CN110083701B - Network space group event early warning system based on average influence - Google Patents
Network space group event early warning system based on average influence Download PDFInfo
- Publication number
- CN110083701B CN110083701B CN201910212323.XA CN201910212323A CN110083701B CN 110083701 B CN110083701 B CN 110083701B CN 201910212323 A CN201910212323 A CN 201910212323A CN 110083701 B CN110083701 B CN 110083701B
- Authority
- CN
- China
- Prior art keywords
- module
- early warning
- user
- influence
- space group
- 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.)
- Active
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
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
-
- 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
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9532—Query formulation
-
- 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
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9538—Presentation of query results
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Abstract
The invention discloses a network space group event early warning system based on average influence, which comprises an acquisition module, a preprocessing module, an identification module and an early warning module. The invention performs multi-strategy crawling on the webpage information through the web crawler, and performs standardized processing on the crawled data. And identifying the standardized data by utilizing an identification module, and inputting the result to an early warning module. The early warning module achieves early warning according to a preset early warning index threshold value and outputs a visual report. The system effectively solves the problem that the influence of the composition of the participants on the recognition rate is ignored due to the fact that only the event is concerned by the existing early warning index system by analyzing the internal composition of the network space group event participants.
Description
Technical Field
The invention belongs to the field of information security, and particularly relates to a network space group event early warning system based on average influence.
Background
Today, national security has not only included traditional national political security and military security, and cyber space security is increasingly one of the important components of the national strategy. In order to ensure the safety of network space, maintain the main rights of network space and national safety and social public interests, protect the legal rights and interests of citizens, legal persons and other organizations, promote the information-based health development of economy and society, and the country formulates a series of laws and regulations. The laws and regulations require that any individual or organization should be responsible for its behavior in using the network. The sound internet laws and regulations facilitate the remediation of network space community events themselves and the follow-up of those who are causing or pushing the event.
Because of the widespread popularity of computers and smartphones, networks have become a major channel for people to learn information, express comments, and respond to problems. There is a large amount of information gathered into the network space every day. Some lawbreakers or organizations have the option of distributing or disseminating infirm information over the network on the premise of a common purpose or benefit. This results in the occurrence of network space-based events. The occurrence of the network space swarm events not only causes the waste of public resources, but also generates bad influence, and is a huge threat to economic development, social harmony and even public security. Therefore, the potential threat in the network space is discovered as soon as possible, and the early warning of the network space group event can be timely and accurately carried out, so that adverse effects can be avoided as much as possible, economic development and social harmony are promoted, the public business management efficiency of related departments can be improved, and the limitation and the defect of manual supervision are avoided.
At present, early warning is carried out according to burst words or pre-established sensitive word lists. The early warning system based on the burst words can have a large number of misjudgment phenomena. A burst word can only represent a sudden rise in the number of uses of the word within a certain time window. This may be affected by many circumstances. In some cases, the detected burst word with high heat may be generated in a non-threat or low threat event, which often needs to be combined with manual auditing to achieve a good effect. Sensitive vocabulary-based early warning systems require manual formulation and timed updating of sensitive vocabularies, often with hysteresis. When netizens use partial words in the network space, new interpretations may be given to the partial words. This results in sensitive vocabulary that is often incomplete in preparation and some of the words may be ambiguous during subsequent updates.
Disclosure of Invention
The present invention is directed to solving the above problems of the prior art. The network space group event early warning system based on the average influence effectively solves the problem that the existing early warning index system only pays attention to the event itself and ignores the influence of the composition of participants on the recognition rate. The technical scheme of the invention is as follows:
a network space group event early warning system based on average influence, comprising: the system comprises an acquisition module, a preprocessing module, an identification module and an early warning module; wherein, the liquid crystal display device comprises a liquid crystal display device,
the acquisition module is used for acquiring webpage data including forums, microblogs and news websites according to an acquisition strategy;
the preprocessing module comprises: and the text content sub-module is used for making short links, expressions and mentions of the proportion of the behaviors in the text content crawled by the acquisition module to the total number of the text content. Then, word segmentation is carried out on the text content, stop words are removed, and the text content is marked with categories according to a pre-built sensitive word list; the user characteristic sub-module is used for extracting the basic information of the user information crawled by the acquisition module; the influence sub-module is used for calculating influence related indexes according to the extracted basic information of the user characteristic sub-module;
the identification module comprises: classifying the data processed by the preprocessing module according to a pre-established classification model, and inputting the classification result and the value of each index in the network space group event early warning index system to the early warning module;
the early warning module comprises: and comparing the classification result of the identification module with a preset threshold value, and outputting an early warning result and a visual report if the classification result exceeds the threshold value.
Furthermore, the acquisition module performs crawling on the webpage-side microblog and the mobile-side microblog through a preset crawling strategy to obtain text data in the microblog, the crawling strategy comprises a random mode and a custom mode, the custom mode comprises setting an acquired time range, keywords, quantity, a storage mode, whether user information is crawled or not and forwarding comment contents, and the random mode can perform random crawling according to a user ID.
Furthermore, the acquisition module inputs the set crawling strategy as a configuration file into a crawler program, the crawler starts to run until a stopping condition is met, the acquired data is generated into a file format required by the preprocessing module according to the crawling strategy or is directly stored into a database server for standby, the acquisition module is a data source of the early warning system, the data is continuously acquired through the crawler program for 24 hours, the instantaneity of the early warning system is ensured, or certain acquisition delay is set in the crawling strategy, and the stability of the early warning system is ensured.
Further, the text content sub-module firstly calculates the proportion of short links, expressions and mentions behaviors in each text content to the total number of the text content, then uses a Chinese word segmentation technology to segment the independent text content crawled by the acquisition module, removes stop words, marks the text content into categories according to a pre-constructed sensitive word list, and the sensitive word list can be updated periodically according to actual needs;
the user characteristic sub-module is in charge of processing the user information crawled by the acquisition module, and reducing repeated indexes with the same utility when the crawled user information is processed;
the influence sub-module is responsible for calculating influence related indexes for measuring network events, mainly comprising average influence and user activity, wherein the network space group events are greatly different from the user compositions of common network events, the average influence and the user activity can reflect the differences of the compositions, and the average influence calculating method comprises the following steps:
wherein Inf Ui Alpha, the influence of the independent user i M represents the number of independent users participating in a network event;
the average user activity calculating method comprises the following steps:
wherein Tw is Ui To be independent text bar number, regiTime Ui Registering time for independent user beta i Is the weight of the independent user.
Further, the early warning index system includes: any one or more of independent text number, comment number, forwarding number, number of participating users, average influence, authentication user proportion, paying user proportion and user liveness, and part of indexes can adopt other names with the same utility according to different crawling strategies.
Further, the identification module further includes: training a network space group event classification model by utilizing a network space group event library in a database according to a pre-established classification model, and classifying the information processed by the preprocessing module according to the network space group event classification model.
The invention has the advantages and beneficial effects as follows:
according to the network space group event early warning system based on the average influence, the collected data are standardized by the preprocessing module according to different crawling strategies through the collecting module, the data of the standardized structure are input into the recognition module for calculation and the result is input into the early warning module, and finally the early warning module achieves the early warning function according to the preset early warning index threshold. The invention adopts the web crawlers to collect the web page data, thereby effectively improving the data crawling speed, and can set various strategies to deal with partial web pages which are difficult to crawl. The invention fully analyzes the characteristics of network space group events and participants for promoting the event development, improves the calculation method of event influence, adds indexes such as user liveness, authenticated user proportion, paid user proportion and the like as one of evaluating event authenticity, effectively solves the defects that the influence of the event influence on the event is excessively unilateral and the degree of distinction is not high, and simultaneously reduces the dependence on manual judgment as much as possible.
Drawings
FIG. 1 is a system architecture diagram of a network space group event early warning system based on average influence in accordance with a preferred embodiment of the present invention;
FIG. 2 is a system flow diagram of a network space group event early warning system based on average impact;
FIG. 3 is a diagram of a network space group event early warning system early warning index system based on average influence.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and specifically described below with reference to the drawings in the embodiments of the present invention. The described embodiments are only a few embodiments of the present invention.
The technical scheme for solving the technical problems is as follows:
the network space group event early warning system based on the average influence can set the acquisition module interface to be a crawling microblog. The hot topics and network events in the domestic microblogs are monitored, and the following parts of the domestic online and offline are concerned.
As shown in fig. 1. A network space group event early warning system (hereinafter referred to as early warning system) based on average influence comprises: the system comprises an acquisition module, a preprocessing module, an identification module and an early warning module; the whole flow of the early warning system is shown in fig. 2.
The acquisition module is mainly responsible for acquiring data in the microblog webpage and is a module input module of data to be processed of the whole early warning system. The module crawls the webpage-side microblogs and the mobile-side microblogs through a preset crawling strategy to obtain text data in the microblogs. The crawling policy includes a random mode and a custom mode. The customization mode comprises the steps of setting the time range, keywords, quantity, storage mode, whether user information is crawled, forwarding comment content and the like of acquisition. The random pattern may be randomly crawled according to the user ID. And (3) inputting the set crawling strategy as a configuration file into a crawler program, and starting the crawler to run until a stopping condition is met (such as that the number of actual microblogs is smaller than a preset maximum value, no new microblogs exist in a time range, and the like). The collected data can be generated into a file format required by the preprocessing module according to the crawling strategy or can be directly stored in a database server for standby. The acquisition module is a data source of the early warning system, and continuously acquires data through a crawler program for 24 hours, so that the real-time performance of the early warning system is ensured, a certain acquisition delay can be set in a crawling strategy, and the stability of the early warning system is ensured.
The preprocessing module is responsible for carrying out standardized processing on the data acquired by the acquisition module. The module may save the standardized data as a file format required by the identification module or directly in a database server for later use. The preprocessing module can improve the running speed of the identification module, so that the whole early warning system is more efficient and stable.
The preprocessing module specifically comprises:
the text content sub-module is firstly responsible for calculating the proportion of short links, expressions and mentioning behaviors in each text content to the total number of the text content. Then, the Chinese word segmentation technology is utilized to segment the independent text content crawled by the acquisition module, stop words are removed, and the text content is marked with categories according to a pre-built sensitive word list. The sensitive vocabulary can be updated periodically according to actual needs.
And the user characteristic sub-module is responsible for processing the user information crawled by the acquisition module. Taking microblog as an example, the registration time, the number of microblogs, the number of fan units and the like of the user can be extracted. Different web pages may exhibit different ways of extraction. And when the crawled user information is processed, reducing the repeated indexes with the same utility.
And the influence sub-module is responsible for calculating influence related indexes for measuring network events. The method mainly comprises average influence and user activity, and other partial indexes can be directly obtained without calculation (such as microblog numbers in network events). The network space community events are very different from the user composition of ordinary network events. The average influence and the user activity can reflect the difference of the composition, and the accuracy of the identification module can be improved.
The average influence calculation method comprises the following steps:
wherein Inf Ui Alpha, the influence of the independent user i Weights for independent users
The average user activity calculating method comprises the following steps:
wherein Tw is Ui To be independent text bar number, regiTime Ui Registering time for independent user beta i Is the weight of the independent user.
And the identification module is responsible for identifying and classifying the data processed by the expected processing module. Firstly, partial data are normalized, so that the convergence speed of the classification model is improved, and the timeliness of the early warning system is improved. And classifying the processed data according to a pre-constructed classification model. If the identification result is a common network event (such as a crown-grabbing of a sports event) which does not develop into a network space group event, the identification result and the values of all the early warning indexes do not need to be input into the early warning module. This helps to promote the efficiency of early warning system, prevents to be occupied the resource by the ordinary network event that need not the early warning.
The early warning module is responsible for timely analyzing and processing the classification result of the identification module, comparing the classification result with a preset threshold value of the early warning index, and outputting the early warning result and the visual report if the classification result exceeds the threshold value. The early warning index system comprises: any one or more of number of independent text, number of comments, number of forwarding, number of participating users, average impact, proportion of authenticated users, proportion of paid users, and user liveness. Some metrics may employ other names with equal utility according to different crawling policies.
The network space group event early warning index system is shown in fig. 3, and each index is illustrated by microblog as follows:
(1) Microblog number: the number of the microblogs can reflect the warmth of the network event.
(2) Comment count: how many comments may reflect the discussion hotness of an event
(3) Number of forwarding: a greater number of hops indicates a greater number of users participating in the network event and continuing to spread downward.
(4) Number of independent participating users: it is true how many users are involved in the discussion of network events.
(5) Average influence: it may be shown that the network space community event is different from the user composition of the normal network event.
(6) User liveness: the system has the same function as the average influence, and can show that the network space group event is different from the user composition of the common network event.
(7) Authentication user ratio: the user composition in the event is better reflected, and whether the network water army participates in the network event is reflected laterally.
(8) Pay-per-view ratio: the method has the same function as the authentication user proportion, well reflects the user composition in the event, and reflects whether the network water army participates in the network event or not.
The above examples should be understood as illustrative only and not limiting the scope of the invention. Various changes and modifications to the present invention may be made by one skilled in the art after reading the teachings herein, and such equivalent changes and modifications are intended to fall within the scope of the invention as defined in the appended claims.
Claims (4)
1. A network space group event early warning system based on average influence, comprising: the system comprises an acquisition module, a preprocessing module, an identification module and an early warning module; wherein, the liquid crystal display device comprises a liquid crystal display device,
the acquisition module is used for acquiring webpage data including forums, microblogs and news websites according to an acquisition strategy;
the preprocessing module comprises: the text content sub-module is used for dividing short links, expressions and mentions of the text content crawled by the acquisition module into the proportion of the short links, expressions and mentions of the short links in the text content to the total number of the text content, then dividing words into the text content, removing stop words, and marking the text content with categories according to a pre-built sensitive word list; the user characteristic sub-module is used for extracting the basic information of the user information crawled by the acquisition module; the influence sub-module is used for calculating influence related indexes according to the extracted basic information of the user characteristic sub-module;
the identification module comprises: classifying the data processed by the preprocessing module according to a pre-established classification model, and inputting the classification result and the value of each index in the network space group event early warning index system to the early warning module;
the early warning module comprises: comparing the classification result of the identification module with a preset threshold value, and outputting an early warning result and a visual report if the classification result exceeds the threshold value;
the text content sub-module firstly calculates the proportion of short links, expressions and mention behaviors in each text content to the total number of the text content, then uses Chinese word segmentation technology to segment the independent text content crawled by the acquisition module, removes stop words, marks the text content into categories according to a pre-built sensitive word list, and the sensitive word list can be updated periodically according to actual needs;
the user characteristic sub-module is in charge of processing the user information crawled by the acquisition module, and reducing repeated indexes with the same utility when the crawled user information is processed;
the influence sub-module is responsible for calculating influence related indexes for measuring network events, mainly comprising average influence and user activity, wherein the network space group events are greatly different from the user compositions of common network events, the average influence and the user activity can reflect the differences of the compositions, and the average influence calculating method comprises the following steps:
wherein Inf Ui Alpha, the influence of the independent user i The weight of the independent user; m represents the number of independent users participating in a network event;
the average user activity calculating method comprises the following steps:
wherein Tw is Ui To be independent text bar number, regiTime Ui Registering time for independent user beta i The weight of the independent user;
the early warning index system comprises: any one or more of independent text number, comment number, forwarding number, number of participating users, average influence, authentication user proportion, paying user proportion and user liveness, and part of indexes can adopt other names with the same utility according to different crawling strategies.
2. The network space swarm event early warning system based on average influence according to claim 1, wherein the acquisition module performs crawling on the web-side microblogs and the mobile-side microblogs through a preset crawling strategy to obtain text data in the microblogs, the crawling strategy comprises a random mode and a custom mode, the custom mode comprises setting an acquired time range, keywords, number, a storage mode, whether user information is crawled or not and forwarding comment contents, and the random mode can be randomly crawled according to user IDs.
3. The system for early warning of network space group events based on average influence according to claim 2, wherein the acquisition module inputs the set crawling strategy as a configuration file into a crawler program, the crawler starts running until a stopping condition is met, the acquired data is generated according to the crawling strategy into a file format required by the preprocessing module or is directly stored into a database server for standby, the acquisition module is a data source of the early warning system, the data is continuously acquired through the crawler program for 24 hours, the real-time performance of the early warning system is ensured, or a certain acquisition delay is set in the crawling strategy, and the stability of the early warning system is ensured.
4. The system of claim 3, wherein the identification module further comprises: training a network space group event classification model by utilizing a network space group event library in a database according to a pre-established classification model, and classifying the information processed by the preprocessing module according to the network space group event classification model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910212323.XA CN110083701B (en) | 2019-03-20 | 2019-03-20 | Network space group event early warning system based on average influence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910212323.XA CN110083701B (en) | 2019-03-20 | 2019-03-20 | Network space group event early warning system based on average influence |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110083701A CN110083701A (en) | 2019-08-02 |
| CN110083701B true CN110083701B (en) | 2023-07-21 |
Family
ID=67413352
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910212323.XA Active CN110083701B (en) | 2019-03-20 | 2019-03-20 | Network space group event early warning system based on average influence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110083701B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110992214B (en) * | 2019-11-29 | 2022-08-16 | 成都中科大旗软件股份有限公司 | Service management system and method based on tourist name county and demonstration area |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8688732B1 (en) * | 2010-11-19 | 2014-04-01 | Amazon Technologies, Inc. | System for mining research data |
| CN106097111A (en) * | 2016-06-20 | 2016-11-09 | 重庆房慧科技有限公司 | A kind of public opinion prediction method based on the big data of intelligence community network |
| CN107229689A (en) * | 2017-05-19 | 2017-10-03 | 四川新网银行股份有限公司 | A kind of method that microblogging public sentiment risk is studied and judged |
| CN108304867A (en) * | 2018-01-24 | 2018-07-20 | 重庆邮电大学 | Information popularity prediction technique towards social networks and system |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103176983B (en) * | 2011-12-20 | 2016-04-27 | 中国科学院计算机网络信息中心 | A kind of event method for early warning based on internet information |
| CN103268350B (en) * | 2013-05-29 | 2017-02-08 | 安徽雷越网络科技有限公司 | Internet public opinion information monitoring system and monitoring method |
| CN104281607A (en) * | 2013-07-08 | 2015-01-14 | 上海锐英软件技术有限公司 | Microblog hot topic analyzing method |
| CN105335422B (en) * | 2014-08-06 | 2019-02-22 | 阿里巴巴集团控股有限公司 | The alarm method and device of public feelings information |
| US10306013B2 (en) * | 2015-07-15 | 2019-05-28 | Sap Se | Churn risk scoring using call network analysis |
| CN105260474B (en) * | 2015-10-29 | 2018-08-14 | 俞定国 | A kind of microblog users influence power computational methods based on information exchange network |
| CN106980692B (en) * | 2016-05-30 | 2020-12-08 | 国家计算机网络与信息安全管理中心 | Influence calculation method based on microblog specific events |
| EP3319355A1 (en) * | 2016-11-03 | 2018-05-09 | Cyan Security Group GmbH | Distributed firewall system |
-
2019
- 2019-03-20 CN CN201910212323.XA patent/CN110083701B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8688732B1 (en) * | 2010-11-19 | 2014-04-01 | Amazon Technologies, Inc. | System for mining research data |
| CN106097111A (en) * | 2016-06-20 | 2016-11-09 | 重庆房慧科技有限公司 | A kind of public opinion prediction method based on the big data of intelligence community network |
| CN107229689A (en) * | 2017-05-19 | 2017-10-03 | 四川新网银行股份有限公司 | A kind of method that microblogging public sentiment risk is studied and judged |
| CN108304867A (en) * | 2018-01-24 | 2018-07-20 | 重庆邮电大学 | Information popularity prediction technique towards social networks and system |
Non-Patent Citations (2)
| Title |
|---|
| 基于改进PageRank算法的微博影响力模型研究;毕秋敏;李世辉;曾志勇;;价值工程(第29期);全文 * |
| 社交网络用户影响力的模糊综合评价;张琛;汤鲲;彭艳兵;;计算机系统应用(第12期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110083701A (en) | 2019-08-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Pacheco et al. | Uncovering coordinated networks on social media: methods and case studies | |
| Dahal et al. | Topic modeling and sentiment analysis of global climate change tweets | |
| Kulshrestha et al. | Quantifying search bias: Investigating sources of bias for political searches in social media | |
| CN103297435B (en) | A kind of abnormal access behavioral value method and system based on WEB daily record | |
| CN101819573B (en) | Self-adaptive network public opinion identification method | |
| CN103136330B (en) | Based on the User reliability appraisal procedure of microblog | |
| CN105117484A (en) | Internet public opinion monitoring method and system | |
| WO2013185601A1 (en) | Method and device for obtaining product information and computer storage medium | |
| Paltoglou | Sentiment‐based event detection in T witter | |
| CN101751458A (en) | Network public sentiment monitoring system and method | |
| CN103853841A (en) | Method for analyzing abnormal behavior of user in social networking site | |
| CN106383887A (en) | Environment-friendly news data acquisition and recommendation display method and system | |
| CN110880075A (en) | Employee departure tendency detection method | |
| CN110134876A (en) | A kind of cyberspace Mass disturbance perception and detection method based on gunz sensor | |
| Sun et al. | Efficient event detection in social media data streams | |
| Lin et al. | Privacy protection of China’s top websites: A Multi-layer privacy measurement via network behaviours and privacy policies | |
| Wu et al. | Statistical analysis of dispelling rumors on Sina Weibo | |
| Rajapaksha et al. | Scrutinizing news media cooperation in facebook and twitter | |
| Zhou et al. | Overlapping influence inspires the selection of multiple spreaders in complex networks | |
| CN110083701B (en) | Network space group event early warning system based on average influence | |
| Dunna et al. | Paying Attention to the Algorithm Behind the Curtain: Bringing Transparency to YouTube's Demonetization Algorithms | |
| Zhang et al. | Analysis and mining of internet public opinion based on LDA subject classification | |
| Paudel et al. | Lambretta: learning to rank for Twitter soft moderation | |
| Weber et al. | Demographic information flows | |
| Akbulut et al. | Agent based pornography filtering system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |