN103207864A (en) | Online novel content similarity comparison method | |
| Nikhil et al. | A survey on text mining and sentiment analysis for unstructured web data | |
| Sun et al. | Efficient event detection in social media data streams | |
| Li et al. | PhishBox: An approach for phishing validation and detection | |
| Mousselly-Sergieh et al. | Tag similarity in folksonomies | |
| Xu et al. | Evolution analysis of societal risk events by risk maps | |
| Ma et al. | A novel online event analysis framework for micro-blog based on incremental topic modeling |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20160330 |
|
| WW01 | Invention patent application withdrawn after publication |