CN114443930A - News public opinion intelligent monitoring and analyzing method, system and computer storage medium - Google Patents
News public opinion intelligent monitoring and analyzing method, system and computer storage medium Download PDFInfo
- Publication number
- CN114443930A CN114443930A CN202210140428.0A CN202210140428A CN114443930A CN 114443930 A CN114443930 A CN 114443930A CN 202210140428 A CN202210140428 A CN 202210140428A CN 114443930 A CN114443930 A CN 114443930A
- Authority
- CN
- China
- Prior art keywords
- public opinion
- information
- opinion information
- topic
- crawling
- 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- Withdrawn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
Images
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
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)
Abstract
The invention discloses a news public opinion intelligent monitoring and analyzing method, a system and a computer storage medium. The news public opinion intelligent monitoring and analyzing method comprises the following steps: acquiring basic information corresponding to the released news event; acquiring basic information corresponding to each public opinion information crawling platform; acquiring topic information of each public opinion information crawling platform; analyzing the content corresponding to the news release event and acquiring a target monitoring topic corresponding to the content; crawling public opinion information related to the news event; public opinion information crawled by each public opinion information crawling platform is analyzed; carrying out early warning on public sentiment information corresponding to the news event; the method effectively solves the problem that the content monitored by the conventional news public opinion monitoring and analyzing method is one-sidedness, so that the accuracy of news public opinion detection and analysis cannot be effectively improved, and simultaneously greatly improves the processing efficiency and the monitoring efficiency of negative public opinions of news events.
Description
Technical Field
The invention belongs to the technical field of public opinion monitoring and analysis, and relates to a news public opinion intelligent monitoring and analysis method, a system and a computer storage medium.
Background
With the rapid development of new media technology, information transmission becomes more convenient, and under the large background, any news event is very easy to be pushed to the wind tip of the public opinion in a short time, and in order to reduce the influence of the public opinion on the news event, the news public opinion needs to be monitored and analyzed.
The existing news public opinion monitoring and analyzing method mainly analyzes public opinion information aiming at hot news, and does not deeply monitor and analyze diffusion information and public opinion guide corresponding to news event public opinions, therefore, the existing news public opinion monitoring and analyzing method also has certain defects, on one hand, the content of the existing news public opinion monitoring and analyzing method has one-sidedness, the accuracy of the news public opinion detection and analysis cannot be effectively improved, on the other hand, the processing efficiency of the existing news public opinion monitoring and analyzing method to the negative public opinions of news events cannot be effectively improved, and on the other hand, the effect of the existing news public opinion monitoring and analyzing method cannot effectively improve the news public opinion monitoring and analyzing effect.
Disclosure of Invention
In view of the above, in order to solve the problems in the background art, an intelligent monitoring and analyzing method, system and computer storage medium for news public sentiment are provided, so as to realize real-time monitoring and accurate analysis of news public sentiment;
the purpose of the invention can be realized by the following technical scheme:
the invention provides a news public opinion intelligent monitoring and analyzing method, which comprises the following steps:
s1, acquiring basic information of news events: acquiring basic information corresponding to the released news event through a news event basic information acquisition module, wherein the basic information corresponding to the news event comprises a release time point corresponding to the news event and release content corresponding to the news event;
s2, obtaining basic information of the public opinion information crawling platform: the method comprises the steps that basic information corresponding to public opinion information crawling platforms is obtained through a basic information obtaining module of the public opinion information crawling platforms, the number of the public opinion information crawling platforms corresponding to news events is further obtained, the public opinion information crawling platforms are numbered according to a preset sequence and are sequentially marked as 1,2,. i,. n, and then the basic information corresponding to the public opinion information crawling platforms is obtained;
s3, obtaining topic information of the public opinion information crawling platform: the topic information of each public opinion information crawling platform is obtained through a topic information obtaining module, the number of topics corresponding to each public opinion information crawling platform is further obtained, the topics corresponding to each public opinion information crawling platform are numbered according to a preset sequence, the number is marked as 1,2, a.
S4, analyzing basic information of news events: analyzing the content corresponding to the published news event through a data processing and analyzing module to obtain a target monitoring topic corresponding to the published news event;
s5, crawling public opinion information: the public opinion information relevant to the news event is crawled from each public opinion information crawling platform through a public opinion information crawling module, and then relevant public opinion information corresponding to each target monitoring topic of the published news event is called from each public opinion information crawling platform according to the target monitoring topic corresponding to the published news event;
s6, crawling public opinion information analysis: public opinion information crawled by each public opinion information crawling platform is analyzed through a data processing and analyzing module, and then the comprehensive early warning influence coefficient of the public opinion information of the news event is counted;
s7, public opinion information early warning: and carrying out early warning on the public sentiment information corresponding to the news event through a public sentiment information early warning terminal, and then carrying out early warning when the comprehensive early warning influence coefficient of the public sentiment information of the news event reaches an early warning value, and sending the important processing platform of the public sentiment information of the news event to a public sentiment manager corresponding to the news event.
Further, the basic information of the public opinion information crawling platform comprises the number of registered users corresponding to the public opinion information crawling platform and the category corresponding to each registered user, and the basic information set J of the public opinion information crawling platform is constructed according to the basic information corresponding to each public opinion information crawling platformw(Jw1,Jw2,...Jwi,...Jwn)，JwThe i represents the w-th basic information corresponding to the ith public opinion information crawling platform of the news release event, w represents the basic information of the public opinion information crawling platform, and w is a1, a2, a1 and a2 respectively represent the number of registered users corresponding to the public opinion information crawling platform and the category corresponding to each registered user.
Furthermore, the news event information analysis is used for acquiring the target keywords of the news event according to the content corresponding to the released news event, meanwhile, according to the text information corresponding to each topic of each public opinion information crawling platform, the target keywords corresponding to each topic of each public opinion information crawling platform are obtained, further, the similarity of each topic of each public opinion information crawling platform and the corresponding published news event is counted, the similarity of each topic of each public opinion information crawling platform and the corresponding published news event is compared with the similarity of each similarity level in the database, further acquiring the similar grade of each topic of each public opinion information crawling platform and the corresponding news release event, and extracting the number of topics corresponding to the first-level similarity level from each public opinion information crawling platform, marking the topics as target monitoring topics, and further acquiring target monitoring topics corresponding to each public opinion information crawling platform of the news release event.
Further, the public opinion information comprises the number of the users participating in the topic, the category corresponding to each user participating in the topic and the evaluation information corresponding to each user participating in the topic, so as to obtain the public opinion information corresponding to each target monitoring topic of each public opinion information crawling platform in each acquisition time period, and construct each target monitoring topic public opinion information set Y of each public opinion information crawling platform in each acquisition time periode dp(Ye dp1,Ye dp2,...Ye dpk,...Ye dpf)，Ye dpk represents the e-th public opinion information corresponding to the p-th target monitoring topic of the d-th public opinion information crawling platform in the k-th collection time period, d represents the public opinion information crawling platform number, d is 1,2,. i,. n, p represents the target monitoring topic number of each public opinion information crawling platform, p is 1,2,. x,. y, e represents the public opinion information, e is b1, b2, b3, b1, b2 and b3 respectively represent the number of participating topic users, the category corresponding to each participating topic user and the evaluation information corresponding to each topic participating user.
Further, the crawling public opinion information analysis is used for analyzing the public opinion diffusion speed corresponding to the news event, acquiring public opinion information sets of all target monitoring topics of all public opinion information crawling platforms in all acquisition time periods, further acquiring the number of participatory topic users corresponding to all target monitoring topics of all public opinion information crawling platforms in all acquisition time periods, acquiring the diffusion speed corresponding to all target monitoring topics of all public opinion information crawling platforms according to the number of participatory topic users corresponding to all target monitoring topics of all acquisition time periods, comparing the diffusion speed corresponding to all target monitoring topics of all public opinion information crawling platforms with the standard diffusion speed corresponding to the public opinion information, and further counting the early warning influence coefficient of the diffusion speed of all target monitoring topics of all public opinion information crawling platforms.
Further, the crawling public opinion information analysis is used for analyzing the public opinion guidance corresponding to the news event, obtaining the evaluation information corresponding to each participated topic user of each target monitoring topic of each public opinion information crawling platform in each collection time period, further analyzing the evaluation information corresponding to each participated topic user of each target monitoring topic of each public opinion information crawling platform in each collection time period, further obtaining the comprehensive public opinion guidance type corresponding to each target monitoring topic of each public opinion information crawling platform, matching and comparing the comprehensive public opinion guidance type corresponding to each target monitoring topic of each public opinion information crawling platform with the early warning influence coefficient corresponding to each public opinion guidance type in the database, and further obtaining each target monitoring public opinion guidance early warning influence coefficient of each public opinion information crawling platform.
Further, the crawling public opinion information analysis is used for analyzing the public opinion diffusion range corresponding to the news event, numbers corresponding to all the participating topic users of all the target monitoring topics of each public opinion information crawling platform are obtained according to the public opinion information, categories corresponding to all the participating topic users of all the target monitoring topics of each public opinion information crawling platform are called, categories corresponding to all the participating topic users of all the target monitoring topics of each public opinion information crawling platform are compared with each other, the number of the participating topic users of each category of each target monitoring topic of each public opinion information crawling platform is counted, the category corresponding to the largest number of the participating topic users of each target monitoring topic of each public opinion information crawling platform is screened, the category is marked as a main participating topic user category of each target monitoring topic of each public opinion information crawling platform, each main topic participating topic user category of each target monitoring topic of each public opinion information crawling platform is monitored according to each public opinion information, and extracting diffusion range early warning influence coefficients corresponding to the user categories from the database, and further acquiring the diffusion range early warning influence coefficients of the target monitoring topics of the public opinion information crawling platforms.
Further, the crawling public opinion information analysis is used for carrying out comprehensive analysis on the public opinion diffusion speed and the public opinion guiding public opinion diffusion range corresponding to the news event, and according to the statistical public opinion information crawling platform target monitoring topic diffusion speed early warning influence coefficient, each public opinion information crawling platform target monitoring topic public opinion guiding early warning influence coefficient and each public opinion information crawling platform target monitoring topic diffusion range early warning influence coefficient, further the statistical public opinion information crawling platform target monitoring topic comprehensive public opinion early warning influence coefficient, according to the statistical public opinion information crawling platform target monitoring topic comprehensive public opinion early warning influence coefficient, the statistical public opinion event public opinion information comprehensive early warning influence coefficient is obtained, and the news event public opinion information key processing platform is obtained.
The invention provides a news public opinion intelligent monitoring and analyzing system, wherein the data processing and analyzing module is respectively connected with a news event basic information acquisition module, a public opinion information crawling platform basic information acquisition module, a topic information acquisition module, a public opinion information crawling module, a database and a public opinion information early warning terminal.
A third aspect of the present invention provides a computer storage medium, where a computer program is burned into the computer storage medium, and when the computer program runs in a memory of a server, the method of the present invention is implemented.
The invention has the beneficial effects that:
(1) according to the intelligent monitoring and analyzing method for the news public sentiments, the public sentiment diffusion speed, the public sentiment guide and the public sentiment diffusion range corresponding to each target monitoring topic of each public sentiment information crawling platform in each collection time period are analyzed, so that the problem that the accuracy of news public sentiment detection and analysis cannot be effectively improved due to the fact that the content of the existing news public sentiment monitoring and analysis has one-sidedness is effectively solved, the processing efficiency of negative public sentiments of news events is greatly improved, and meanwhile, the effect of the news public sentiment monitoring and analysis is also effectively improved.
(2) The invention effectively obtains the public sentiment current situation corresponding to the news event in each public sentiment information crawling platform by crawling the public sentiment information related to the news event from each public sentiment information crawling platform, thereby providing a powerful information basis for the follow-up public sentiment analysis of the news event.
(3) The invention effectively avoids more serious public opinion influence caused by untimely processing by early warning of the public opinion information corresponding to the news event, thereby effectively maintaining the public opinion environment of the network and greatly improving the response efficiency of the public opinion information processing of the news event.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a diagram of the steps of the method of the present invention;
FIG. 2 is a schematic diagram of the connection of modules of the system of the present invention.
Detailed Description
While the foregoing is directed to embodiments of the present invention, other and further embodiments of the invention may be devised without departing from the basic scope thereof, and the scope thereof is determined by the claims that follow.
Referring to fig. 1, a first aspect of the present invention provides a news public opinion intelligent monitoring and analyzing method, including the following steps:
s1, acquiring basic information of news events: acquiring basic information corresponding to the released news event through a news event basic information acquisition module, wherein the basic information corresponding to the news event comprises a release time point corresponding to the news event and release content corresponding to the news event;
s2, obtaining basic information of the public opinion information crawling platform: the method comprises the steps that basic information corresponding to public opinion information crawling platforms is obtained through a basic information obtaining module of the public opinion information crawling platforms, the number of the public opinion information crawling platforms corresponding to news events is further obtained, the public opinion information crawling platforms are numbered according to a preset sequence and are sequentially marked as 1,2, 1.i.n, and further the basic information corresponding to the public opinion information crawling platforms is obtained;
specifically, the basic information of the public opinion information crawling platform comprises the number of registered users corresponding to the public opinion information crawling platform and the category corresponding to each registered user, and the basic information set J of the basic information of each public opinion information crawling platform is constructed according to the basic information corresponding to each public opinion information crawling platformw(Jw1,Jw2,...Jwi,...Jwn)，JwThe i represents the w-th basic information corresponding to the ith public opinion information crawling platform of the news release event, w represents the basic information of the public opinion information crawling platform, and w is a1, a2, a1 and a2 respectively represent the number of registered users corresponding to the public opinion information crawling platform and the category corresponding to each registered user.
In a specific embodiment, the public opinion information crawling platform includes, but is not limited to, media such as micro blogs, posts, forums, blogs, and the like.
According to the embodiment of the invention, the reliability and the authenticity of the follow-up news public opinion information analysis result are effectively improved by acquiring the basic information of the public opinion information crawling platform.
S3, obtaining topic information of the public opinion information crawling platform: the topic information of each public opinion information crawling platform is obtained through a topic information obtaining module, the number of topics corresponding to each public opinion information crawling platform is further obtained, the topics corresponding to each public opinion information crawling platform are numbered according to a preset sequence, the number is marked as 1,2, a.
According to the embodiment of the invention, by acquiring the topic information corresponding to each public opinion information crawling platform, a cushion is provided for acquiring the target monitoring topic of the news release event.
S4, analyzing basic information of news events: analyzing the content corresponding to the published news event through a data processing and analyzing module to obtain a target monitoring topic corresponding to the published news event;
specifically, the news event information analysis is used for acquiring the target keywords of the news event according to the content corresponding to the released news event, meanwhile, according to the text information corresponding to each topic of each public opinion information crawling platform, the target keywords corresponding to each topic of each public opinion information crawling platform are obtained, further, the similarity of each topic of each public opinion information crawling platform and the corresponding published news event is counted, the similarity of each topic of each public opinion information crawling platform and the corresponding published news event is compared with the similarity of each similarity level in the database, further acquiring the similar grade of each topic of each public opinion information crawling platform and the corresponding news release event, and extracting the number of topics corresponding to the first-level similarity level from each public opinion information crawling platform, marking the topics as target monitoring topics, and further acquiring target monitoring topics corresponding to each public opinion information crawling platform of the news release event.
The acquisition process of the news event target keywords comprises the following steps: dividing the content corresponding to the published news event into words, filtering stop words corresponding to the divided words, recording the divided words after filtering as candidate keywords, extracting the weight corresponding to each candidate keyword from a database, sequencing the weights corresponding to the candidate keywords in descending order, extracting the candidate keywords with three top-ranked bits, and recording the candidate keywords as news event target keywords.
And obtaining the target keywords of each topic of each public opinion information crawling platform by an obtaining method according to the target keywords of the news event, and further obtaining the target keywords corresponding to each topic of each public opinion information crawling platform.
The similarity statistical process of each topic of each public opinion information crawling platform corresponding to the news event is as follows: acquiring the weight corresponding to each news event target keyword, converting the weight corresponding to each news event target keyword into a vector form, acquiring the weight corresponding to each target keyword of each topic of each public opinion information crawling platform, and acquiring the weight corresponding to each target keyword of each topic of each public opinion information crawling platformConverting the vector form again, respectively constructing a topic vector set and a news event vector set of each public opinion information crawling platform, respectively marking the topic vector set and the released news event vector set of each public opinion information crawling platform as A and B, and further counting the corresponding similarity of each topic of each public opinion information crawling platform and the released news event, and a calculation formula thereof
δd rRepresenting the similarity of the ith topic of the ith public opinion information crawling platform and the corresponding news release event, Ad rAnd expressing a vector set corresponding to the r-th topic of the d-th public opinion information crawling platform.
According to the embodiment of the invention, through analyzing the information corresponding to the published news event, the pertinence and the accuracy of monitoring the public sentiment information of the published news event are greatly improved, and the efficiency of monitoring the public sentiment information of the published news event is greatly improved.
S5, crawling public opinion information: the method comprises the steps that public opinion information relevant to a news event is crawled from all public opinion information crawling platforms through a public opinion information crawling module, and then relevant public opinion information corresponding to all target monitoring topics of the published news event is called from all public opinion information crawling platforms according to the target monitoring topics corresponding to the published news event;
specifically, the public opinion information comprises the number of users participating in topics, categories corresponding to the users participating in topics and evaluation information corresponding to the users participating in topics, so that the public opinion information corresponding to each target monitoring topic of each public opinion information crawling platform in each acquisition time period is obtained, and a public opinion information set Y of each target monitoring topic of each public opinion information crawling platform in each acquisition time period is constructede dp(Ye dp1,Ye dp2,...Ye dpk,...Ye dpf)，Ye dpk represents the e-th public opinion information corresponding to the p-th target monitoring topic of the d-th public opinion information crawling platform in the kth acquisition time period, d represents the serial number of the public opinion information crawling platform, and d is 1,2The information crawling platform target monitoring topic number is p1, 2,.. x,. y, e represents public opinion information, and e b1, b2, b3, b1, b2 and b3 represent the number of users participating in the topic, the category corresponding to each user participating in the topic and the evaluation information corresponding to each user participating in the topic.
The embodiment of the invention effectively acquires the public opinion current situation corresponding to the news event in each public opinion information crawling platform by crawling the public opinion information related to the news event from each public opinion information crawling platform, thereby providing a powerful information basis for the follow-up public opinion analysis of the news event.
S6, crawling public opinion information analysis: public opinion information crawled by each public opinion information crawling platform is analyzed through a data processing and analyzing module, and then the comprehensive early warning influence coefficient of the public opinion information of the news event is counted;
specifically, the crawling public opinion information analysis is used for analyzing the public opinion diffusion speed corresponding to the news event, acquiring the public opinion information set of each target monitoring topic of each public opinion information crawling platform in each acquisition time period, further acquiring the number of participatory topic users corresponding to each target monitoring topic of each public opinion information crawling platform in each acquisition time period, acquiring the diffusion speed corresponding to each target monitoring topic of each public opinion information crawling platform according to the number of participatory topic users corresponding to each target monitoring topic of each acquisition time period, comparing the diffusion speed corresponding to each target monitoring topic of each public opinion information crawling platform with the standard diffusion speed corresponding to the public opinion information, and further calculating the early warning influence coefficient of each target monitoring topic of each public opinion information crawling platform.
Wherein, the public opinion information crawling platform has a diffusion speed calculation formula corresponding to each target monitoring topic
vd rB1 showing the diffusion speed corresponding to the pth target monitoring topic of the pth public opinion information crawling platformt+1 dpRepresents that the pth target monitoring topic of the pth public opinion information crawling platform is corresponding to the t +1 collection time periodNumber of users participating in the topic, b1t dpThe number of participated topic users corresponding to the tth acquisition time period of the pth target monitoring topic of the pth public opinion information crawling platform is represented, T represents an acquisition time period number, and T is 1, 2.
Wherein, the calculation formula of each target monitoring topic diffusion speed early warning influence coefficient of each public opinion information crawling platform is
βd pRepresenting diffusion velocity early warning influence coefficient, v, corresponding to the pth target monitoring topic of the pth public opinion information crawling platformStandard of meritAnd expressing the standard diffusion speed corresponding to the public sentiment information.
Specifically, the crawling public opinion information analysis is used for analyzing the public opinion guidance corresponding to the news event, obtaining the evaluation information corresponding to each participatory topic user of each target monitoring topic of each public opinion information crawling platform in each collection time period, further analyzing the evaluation information corresponding to each participatory topic user of each target monitoring topic of each public opinion information crawling platform in each collection time period, further obtaining the comprehensive public opinion guidance type corresponding to each target monitoring topic of each public opinion information crawling platform, matching and comparing the comprehensive public opinion guidance type corresponding to each target monitoring topic of each public opinion information crawling platform with the early warning influence coefficient corresponding to each public opinion guidance type in the database, and further obtaining each target monitoring public opinion guidance early warning influence coefficient of each public opinion information crawling platform.
The analysis process of the evaluation information corresponding to each user participating in each topic of each target monitoring topic of each public opinion information crawling platform in each acquisition time period is as follows:
p1, acquiring the number of participated topic users corresponding to each target monitoring topic of each public opinion information crawling platform in each acquisition time period and the evaluation information corresponding to each participated topic user, segmenting the evaluation information corresponding to each participated topic user of each target monitoring topic of each public opinion information crawling platform in each acquisition time period, removing stop words corresponding to the segmented information, and acquiring the segmented word number corresponding to each participated topic user of each target monitoring topic of each public opinion information crawling platform in each acquisition time period after the stop words are removed;
p2, extracting the quantity of the emotion vocabulary corresponding to each public opinion guide type from the database, and further constructing the emotion vocabulary set Q of each public opinion guide type according to the quantity of the emotion vocabulary corresponding to each public opinion guide typez(Qz1，Qz2，....Qzs,...Qzl)，Qzs represents the s-th emotional vocabulary corresponding to the z-th public opinion guide type, z represents the public opinion guide type, and z is c1, c2, c3, c1, c2 and c3 which respectively represent positive guide, negative guide and neutral guide;
p3, acquiring the number of users participating in the topics corresponding to the target monitoring topics of the public opinion information crawling platform according to the number of users participating in the topics of the target monitoring topics of the public opinion information crawling platform in each acquisition time period, further acquiring the number of participles corresponding to the users participating in the topics of the target monitoring topics of the public opinion information crawling platform, and further constructing a participle set F of the users participating in the topics of the target monitoring topics of the public opinion information crawling platformdp u(Fdp u1,Fdp u2,...Fdp ug,...Fdp uh)，Fdp ug represents the g-th participle corresponding to the u-th participle of the p-th target monitoring topic user of the d-th public opinion information crawling platform, u represents the number of each target monitoring topic participle user, and u is 1,2,. alpha,. epsilon;
and P4, matching and comparing the participles of the users participating in the topics of each target monitoring topic of each public opinion information crawling platform with the emotion vocabularies of all public opinion guide types, further counting the public opinion guide types corresponding to the users participating in the topics of each target monitoring topic of each public opinion information crawling platform, and acquiring the comprehensive public opinion guide types corresponding to the target monitoring topics of each public opinion information crawling platform according to the public opinion guide types corresponding to the users participating in the topics of each target monitoring topic of each public opinion information crawling platform.
Wherein, each public opinion information crawling platform calculates public opinion guide type corresponding to each participated topic user of each target monitoring topicIs of the formula
Hdp uAnd the public opinion guide type corresponding to the user of the u th participated topic of the p th target monitoring topic of the ith public opinion information crawling platform is represented.
The comprehensive guidance types corresponding to the target monitoring topics of the public opinion information crawling platforms are used for mutually comparing the public opinion guidance types corresponding to the target monitoring topics of the public opinion information crawling platforms according to the public opinion guidance types corresponding to the participatory topic users of the target monitoring topics of the public opinion information crawling platforms, further acquiring the number of participatory topic users corresponding to the public opinion guidance types of the target monitoring topics of the public opinion information crawling platforms, sequencing the number of participatory topic users corresponding to the participatory topic guidance types of the target monitoring topics of the public opinion information crawling platforms from large to small, and taking the public opinion guidance type with the first ranking as the comprehensive guidance type corresponding to the target monitoring topics of the public opinion information crawling platforms.
Specifically, the crawling public opinion information analysis is used for analyzing the public opinion diffusion range corresponding to the news event, numbers corresponding to all participating topic users of all target monitoring topics of each public opinion information crawling platform are obtained according to the public opinion information, categories corresponding to all participating topic users of all target monitoring topics of each public opinion information crawling platform are called, categories corresponding to all participating topic users of all target monitoring topics of each public opinion information crawling platform are compared with each other, the number of all categories of participating topic users of all target monitoring topics of each public opinion information crawling platform is counted, the category corresponding to the largest number of all target monitoring topic participating topic users of each public opinion information crawling platform is selected, the category is marked as a category of main participating topic users of all target monitoring topics of each public opinion information crawling platform, the categories of the main participating topic users of each target monitoring topic of each public opinion information crawling platform are monitored according to each public opinion information crawling platform, and extracting diffusion range early warning influence coefficients corresponding to the user categories from the database, and further acquiring the diffusion range early warning influence coefficients of the target monitoring topics of the public opinion information crawling platforms.
Specifically, the crawling public opinion information analysis is used for carrying out comprehensive analysis on the public opinion diffusion speed and the public opinion guiding public opinion diffusion range corresponding to the news event, and according to the statistical public opinion information crawling platform target monitoring topic diffusion speed early warning influence coefficient, each public opinion information crawling platform target monitoring topic public opinion guiding early warning influence coefficient and each public opinion information crawling platform target monitoring topic diffusion range early warning influence coefficient, further statistics is carried out on each public opinion information crawling platform target monitoring topic comprehensive public opinion early warning influence coefficient, according to the statistical public opinion information crawling platform target monitoring topic comprehensive public opinion early warning influence coefficient, statistics is carried out on the public opinion information comprehensive early warning influence coefficient, and the important processing platform of the public opinion event public opinion information is obtained.
Wherein, the calculation formula of the comprehensive public opinion early warning influence coefficient of each target monitoring topic of each public opinion information crawling platform is
λd pThe comprehensive public opinion early warning influence coefficient corresponding to the pth target monitoring topic of the pth public opinion information crawling platform is shown,
expressing the public opinion guiding early warning influence coefficient, phi, corresponding to the pth target monitoring topic of the pth public opinion information crawling platformd pAnd representing the diffusion range early warning influence coefficient corresponding to the pth target monitoring topic of the pth public opinion information crawling platform.
Wherein, the news event public opinion information comprehensive early warning influence coefficient calculation formula of the news event is
Psi represents the comprehensive early warning influence coefficient corresponding to the news event public opinion information.
The news event key public opinion information crawling platform acquires comprehensive public opinion early warning influence coefficients for monitoring topics of each target of each public opinion information crawling platform according to statisticsAnd further acquiring comprehensive public opinion information early warning influence coefficient of each public opinion information crawling platform, wherein the calculation formula is
γdAnd the comprehensive public opinion information early warning influence coefficients corresponding to the d public opinion information crawling platforms are expressed, the comprehensive public opinion information early warning influence coefficients of the public opinion information crawling platforms are sequenced from big to small, the public opinion information crawling platform with the first ranking is extracted, and the public opinion information crawling platform is marked as the news event public opinion information key processing platform.
The embodiment of the invention analyzes the public opinion diffusion speed, the public opinion guidance and the public opinion diffusion range corresponding to each target monitoring topic of each public opinion information crawling platform in each acquisition time period, effectively solves the problem that the content of the existing news public opinion monitoring and analysis has one-sidedness, and further cannot effectively improve the accuracy of news public opinion detection and analysis, greatly improves the processing efficiency of negative public opinions of news events, and also effectively improves the effect of news public opinion monitoring and analysis.
S7, public opinion information early warning: and carrying out early warning on the public sentiment information corresponding to the news event through a public sentiment information early warning terminal, and then carrying out early warning when the comprehensive early warning influence coefficient of the public sentiment information of the news event reaches an early warning value, and sending the important processing platform of the public sentiment information of the news event to a public sentiment manager corresponding to the news event.
The embodiment of the invention effectively avoids more serious public opinion influence caused by untimely processing by early warning the public opinion information corresponding to the news event, thereby effectively maintaining the public opinion environment of the network and greatly improving the response efficiency of processing the public opinion information of the news event.
Referring to fig. 2, a second aspect of the present invention provides an intelligent monitoring and analyzing system for news and public sentiment, which includes a news event basic information acquiring module, a public sentiment information crawling platform basic information acquiring module, a topic information acquiring module, a public sentiment information crawling module, a data processing and analyzing module, a database, and a public sentiment information early warning terminal;
the data processing and analyzing module is respectively connected with the news event basic information acquisition module, the public opinion information crawling platform basic information acquisition module, the topic information acquisition module, the public opinion information crawling module, the database and the public opinion information early warning terminal.
The database is used for storing similarity corresponding to each similar grade, weight corresponding to each word, standard diffusion speed corresponding to public opinion information, early warning influence coefficient corresponding to each public opinion guide type, emotion word quantity corresponding to each public opinion guide type and diffusion range early warning influence coefficient corresponding to each user category.
A third aspect of the present invention provides a computer storage medium, where a computer program is burned into the computer storage medium, and when the computer program runs in a memory of a server, the method of the present invention is implemented.
The foregoing is merely exemplary and illustrative of the principles of the present invention and various modifications, additions and substitutions of the specific embodiments described herein may be made by those skilled in the art without departing from the principles of the present invention or exceeding the scope of the claims set forth herein.
Claims (10)
1. An intelligent news public opinion monitoring and analyzing method is characterized by comprising the following steps: the method comprises the following steps:
s1, acquiring basic information of news events: acquiring basic information corresponding to the released news event through a news event basic information acquisition module, wherein the basic information corresponding to the news event comprises a release time point corresponding to the news event and release content corresponding to the news event;
s2, obtaining basic information of the public opinion information crawling platform: the method comprises the steps that basic information corresponding to public opinion information crawling platforms is obtained through a basic information obtaining module of the public opinion information crawling platforms, the number of the public opinion information crawling platforms corresponding to news events is further obtained, the public opinion information crawling platforms are numbered according to a preset sequence and are sequentially marked as 1,2, 1.i.n, and further the basic information corresponding to the public opinion information crawling platforms is obtained;
s3, obtaining topic information of the public opinion information crawling platform: the method comprises the steps that topic information of each public opinion information crawling platform is obtained through a topic information obtaining module, then the number of topics corresponding to each public opinion information crawling platform is obtained, the topics corresponding to each public opinion information crawling platform are numbered according to a preset sequence, the number is marked as 1,2,.
S4, analyzing basic information of news events: analyzing the content corresponding to the published news event through a data processing and analyzing module to obtain a target monitoring topic corresponding to the published news event;
s5, crawling public opinion information: the method comprises the steps that public opinion information relevant to a news event is crawled from all public opinion information crawling platforms through a public opinion information crawling module, and then relevant public opinion information corresponding to all target monitoring topics of the published news event is called from all public opinion information crawling platforms according to the target monitoring topics corresponding to the published news event;
s6, crawling public opinion information analysis: public opinion information crawled by each public opinion information crawling platform is analyzed through a data processing and analyzing module, and then the comprehensive early warning influence coefficient of the public opinion information of the news event is counted;
s7, public opinion information early warning: and carrying out early warning on the public sentiment information corresponding to the news event through a public sentiment information early warning terminal, and then carrying out early warning when the comprehensive early warning influence coefficient of the public sentiment information of the news event reaches an early warning value, and sending the important processing platform of the public sentiment information of the news event to a public sentiment manager corresponding to the news event.
2. The news public opinion intelligent monitoring and analysis method according to claim 1, characterized in that: the basic information of the public opinion information crawling platform comprises the number of registered users corresponding to the public opinion information crawling platform and the category corresponding to each registered user, and the basic information corresponding to each public opinion information crawling platform is constructed according to the basic information corresponding to each public opinion information crawling platform, so that a basic information set J of each public opinion information crawling platform is constructedw(Jw1,Jw2,...Jwi,...Jwn)，JwThe i represents the w-th basic information corresponding to the ith public opinion information crawling platform of the news release event, w represents the basic information of the public opinion information crawling platform, and w is a1, a2, a1 and a2 respectively represent the number of registered users corresponding to the public opinion information crawling platform and the category corresponding to each registered user.
3. The news public opinion intelligent monitoring and analysis method according to claim 1, characterized in that: the news event information analysis is used for acquiring the target key words of the news event according to the content corresponding to the released news event, meanwhile, according to the text information corresponding to each topic of each public opinion information crawling platform, the target keywords corresponding to each topic of each public opinion information crawling platform are obtained, further, the similarity of each topic of each public opinion information crawling platform and the corresponding published news event is counted, the similarity of each topic of each public opinion information crawling platform and the corresponding published news event is compared with the similarity of each similarity level in the database, further acquiring the similar grade of each topic of each public opinion information crawling platform and the corresponding news release event, and extracting the number of topics corresponding to the first-level similarity level from each public opinion information crawling platform, marking the topics as target monitoring topics, and further acquiring target monitoring topics corresponding to each public opinion information crawling platform of the news release event.
4. The news public opinion intelligent monitoring and analysis method according to claim 1, characterized in that: the public opinion information comprises the number of the users participating in the topic, the categories corresponding to the users participating in the topic and the evaluation information corresponding to the users participating in the topic, so that the public opinion information corresponding to each target monitoring topic of each public opinion information crawling platform in each acquisition time period is obtained, and a public opinion information set Y of each target monitoring topic of each public opinion information crawling platform in each acquisition time period is establishede dp(Ye dp1,Ye dp2,...Ye dpk,...Ye dpf)，Ye dpk denotes the kth acquisition time period dThe method comprises the steps that the first public opinion information corresponding to the first target monitoring topic of each public opinion information crawling platform, d represents a public opinion information crawling platform number, d is 1,2, i, n and p represent target monitoring topic numbers of each public opinion information crawling platform, p is 1,2, x, y and e represent public opinion information, e is b1, b2, b3, b1, b2 and b3 represent the number of users participating in topics, categories corresponding to users participating in topics and evaluation information corresponding to users participating in topics respectively.
5. The news public opinion intelligent monitoring and analysis method according to claim 1, characterized in that: the crawling public opinion information analysis is used for analyzing the public opinion diffusion speed corresponding to the news event, acquiring public opinion information sets of all target monitoring topics of all public opinion information crawling platforms in all acquisition time periods, further acquiring the number of participatory topic users corresponding to all target monitoring topics of all public opinion information crawling platforms in all acquisition time periods, acquiring the diffusion speed corresponding to all target monitoring topics of all public opinion information crawling platforms according to the number of participatory topic users corresponding to all target monitoring topics of all acquisition time periods, comparing the diffusion speed corresponding to all target monitoring topics of all public opinion information crawling platforms with the standard diffusion speed corresponding to the public opinion information, and further counting the early warning influence coefficient of all target monitoring diffusion speeds of all public opinion information crawling platforms.
6. The news public opinion intelligent monitoring and analysis method according to claim 1, characterized in that: the crawling public opinion information analysis is used for analyzing the public opinion guidance corresponding to the news event, obtaining the evaluation information corresponding to each participated topic user of each target monitoring topic of each public opinion information crawling platform in each collection time period, further analyzing the evaluation information corresponding to each participated topic user of each target monitoring topic of each public opinion information crawling platform in each collection time period, further obtaining the comprehensive public opinion guidance type corresponding to each target monitoring topic of each public opinion information crawling platform, matching and comparing the comprehensive public opinion guidance type corresponding to each target monitoring topic of each public opinion information crawling platform with the early warning influence coefficient corresponding to each public opinion guidance type in the database, and further obtaining the public opinion guidance early warning influence coefficient of each target monitoring topic of each public opinion information crawling platform.
7. The news public opinion intelligent monitoring and analysis method according to claim 1, characterized in that: the crawling public opinion information analysis is used for analyzing the public opinion diffusion range corresponding to the news event, numbers corresponding to all participating topic users of all target monitoring topics of each public opinion information crawling platform are obtained according to the public opinion information, categories corresponding to all participating topic users of all target monitoring topics of each public opinion information crawling platform are called, categories corresponding to all participating topic users of all target monitoring topics of each public opinion information crawling platform are compared with each other, the number of all categories of participating topic users of all target monitoring topics of each public opinion information crawling platform is counted, the category corresponding to the maximum number of all target monitoring topic participating topic users of each public opinion information crawling platform is screened out, the category is marked as all target monitoring main participating topic user categories of each public opinion information crawling platform, all target monitoring topic main participating user categories of each public opinion information crawling platform are obtained according to all the public opinion information crawling platforms, and extracting diffusion range early warning influence coefficients corresponding to the user categories from the database, and further acquiring the diffusion range early warning influence coefficients of the target monitoring topics of the public opinion information crawling platforms.
8. The news public opinion intelligent monitoring and analysis method according to claim 1, characterized in that: the crawling public opinion information analysis is used for carrying out comprehensive analysis on the public opinion diffusion speed and the public opinion guiding public opinion diffusion range corresponding to the news event, and carrying out early warning influence coefficients of the diffusion speed of each target monitoring topic of a crawling platform according to each piece of public opinion information to be counted, each target monitoring topic public opinion guiding early warning influence coefficient of each crawling platform for each piece of public opinion information and each target monitoring topic diffusion range early warning influence coefficient of each crawling platform for each piece of public opinion information, further carrying out statistics on each target monitoring topic comprehensive public opinion early warning influence coefficient of each crawling platform for each piece of public opinion information, carrying out comprehensive early warning influence coefficient of each target monitoring topic of each crawling platform for each piece of public opinion information according to each piece of public opinion information to be counted, carrying out statistics on the comprehensive early warning influence coefficients of the news event public opinion information, and obtaining the key processing platform for the news event public opinion information.
9. The utility model provides a news public opinion intelligent monitoring analytic system which characterized in that: the data processing and analyzing module is respectively connected with the news event basic information acquisition module, the public opinion information crawling platform basic information acquisition module, the topic information acquisition module, the public opinion information crawling module, the database and the public opinion information early warning terminal.
10. A computer storage medium, characterized in that: the computer storage medium is burned with a computer program, which when run in the memory of the server implements the method of any of the above claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210140428.0A CN114443930A (en) | 2022-02-16 | 2022-02-16 | News public opinion intelligent monitoring and analyzing method, system and computer storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210140428.0A CN114443930A (en) | 2022-02-16 | 2022-02-16 | News public opinion intelligent monitoring and analyzing method, system and computer storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114443930A true CN114443930A (en) | 2022-05-06 |
Family
ID=81373869
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210140428.0A Withdrawn CN114443930A (en) | 2022-02-16 | 2022-02-16 | News public opinion intelligent monitoring and analyzing method, system and computer storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114443930A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114912026A (en) * | 2022-05-30 | 2022-08-16 | 武汉嘉越似锦文化传媒有限公司 | Network public opinion monitoring analysis processing method, equipment and computer storage medium |
-
2022
- 2022-02-16 CN CN202210140428.0A patent/CN114443930A/en not_active Withdrawn
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114912026A (en) * | 2022-05-30 | 2022-08-16 | 武汉嘉越似锦文化传媒有限公司 | Network public opinion monitoring analysis processing method, equipment and computer storage medium |
| CN114912026B (en) * | 2022-05-30 | 2023-11-07 | 贵州梦动科技有限公司 | Network public opinion monitoring analysis processing method, equipment and computer storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107092596B (en) | Text emotion analysis method based on attention CNNs and CCR | |
| CN110516067B (en) | Public opinion monitoring method, system and storage medium based on topic detection | |
| CN109299271B (en) | Training sample generation method, text data method, public opinion event classification method and related equipment | |
| CN106202372A (en) | A kind of method of network text information emotional semantic classification | |
| CN113327140B (en) | Video advertisement putting effect intelligent analysis management system based on big data analysis | |
| CN112417127B (en) | Dialogue model training and dialogue generation methods, devices, equipment and media | |
| CN110737821B (en) | Similar event query method, device, storage medium and terminal equipment | |
| CN107180087B (en) | A kind of searching method and device | |
| CN113378565A (en) | Event analysis method, device and equipment for multi-source data fusion and storage medium | |
| Shekhawat | Sentiment classification of current public opinion on brexit: Naïve Bayes classifier model vs Python’s Textblob approach | |
| CN113032557A (en) | Microblog hot topic discovery method based on frequent word set and BERT semantics | |
| CN114077705A (en) | Method and system for portraying media account on social platform | |
| CN117520522B (en) | Intelligent dialogue method and device based on combination of RPA and AI and electronic equipment | |
| CN114443930A (en) | News public opinion intelligent monitoring and analyzing method, system and computer storage medium | |
| CN106372083B (en) | A kind of method and system that controversial news clue is found automatically | |
| CN107480126B (en) | Intelligent identification method for engineering material category | |
| CN117131345A (en) | Multi-source data parameter evaluation method based on data deep learning calculation | |
| CN113468868B (en) | NLP-based real-time network hot content analysis method | |
| CN109726938A (en) | A kind of students ' thinking political affairs situation method for early warning based on deep learning | |
| CN115186095A (en) | Juvenile text recognition method and device | |
| Hajare et al. | A machine learning pipeline to examine political bias with congressional speeches | |
| CN115248888A (en) | Data identification system for searching hot words through big data | |
| CN112434155A (en) | Comment quality classification method, device, equipment and readable medium | |
| CN113688623A (en) | Aspect level emotion analysis method based on deep learning | |
| CN111651565A (en) | False information identification system of social media platform |
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 | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20220506 |
|
| WW01 | Invention patent application withdrawn after publication |