CN112989161A - News public opinion monitoring method and device, electronic equipment and storage medium - Google Patents
News public opinion monitoring method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN112989161A CN112989161A CN202110260483.9A CN202110260483A CN112989161A CN 112989161 A CN112989161 A CN 112989161A CN 202110260483 A CN202110260483 A CN 202110260483A CN 112989161 A CN112989161 A CN 112989161A
- Authority
- CN
- China
- Prior art keywords
- news
- current period
- target subject
- monitoring
- target
- 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.)
- Pending
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 79
- 238000000034 method Methods 0.000 title claims abstract description 48
- 238000012806 monitoring device Methods 0.000 claims abstract description 8
- 230000008859 change Effects 0.000 claims description 69
- 230000002159 abnormal effect Effects 0.000 claims description 19
- 230000015654 memory Effects 0.000 claims description 17
- 238000004590 computer program Methods 0.000 claims description 14
- 238000005516 engineering process Methods 0.000 claims description 8
- 230000005540 biological transmission Effects 0.000 claims description 5
- 238000012552 review Methods 0.000 description 13
- 238000004422 calculation algorithm Methods 0.000 description 6
- 238000004364 calculation method Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 235000019633 pungent taste Nutrition 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 239000002699 waste material Substances 0.000 description 2
- 239000000969 carrier Substances 0.000 description 1
- 230000009193 crawling Effects 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2462—Approximate or statistical queries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2477—Temporal data queries
-
- 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
- G06F16/34—Browsing; Visualisation therefor
- G06F16/345—Summarisation for human users
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Probability & Statistics with Applications (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application is suitable for the technical field of big data, and provides a news public opinion monitoring method, a news public opinion monitoring device, electronic equipment and a readable storage medium. The method comprises the following steps: acquiring first news data of a target subject and second news data of a target group where the target subject is located in real time; determining the news broadcast volume of the target subject in the current period according to the first news data; determining the total news propagation volume of the target group in the current period according to the second news data, wherein the total news propagation volume is used for representing the sum of the news propagation volumes of all subjects in the target group; determining the news popularity ratio of the target subject in the current period according to the news propagation volume and the total news propagation volume; and monitoring the news public opinion of the target subject according to the news popularity ratio of the current period. The method can automatically monitor the news public sentiments in real time, and improves the real-time performance and accuracy of news public sentiment monitoring.
Description
Technical Field
The application belongs to the technical field of big data, and particularly relates to a news public opinion monitoring method, a news public opinion monitoring device, electronic equipment and a readable storage medium.
Background
With the rapid development of the internet, network media has become one of the main carriers of news public opinions. The news public sentiment in the network can reflect the attention degree of people to the hot event and can also reflect the influence range and the influence degree of the hot event. Therefore, monitoring of the network news public opinion is necessary.
In the traditional technology, for news public sentiment of a certain subject, the news public sentiment is mainly monitored based on the searching and counting results by manually searching and counting news reports related to the subject.
However, it takes a long time to manually search and count news reports one by one, which not only takes time and labor, but also has hysteresis in the obtained news public opinion information.
Disclosure of Invention
The application provides a news public opinion monitoring method, a device, an electronic device and a readable storage medium, which can solve the problem of lag in news public opinion monitoring in the traditional technology.
In a first aspect, an embodiment of the present application provides a news public opinion monitoring method, including:
acquiring first news data of a target subject and second news data of a target group where the target subject is located in real time;
determining the news broadcast volume of the target subject in the current period according to the first news data;
determining the total news propagation volume of the target group in the current period according to the second news data, wherein the total news propagation volume is used for representing the sum of the news propagation volumes of all subjects in the target group;
determining the news popularity ratio of the target subject in the current period according to the news propagation volume and the total news propagation volume;
and monitoring the news public opinion of the target subject according to the news popularity ratio of the current period.
In one embodiment, the monitoring of the news opinion of the target subject according to the news popularity ratio of the current period includes:
acquiring the news popularity ratio of the previous period;
determining the news popularity change rate of the current period according to the news popularity ratio of the previous period and the news popularity ratio of the current period;
and monitoring the news public opinion of the target subject according to the news heat change rate of the current period.
In one embodiment, the monitoring of the news opinion of the target subject according to the news heat change rate of the current period includes:
acquiring the news heat change rate of the previous period;
calculating the difference between the news heat change rate of the current period and the news heat change rate of the previous period to obtain the change rate difference value of the current period;
and monitoring the news public opinion of the target subject according to the change rate difference value of the current period.
In one embodiment, the monitoring the news opinion of the target subject according to the difference of the change rate of the current period includes:
and if the change rate difference value of the current period is larger than a preset threshold value, determining that the news public opinion of the target subject is abnormal.
In one embodiment, the first news data includes news information and news publication time corresponding to the news information, and the news information includes news reports, report forwarding and report comments; the determining the news broadcasting volume of the target subject in the current period according to the first news data comprises the following steps:
determining the times of the news reports, the times of the report forwarding and the times of the report comments in a preset time before the current time according to the news publishing time;
and determining the news broadcasting quantity according to the times of the news reports, the times of the report forwarding and the times of the report comments.
In one embodiment, the first news data includes news headlines, and the method further includes:
if the news public sentiment of the target subject is abnormal, clustering the news headlines in the current period to obtain a plurality of clustering results;
and respectively extracting the news headlines in each clustering result to obtain the text abstract of each clustering result.
In one embodiment, the obtaining first news data of the target subject in real time includes:
acquiring a keyword of the target subject;
and acquiring the first news data by utilizing a distributed crawler technology according to the keywords.
In a second aspect, an embodiment of the present application provides a news public opinion monitoring device, including:
the data acquisition module is used for acquiring first news data of a target main body and second news data of a target group where the target main body is located in real time;
the transmission amount determining module is used for determining the news transmission amount of the target main body in the current period according to the first news data;
a total propagation amount determining module, configured to determine, according to the second news data, a total news propagation amount of the target group in the current period, where the total news propagation amount is used to represent a sum of news propagation amounts of each subject in the target group;
the popularity ratio determining module is used for determining the news popularity ratio of the target subject in the current period according to the news propagation volume and the total news propagation volume;
and the monitoring module is used for monitoring the news public sentiment of the target subject according to the news popularity ratio of the current period.
In a third aspect, an embodiment of the present application provides an electronic device, including: the news public opinion monitoring method comprises a memory, a processor and a computer program which is stored in the memory and can run on the processor, wherein the processor executes the computer program to realize the news public opinion monitoring method in any one of the first aspect.
In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, where a computer program is stored, and when the computer program is executed by a processor, the method for monitoring news public sentiment according to any one of the first aspect is implemented.
According to the news public opinion monitoring method, the news public opinion monitoring device, the electronic equipment and the readable storage medium, the news broadcasting quantity of the target main body is determined through the first news data, the total news broadcasting quantity of the target group is determined through the second news data, the news popularity ratio of the current period is determined through the news broadcasting quantity and the total news broadcasting quantity, and therefore the news public opinion of the target main body is monitored according to the news popularity ratio. The news public opinion monitoring method, the device, the electronic equipment and the readable storage medium provided by the embodiment can realize automatic monitoring and real-time monitoring of news public opinions, avoid manual searching and statistics, and improve the statistical efficiency of news public opinion data, thereby improving the real-time performance and accuracy of news public opinion monitoring and solving the problems of time and labor waste and monitoring lag in the traditional technology. Meanwhile, the news popularity ratio can fully reflect the proportion of the news broadcasting volume of the target subject to the total news broadcasting volume of the target group, and the news public sentiment of the target subject can be more accurately monitored according to the news popularity ratio.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the embodiments or the prior art descriptions will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive exercise.
Fig. 1 is a schematic structural diagram of an electronic device according to an embodiment of the present application;
fig. 2 is a flowchart illustrating a news public opinion monitoring method according to an embodiment of the present application;
fig. 3 is a flowchart illustrating a news public opinion monitoring method according to another embodiment of the present application;
fig. 4 is a flowchart illustrating a news public opinion monitoring method according to another embodiment of the present application;
fig. 5 is a schematic structural diagram of a news public opinion monitoring device according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
It is to be understood that the terms "first," "second," "third," "fourth," and the like (if any) in the embodiments of the present application are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order.
It is understood that the term "and/or" as used herein refers to and includes any and all possible combinations of one or more of the associated listed items.
The news public opinion monitoring method provided by the embodiment of the application is used for monitoring the network news public opinion of the target main body and determining whether the news public opinion of the target main body is abnormal or not. Wherein the target subject includes, but is not limited to, a company, an individual, a product or a product brand, etc. Taking the target subject as an example of a company, the news public opinion monitoring result of the company can be used for financial investment, but is not limited to. The company basic surface is an important aspect of the research analysis of the individual shares performed by investors, and the news public opinion of the company is an important reason causing the price fluctuation of the individual shares. Without a special event, the news opinion of a company is smooth, sparse, or even absent. Once a company has a special event, the news popularity of the company is increased sharply, and the news public sentiment is abnormal. Therefore, for investors, the ability to obtain news and public opinions of companies in time is needed, so that the change of the companies is monitored according to the news and public opinions, and investment loss caused by information lag is avoided. The embodiment of the application aims to provide a news public opinion monitoring method to realize automatic monitoring of news public opinions and solve the problem of lag in news public opinion monitoring in the traditional technology.
The news public opinion monitoring method provided by the embodiment of the application can be applied to electronic equipment. Exemplarily, fig. 1 is a schematic structural diagram of an electronic device according to an embodiment of the present application. As shown in fig. 1, the electronic apparatus 1 may include: the news public opinion monitoring method provided by the embodiment of the application can be realized when the processor 10 executes the computer program 12, wherein the processor 10, the memory 11 and the computer program 12 are stored in the memory 11 and can run on the processor 10. The number and type of the processors 10 and the memories 11 are not limited in the embodiments of the present application.
The embodiment of the present application does not limit the type of the electronic device 1. For example, the computing device may be a desktop computer, a notebook, a palm top computer, a cloud server, and the like.
The technical solution in the present application will be described in detail below with reference to the accompanying drawings. It should be noted that, in the present application, different technical features may be combined with each other without conflict.
Fig. 2 shows a schematic flowchart of a news public opinion monitoring method provided by the present application. As shown in fig. 2, the news public opinion monitoring method provided in this embodiment may include:
s201, first news data of the target subject and second news data of the target group where the target subject is located are obtained in real time.
The first news data refers to news data related to the target subject. The first news data may include news information and news release time, etc. related to the target subject. The news information may include news reports directly published by news websites, microblogs, or WeChats, and may also include forwarding of published news reports (hereinafter, referred to as report forwarding), comments (hereinafter, referred to as report comments), or praise. It is understood that each news report, each report forward, each report review, and each like corresponds to a news publication time.
Alternatively, the first news data may be obtained by keyword search related to the target subject. Taking the first target subject as a certain marketing company as an example, the first news data can be obtained by obtaining keywords of the company and crawling the keywords in network channels such as news websites, microblogs, WeChats and the like by using a distributed crawler. For example, the keywords may include a company name of the company, a product brand of the company, a top management name of the company, and the like. Optionally, the distributed crawler may use an Acrap framework.
The target group can be determined according to the nature of the target subject and the specific application of the news public opinion monitoring result. For example, when the target subject is a certain listed company and the news opinion monitoring result is used for financial investment, all listed companies may be regarded as the target group, or a preset number of companies among the listed companies may be regarded as the target group. The second news data may include news information and news release times for all subjects within the target group. The second news data can be obtained through a related data statistics website, data statistics software and the like, and can also be obtained through a distributed crawler.
S202, according to the first news data, determining the news broadcasting volume of the target subject in the current period.
The news traffic is used to characterize the amount of dissemination of news information over the current time period. It can be understood that the statistical period of the news broadcast amount can be set according to actual needs, and can be a period of a week, a period of a day, or a period of an hour. Alternatively, for the statistics of the news broadcasting amount, the statistics may be performed in a sliding time window manner. And counting in a sliding time window mode, wherein the counting period duration of the news broadcast quantity is the window width of the sliding time window.
And determining the broadcast volume of the news information related to the target subject in the current period according to the first news data to obtain the news broadcast volume. Specifically, the news propagation amount may be determined according to one or more of the number of news stories related to the target subject, the number of story forwarding, the number of story review, the number of praise, and the like.
S203, determining the total news broadcast volume of the target group in the current period according to the second news data, wherein the total news broadcast volume is used for representing the sum of the news broadcast volumes of all the subjects in the target group.
The statistical period of the total news broadcast volume is the same as that of the target subject. The data type selected for the total newsfeed statistics is the same as the data type selected for the target subject's newsfeed statistics. For example, if the news propagation volume of the target subject is determined by the number of times of report forwarding, the total news propagation volume is obtained by calculating the sum of the number of times of report forwarding of all subjects in the target group; if the news propagation volume of the target subject is determined by the number of times of report forwarding and the number of times of report review, the total news propagation volume is obtained by calculating the sum of the number of times of report forwarding and the number of times of report review of all subjects in the target group.
And S204, determining the news popularity ratio of the target subject in the current period according to the news broadcast volume and the total news broadcast volume.
The news popularity ratio is used for representing the proportion of the news broadcast volume of the target subject in the current period to the total news broadcast volume of the target group. Optionally, the news popularity ratio may be obtained by directly calculating a ratio of the news broadcast volume to the total news broadcast volume, or by further calculating on the basis of the ratio of the news broadcast volume to the total news broadcast volume.
S205, monitoring the news public sentiment of the target subject according to the news popularity ratio of the current period.
And monitoring whether the news public sentiment of the target subject is abnormal in real time according to the calculated news popularity ratio. Optionally, when the value of the news popularity ratio exceeds a preset popularity ratio threshold, it is determined that the news public opinion is abnormal.
It is understood that, by repeating the above steps S201 to S205 every cycle, real-time dynamic monitoring of the target subject news opinion can be realized.
In this embodiment, the news popularity of the target subject is determined by the first news data, the total news popularity of the target group is determined by the second news data, and the popularity ratio of the news in the current period is determined by the news popularity and the total news popularity, so that the news public opinion of the target subject is monitored according to the news popularity ratio. The method provided by the embodiment can realize automatic monitoring and real-time monitoring of the news public sentiment, avoid manual searching and statistics, and improve the statistical efficiency of the news public sentiment data, thereby improving the real-time performance and accuracy of the news public sentiment monitoring and solving the problems of time and energy waste and lag in monitoring of the public sentiment monitoring in the traditional technology. Meanwhile, the news popularity ratio can fully reflect the proportion of the news broadcasting volume of the target subject to the total news broadcasting volume of the target group, and the news public sentiment of the target subject can be more accurately monitored according to the news popularity ratio.
In one embodiment, determining the news propagation amount of the target subject in the current period according to the first news data may be implemented by:
determining the times of news reports, report forwarding times and report comment times related to a target subject in a preset time before the current time according to the news publishing time; and determining the news transmission amount according to the times of news reports, the times of report forwarding and the times of report comments.
Specifically, assuming that the current time is T and the period is T, counting the times of news reports, the times of report forwarding and the times of report review when the news publication time is between T-T and T. The news reports may include reports of news websites, reports of microblogs, reports of WeChats, and the like. The number of times of report forwarding and the number of times of report review may include the number of times of forwarding and review of reports in a microblog or WeChat, and may also include the number of times of forwarding and review of reports in a news website.
And summing the report times, the report forwarding times and the report review times to obtain the news broadcast volume. The summation may be direct summation or weighted summation. Optionally, the number of reports, the number of report forwarding times, and the number of report review times acquired by each network channel may be summed respectively, and the summed results obtained by each network channel are summed to obtain the news broadcast volume.
Is exemplary, canBy the formula rt+wtCalculating to obtain news broadcast volume, wherein rtIndicates the number of news reports related to the target subject in the news website in the current period, wtAnd the sum of the number of news reports, the number of report comments and the number of report forwarding related to the target subject in the microblog in the current period is represented. Accordingly, the total news propagation amount in the current period can be obtained by calculating the sum of the times of news reports, report forwarding times and report review times related to all subjects in the target group. Then, the news popularity ratio of the target subject in the current period can be calculated by formula (1):
wherein h istA news popularity ratio indicating a current period, i indicates a serial number of a subject within the target group, ritRepresents the number of times, w, of news stories related to the ith subject in the target group in the news website in the current perioditAnd the sum of the times of news reports, report review times and report forwarding times related to the ith subject in the target group in the microblog in the current period is represented.
The frequency of news reports can reflect the attention of the media to news events, and the frequency of report forwarding and the frequency of report comments can reflect the attention of the public to news events. In the embodiment, the news broadcasting volume is determined according to the times of news reports, the times of report forwarding and the times of report comments, the attention of media and public to news events is comprehensively considered, and the obtained news broadcasting volume is more accurate, so that the monitoring of news public opinions is more accurate.
The following embodiments are provided to further explain a specific method for monitoring news opinions according to the popularity ratio of news in the current period.
Fig. 3 is a schematic flowchart of a news public opinion monitoring method according to another embodiment. As shown in fig. 3, the step S205 of monitoring news opinions of the target subject according to the news popularity ratio of the current period may include:
s301, obtaining the news popularity ratio of the previous period.
The specific calculation method of the news popularity ratio in the previous period and the calculation method of the news popularity ratio in the current period refer to the above embodiments, and are not described herein again.
S302, determining the news popularity change rate of the current period according to the news popularity ratio of the previous period and the news popularity ratio of the current period.
The news popularity change rate of the current period is used for representing the change proportion of the news popularity ratio of the current period compared with the news popularity ratio of the previous period. By way of example and not limitation, the rate of change of news popularity for the current period may be formulated
And (4) calculating. Wherein, ctNews heat change rate, h, representing the current periodtNews popularity ratio, h, representing the current periodt-1Indicating the news popularity ratio of the previous period.
And S303, monitoring the news public sentiment of the target subject according to the news heat change rate of the current period.
Optionally, the news hotness change rate c according to the current periodtAnd directly judging whether the news public sentiment of the target subject is abnormal or not. Specifically, if the news hotness change rate c of the current periodtAnd if the current time is greater than the first preset threshold value, determining that the news public sentiment of the target subject is abnormal. The news heat change rate can objectively reflect the change situation of the news heat ratio in the current period compared with the previous period, so the news heat change rate c passing through the current periodtWhether the news public sentiment of the target subject is abnormal or not can be accurately judged, and the method is simple.
Optionally, the news hotness change rate c of the previous period may be further obtainedt-1Calculating the news heat change rate c of the current periodtNews heat rate c from the previous periodt-1The difference is obtained to obtain the change rate difference value Delta c of the current periodtAccording to the difference Δ c of the change rate of the current cycletMonitoring target masterPhysical news consensus. In practical application, when the news popularity ratio changes steadily or decreases, the news public sentiment of the target subject is considered to be normal without much attention. When the news popularity ratio is suddenly increased, the news public sentiment is considered to be abnormal. The change rate difference can reflect the change situation of the news popularity ratio more accurately, so that the change situation of the public sentiment can be accurately judged according to the change rate difference.
Alternatively, the rate of change difference Δ c may be directly based on the current periodtAnd monitoring news public sentiments of the target subject. If the change rate difference value Delta c of the current periodtAnd if the second preset threshold value is larger than the second preset threshold value, determining that the news public opinion of the target subject is abnormal. The change rate difference of the current period is obtained by calculating the news heat change rate of the current period and the news heat change rate of the previous period, so that the change rate difference of the current period covers the news heat ratio of the current period and two periods before the current period, and the news public opinion result obtained by monitoring according to the change rate difference of the current period is more accurate.
Optionally, the difference Δ c between the change rates of the previous period may be further obtainedt-1If the change rate difference value Delta c of the current period is larger than the threshold value Delta ctGreater than the rate of change difference Δ c of the previous cyclet-1Then the news opinion of the target subject is abnormal. The change rate difference value of the current period covers the news popularity situation of the current period and two periods before the current period, and the change rate difference value of the previous period covers the news popularity situation of the previous period and two periods before the previous period, so that the news public opinion is monitored through the change rate difference value of the current period and the change rate difference value of the previous period, the news popularity situation of four periods is covered, and the accuracy of the news public opinion result is further improved.
Fig. 4 shows a schematic flowchart of a news public opinion monitoring method according to another embodiment of the present application. As shown in fig. 4, on the basis of the foregoing embodiment, the news public opinion monitoring method may further include:
s401, if the news public sentiment of the target subject is abnormal, clustering news titles in the current period to obtain a plurality of clustering results.
Optionally, the first news data may include a news title, and the news title is in a text form. The news headlines can reflect the content of news events, and clustering the news headlines is equivalent to classifying the news events. Alternatively, clustering may be performed by an x-means algorithm. Compared with the traditional k-means algorithm, the x-means algorithm does not need to specify the number of clusters, only needs to give an approximate range of the number of clusters, iteratively selects the optimal number of clusters according to the quality index of the clusters, and is simple in algorithm and high in calculation efficiency.
And clustering all news titles in the current period to obtain a plurality of clustering results, wherein each clustering result is a set of a plurality of news titles related to one news event.
S402, respectively extracting the news headlines in each clustering result to obtain the text abstract of each clustering result.
And for each clustering result, extracting the abstract of the news headline in the cluster to obtain a text abstract corresponding to the clustering result, and outputting the text abstract.
In this embodiment, when the news public opinion of the target subject is abnormal, the news headlines in the current period are clustered to obtain a plurality of clustering results, and the news headlines in each clustering result are respectively extracted to obtain the text abstract of each clustering result, so that the user can better know the specific news public opinion status, further news public opinion analysis is facilitated, and the practicability is high.
Optionally, the abstract extraction may be performed based on a Text ranking (Text Rank) algorithm. Specifically, the method can be realized by the following steps:
1) the news title is divided into sentences to obtain a plurality of sentences;
2) taking each sentence as a node, and establishing a candidate key sentence graph;
optionally, a co-occurrence relationship (co-occurrence) may be used to construct an edge between two nodes;
optionally, the similarity between any two sentences may be circularly calculated through the formula (2), and by setting a similarity threshold, edge connection between nodes corresponding to two sentences with lower similarity is removed, so as to construct a final key sentence graph;
wherein S isiRepresents the ith sentence of the plurality of sentences SjRepresenting the jth sentence, w, of a plurality of sentenceskRepresenting a word in a sentence, Similarity (S)i,Sj) Indicating the similarity. In the formula, the numerator part represents the number of the same word appearing in two sentences at the same time, and the denominator part is the sum of the logarithms of the numbers of the words in the sentences. By adopting the calculation mode to calculate the similarity between the two sentences, the advantages of longer sentences in similarity calculation can be restrained, and the obtained similarity is more accurate.
4) Iteratively calculating the Text Rank value of each node in the key sentence graph;
5) sorting the nodes in the key sentence graph in a reverse order according to the Text Rank value to obtain a node sorting table;
6) obtaining sentences corresponding to the first k nodes in the node sorting table, and combining the sentences to obtain a text abstract; wherein k is a positive integer; alternatively, k may be 3 or 4.
In the embodiment, the abstract is extracted through the text sorting algorithm, the abstract can be directly extracted from the news headlines, learning training on a plurality of documents is not needed in advance, and the text abstract can be simply and effectively extracted.
Fig. 5 shows a block diagram of a news public opinion monitoring device according to an embodiment of the present application. As shown in fig. 5, the news public opinion monitoring apparatus provided in this embodiment may include:
the data acquisition module 501 is configured to acquire first news data of a target subject and second news data of a target group where the target subject is located in real time;
a broadcast volume determining module 502, configured to determine, according to the first news data, a news broadcast volume of the target subject in a current period;
a total propagation amount determining module 503, configured to determine, according to the second news data, a total news propagation amount of the target group in the current period, where the total news propagation amount is used to represent a sum of news propagation amounts of each subject in the target group;
a popularity ratio determining module 504, configured to determine a news popularity ratio of the target subject in the current period according to the news propagation volume and the total news propagation volume;
and a monitoring module 505, configured to monitor the news public opinion of the target subject according to the news popularity ratio of the current period.
In one embodiment, the monitoring module 505 is specifically configured to obtain a news popularity ratio of a previous period; determining the news popularity change rate of the current period according to the news popularity ratio of the previous period and the news popularity ratio of the current period; and monitoring the news public opinion of the target subject according to the news heat change rate of the current period.
In one embodiment, the monitoring module 505 is specifically configured to obtain a news popularity change rate of a previous period; calculating the difference between the news heat change rate of the current period and the news heat change rate of the previous period to obtain the change rate difference value of the current period; and if the change rate difference value of the current period is larger than a preset threshold value, determining that the news public opinion of the target subject is abnormal.
In one embodiment, the monitoring module 505 is specifically configured to obtain a news popularity change rate of a previous period; calculating the difference between the news heat change rate of the current period and the news heat change rate of the previous period to obtain the change rate difference value of the current period; obtaining a change rate difference value of the previous period; and monitoring the news public opinion of the target subject according to the change rate difference value of the current period.
In an embodiment, the monitoring module 505 is specifically configured to determine that the target subject's news opinion is abnormal if the difference of the change rates of the current period is greater than the difference of the change rates of the heat of the previous period.
In one embodiment, the first news data includes news information and news publication time corresponding to the news information, the news information including news stories, story forwarding, and story reviews; the propagation amount determining module 502 is specifically configured to determine, according to the news publication time, the number of times of the news reports, the number of times of the report forwarding, and the number of times of the report comments in a preset time period before the current time; and determining the news broadcasting quantity according to the times of the news reports, the times of the report forwarding and the times of the report comments.
In an embodiment, the apparatus for monitoring public news opinion further includes an abstract extracting module 506, configured to cluster the news titles in a current period to obtain a plurality of clustering results if the public news opinion of the target subject is abnormal; and respectively extracting the news headlines in each clustering result to obtain the text abstract of each clustering result.
In one embodiment, the data obtaining module 501 is specifically configured to obtain the keywords of the target subject; and acquiring the first news data by utilizing a distributed crawler technology according to the keywords.
The news public opinion monitoring device provided in this embodiment is used for executing the news public opinion monitoring method provided in the embodiment of the method of the present application, and the technical principle and the technical effect are similar, which can be specifically referred to the part of the embodiment of the method and are not described herein again.
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-mentioned division of the functional units and modules is illustrated, and in practical applications, the above-mentioned function distribution may be performed by different functional units and modules according to needs, that is, the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-mentioned functions. Each functional unit and module in the embodiments may be integrated in one processing unit, or each unit may exist alone physically, or two or more units are integrated in one unit, and the integrated unit may be implemented in a form of hardware, or in a form of software functional unit. In addition, specific names of the functional units and modules are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present application. The specific working processes of the units and modules in the system may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
An embodiment of the present application further provides an electronic device, for example, as shown in fig. 1, the electronic device includes: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, the processor implementing the steps of any of the method embodiments described above when executing the computer program.
Embodiments of the present application further provide a computer-readable storage medium, which stores a computer program, and when the computer program is executed by a processor, the computer program can implement the steps in any of the above method embodiments.
It will be appreciated by those of ordinary skill in the art that any reference to memory, storage, databases, or other media used in the embodiments provided herein may include non-volatile and/or volatile memory. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
The above-mentioned embodiments are only used for illustrating the technical solutions of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not substantially depart from the spirit and scope of the embodiments of the present application and are intended to be included within the scope of the present application.
Claims (10)
1. A news public opinion monitoring method is characterized by comprising the following steps:
acquiring first news data of a target subject and second news data of a target group where the target subject is located in real time;
determining the news broadcast volume of the target subject in the current period according to the first news data;
determining the total news propagation volume of the target group in the current period according to the second news data, wherein the total news propagation volume is used for representing the sum of the news propagation volumes of all subjects in the target group;
determining the news popularity ratio of the target subject in the current period according to the news propagation volume and the total news propagation volume;
and monitoring the news public opinion of the target subject according to the news popularity ratio of the current period.
2. The method of claim 1, wherein the monitoring of the target subject's news opinion according to the current period news popularity ratio comprises:
acquiring the news popularity ratio of the previous period;
determining the news popularity change rate of the current period according to the news popularity ratio of the previous period and the news popularity ratio of the current period;
and monitoring the news public opinion of the target subject according to the news heat change rate of the current period.
3. The method of claim 2, wherein the monitoring the target subject's news opinion according to the news heat change rate of the current period comprises:
acquiring the news heat change rate of the previous period;
calculating the difference between the news heat change rate of the current period and the news heat change rate of the previous period to obtain the change rate difference value of the current period;
and monitoring the news public opinion of the target subject according to the change rate difference value of the current period.
4. The method of claim 3, wherein the monitoring the target subject's news consensus based on the difference in the rate of change of the current cycle comprises:
and if the change rate difference value of the current period is larger than a preset threshold value, determining that the news public opinion of the target subject is abnormal.
5. The method of claim 1, wherein the first news data comprises news information and news publication time corresponding to the news information, the news information comprising news stories, story forwarding, and story comments; the determining the news broadcasting volume of the target subject in the current period according to the first news data comprises the following steps:
determining the times of the news reports, the times of the report forwarding and the times of the report comments in a preset time before the current time according to the news publishing time;
and determining the news broadcasting quantity according to the times of the news reports, the times of the report forwarding and the times of the report comments.
6. The method of claim 1, wherein the first news data comprises a news headline, the method further comprising:
if the news public sentiment of the target subject is abnormal, clustering the news headlines in the current period to obtain a plurality of clustering results;
and respectively extracting the news headlines in each clustering result to obtain the text abstract of each clustering result.
7. The method of any one of claims 1 to 6, wherein the obtaining first news data of the target subject in real-time comprises:
acquiring a keyword of the target subject;
and acquiring the first news data by utilizing a distributed crawler technology according to the keywords.
8. The utility model provides a news public opinion monitoring device which characterized in that includes:
the data acquisition module is used for acquiring first news data of a target main body and second news data of a target group where the target main body is located in real time;
the transmission amount determining module is used for determining the news transmission amount of the target main body in the current period according to the first news data;
a total propagation amount determining module, configured to determine, according to the second news data, a total news propagation amount of the target group in the current period, where the total news propagation amount is used to represent a sum of news propagation amounts of each subject in the target group;
the popularity ratio determining module is used for determining the news popularity ratio of the target subject in the current period according to the news propagation volume and the total news propagation volume;
and the monitoring module is used for monitoring the news public sentiment of the target subject according to the news popularity ratio of the current period.
9. An electronic device, comprising: memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing the method according to any of claims 1 to 7 when executing the computer program.
10. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program which, when executed by a processor, implements the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110260483.9A CN112989161A (en) | 2021-03-10 | 2021-03-10 | News public opinion monitoring method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110260483.9A CN112989161A (en) | 2021-03-10 | 2021-03-10 | News public opinion monitoring method and device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112989161A true CN112989161A (en) | 2021-06-18 |
Family
ID=76336338
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110260483.9A Pending CN112989161A (en) | 2021-03-10 | 2021-03-10 | News public opinion monitoring method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112989161A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113590914A (en) * | 2021-06-23 | 2021-11-02 | 北京百度网讯科技有限公司 | Information processing method, device, electronic equipment and storage medium |
| CN116340639A (en) * | 2023-03-31 | 2023-06-27 | 北京百度网讯科技有限公司 | News recall method, device, equipment and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107908694A (en) * | 2017-11-01 | 2018-04-13 | 平安科技（深圳）有限公司 | Public sentiment clustering method, application server and the computer-readable recording medium of internet news |
| CN109657116A (en) * | 2018-11-12 | 2019-04-19 | 平安科技（深圳）有限公司 | A kind of public sentiment searching method, searcher, storage medium and terminal device |
| WO2019227710A1 (en) * | 2018-05-31 | 2019-12-05 | 平安科技（深圳）有限公司 | Network public opinion analysis method and apparatus, and computer-readable storage medium |
| CN111737555A (en) * | 2020-06-18 | 2020-10-02 | 苏州朗动网络科技有限公司 | Method and device for selecting hot keywords and storage medium |
-
2021
- 2021-03-10 CN CN202110260483.9A patent/CN112989161A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107908694A (en) * | 2017-11-01 | 2018-04-13 | 平安科技（深圳）有限公司 | Public sentiment clustering method, application server and the computer-readable recording medium of internet news |
| WO2019227710A1 (en) * | 2018-05-31 | 2019-12-05 | 平安科技（深圳）有限公司 | Network public opinion analysis method and apparatus, and computer-readable storage medium |
| CN109657116A (en) * | 2018-11-12 | 2019-04-19 | 平安科技（深圳）有限公司 | A kind of public sentiment searching method, searcher, storage medium and terminal device |
| CN111737555A (en) * | 2020-06-18 | 2020-10-02 | 苏州朗动网络科技有限公司 | Method and device for selecting hot keywords and storage medium |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113590914A (en) * | 2021-06-23 | 2021-11-02 | 北京百度网讯科技有限公司 | Information processing method, device, electronic equipment and storage medium |
| CN113590914B (en) * | 2021-06-23 | 2024-02-20 | 北京百度网讯科技有限公司 | Information processing method, apparatus, electronic device and storage medium |
| CN116340639A (en) * | 2023-03-31 | 2023-06-27 | 北京百度网讯科技有限公司 | News recall method, device, equipment and storage medium |
| CN116340639B (en) * | 2023-03-31 | 2023-12-12 | 北京百度网讯科技有限公司 | News recall method, device, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Oliveira et al. | Can social media reveal the preferences of voters? A comparison between sentiment analysis and traditional opinion polls | |
| He et al. | Predicting the popularity of web 2.0 items based on user comments | |
| Ruiz et al. | Correlating financial time series with micro-blogging activity | |
| Jeon et al. | A framework to predict the quality of answers with non-textual features | |
| Alvanaki et al. | See what's enBlogue: real-time emergent topic identification in social media | |
| Qamra et al. | Mining blog stories using community-based and temporal clustering | |
| US9208441B2 (en) | Information processing apparatus, information processing method, and program | |
| Li et al. | Enhancing clustering blog documents by utilizing author/reader comments | |
| US20080104034A1 (en) | Method For Scoring Changes to a Webpage | |
| Paltoglou | Sentiment‐based event detection in T witter | |
| Mahyuddin et al. | Behavior of the resources in the growth of social network | |
| US10592841B2 (en) | Automatic clustering by topic and prioritizing online feed items | |
| CN111026868B (en) | Multi-dimensional public opinion crisis prediction method, terminal device and storage medium | |
| CN106557552B (en) | Network topic heat prediction method | |
| Tsigilis et al. | Impact factors of the sport sciences journals: Current trends, relative positions, and temporal stability | |
| Li et al. | A hybrid model for experts finding in community question answering | |
| Bahamonde et al. | Power structure in Chilean news media | |
| CN112989161A (en) | News public opinion monitoring method and device, electronic equipment and storage medium | |
| Wu et al. | Extracting topics based on Word2Vec and improved Jaccard similarity coefficient | |
| CN110825868A (en) | Topic popularity based text pushing method, terminal device and storage medium | |
| CN110196941B (en) | Information recommendation method, device, server and storage medium | |
| Zhao et al. | Research on the impact evaluation of academic journals based on altmetrics and citation indicators | |
| Huang et al. | Retweet behavior prediction in twitter | |
| Wang et al. | Group article recommendation based on ER rule in Scientific Social Networks | |
| Erfanmanesh et al. | What can Bookmetrix tell us about the impact of Springer Nature’s books |
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 |