CN113065975A - Method, system and terminal for calculating focusing degree and evolution relation of network public sentiment topics - Google Patents
Method, system and terminal for calculating focusing degree and evolution relation of network public sentiment topics Download PDFInfo
- Publication number
- CN113065975A CN113065975A CN202110309223.6A CN202110309223A CN113065975A CN 113065975 A CN113065975 A CN 113065975A CN 202110309223 A CN202110309223 A CN 202110309223A CN 113065975 A CN113065975 A CN 113065975A
- Authority
- CN
- China
- Prior art keywords
- degree
- public opinion
- topic
- topics
- evolution
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/01—Social networking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
Abstract
The invention discloses a method, a system and a terminal for calculating the focusing degree and the evolution relation of network public sentiment topics, and relates to the technical field of network space cognition. Introducing the public opinion evolution degree into a social platform network public opinion topic focusing degree monitoring system; the focus degree index calculation based on the absolute value of the posting heat degree is converted into more reasonable relative ratio calculation; monitoring and capturing hot topics by utilizing a text clustering and topic extraction model based on a machine learning natural language processing algorithm; and obtaining a hot topic monitoring mode of the topic ranking list focused by the user attention point by counting and counting the behaviors of posting, forwarding, commenting and appropriating the attention user related to the topic label. The system realizes omnibearing, deepened and intelligent monitoring, meets the monitoring and analyzing requirements of the focusing degree of the network public opinion topics of different user social platforms, overcomes the defects of the existing network public opinion monitoring system and technology, and efficiently meets the network public opinion monitoring requirements of dynamic change.
Description
Technical Field
The invention belongs to the technical field of network space cognition, and particularly relates to a method for calculating the focusing degree and the evolution relation of network public sentiment topics.
Background
Topic focus capture in the existing social platform network media mainly generates topics in a user-defined topic tag mode, and obtains a topic ranking list focused by user focus in a mode of counting and counting user behaviors related to topic tags, such as text pasting, forwarding, comment, praise and follow-up. The ranking list not only can be used as a functional module of a social network platform to be displayed to users, but also can provide information support for relevant departments to know network public sentiments and conduct public sentiment guidance.
The existing social network public opinion topic focusing degree monitoring method mainly has the following problems:
(1) the existing method for monitoring the focusing degree of the social network public sentiment topics mainly comprises the steps of automatically counting the occurrence times of topic labels marked by users, presenting a plurality of topics before ranking the accumulated occurrence times in unit time as focus topics to the users, and using the absolute values of the occurrence times of the labels of the topics as ranking reference bases. The method can only embody labels with more relative occurrence times in the transverse comparison of the topics, but cannot reflect the actual relative focusing degree of the specific topics in the whole network, and cannot embody the focusing degree of the whole public sentiment wind direction of the whole network. For example, when the overall public sentiment focus of the whole network is quite dispersed, topics occupying the top of the topic hotspot ranking list may not have high topic focusing degree in the social network actually, but only the absolute times of reference of the topic labels are slightly higher than other topics; on the other hand, when the overall public opinion activity of the whole network is not high but the topics are concentrated, the topic label quote absolute times of the focused topics may not be higher than other monitoring dates with the overall public opinion activity of the whole network, but the relative value of the overall public opinion discussion proportion of the whole network occupied by the topic label quotes may be very high, and represents a considerable proportion of the current-day public opinion hotspots discussed in a concentrated way.
(2) The statistical mechanism of the current hot topic ranking list lacks deep mining of the relevance and the evolution trend between the hot and the focus topic, and simply lists the first few topics which appear most frequently in the daily-appearing topic tags. However, when considering the overall evaluation of the wind direction focusing degree of social network, it should be noted that there are strong correlations between many focused topics, even different expressions of the same concept. Such strong correlation between the focused topics, or the evolution trend of a single focused topic to multiple related focused topics, also constitutes an important component of the focusing degree of the wind direction topic of the internet public opinion, and therefore should be taken into consideration in the calculation and analysis of the focusing degree of the internet public opinion topics.
(3) The topic sources of the current social network platform are generated in a user-defined topic label (#) mode, the definition and judgment of topics are completely mastered by a user and are performed spontaneously, and various problems that the same actual topic is repeatedly defined by various expression modes, topic definitions are omitted, misinterpretation is caused, standards are different and the like may occur, so that the inaccuracy of the network public opinion topic focusing degree and the evolution relation calculation evaluation result is caused.
Disclosure of Invention
In order to solve the problems in the prior art, the invention provides a method for calculating the focusing degree and the evolution relation of network public sentiment topics.
The invention is realized in such a way that a method for calculating the focusing degree and the evolution relation of the network public opinion topics is applied to an information data processing terminal, and the method for calculating the focusing degree and the evolution relation of the network public opinion topics comprises the following steps:
the method comprises the steps of firstly, introducing public opinion evolution degree into a social platform network public opinion topic focusing degree monitoring system;
step two, the focus degree index calculation based on the absolute value of the posting heat degree is converted into more reasonable relative ratio calculation;
thirdly, monitoring and capturing hot topics by utilizing a text clustering and topic extraction model based on a machine learning natural language processing algorithm;
and fourthly, obtaining a hot topic monitoring mode of the topic ranking list focused by the user focus points by counting and counting the behaviors of the users concerned with the topic labels, such as text pasting, forwarding, comment and approval of the user concerned.
In one embodiment, in step two, the calculation of the focus level index comprises the steps of:
counting the total posting amount of the current social network platform, and crawling all posting content information of the current social network platform;
according to the collected posting content information, text clustering and topic extraction are carried out by utilizing a machine learning algorithm based on a natural language processing technology;
and forming a hot topic ranking list of the current day according to the topic extraction result, selecting the hot topics of the top N positions of the ranking list according to user-defined parameters, and calculating the proportion of the number of posts contained in the top N hot topics to the total post volume of the social network platform of the current day as an index value of the N-order public opinion power of the current day.
In one embodiment, wherein the public opinion power calculation formula is:
the post _ count (i) is the number of posts included in the ith topic named on the hot topic ranking list, and the post _ count _ all is the total posting volume of the social network platform on the current day.
In one embodiment, in the step one, the public opinion performance degree is calculated based on the extraction of the hot topics N-bit before the ranking list of the hot topics on the day in the public opinion power calculation process;
after determining the hot topics with N positions before ranking in the ranking list of the hot topics on the current day, analyzing and extracting K key words in the post text content corresponding to each topic in the hot topics with N positions before ranking by using a text word segmentation technology processed by natural language according to a user-defined parameter K;
calculating the ratio of the number of intersection elements to the number of union elements between every two K-element hot word sets of each hot topic with N top ranks, and generating the sum
And summing the calculation results to obtain the (N, K) order public opinion evolution degree index value of the current day.
In one embodiment, the public opinion evolution degree calculation formula is as follows:
wherein word _ setK(x) And representing a set of K keywords extracted from all the post contents corresponding to the x-th topic on the ranking list of the hot topic on the day.
In one embodiment, a daily public opinion power index and a public opinion evolution index value are calculated through public opinion varying power, respective weights are calculated for the daily public opinion power and public opinion evolution data in a given time range by using an entropy power method, and a daily comprehensive public opinion zooming index value is obtained by calculating the weighted sum of the daily public opinion power and the public opinion evolution according to the weighting result of the entropy power method.
In one embodiment, the public opinion zoom level calculation formula is:
focus_diffusion_index
＝weight(focus_index)×focus_index
+weight(diffusion_index)×diffusion_index
wherein, weight (x) represents the weight of index x after weighting by entropy weighting method.
The invention also aims to provide a system for realizing the method for calculating the focusing degree and the evolution relation of the network public opinion topics, the system for calculating the focusing degree and the evolution relation of the network public opinion topics is provided with a public opinion zooming degree unit, the public opinion zooming degree unit calculates respective weights by applying an entropy weight method through historical data, obtains an overall public opinion zooming degree according to the weights and the calculation, and quantitatively reflects the comprehensive situation of the focusing degree and the evolution relation of the social network public opinion topics.
In one embodiment, the public opinion zoom unit comprises:
the public opinion power calculating unit reflects the focusing degree of the overall public opinion atmosphere of the social network on the hot topics with the front rank on the overall network public opinion;
and the public opinion performance variation degree calculating unit reflects the correlation degree between the public opinion hot topics.
Another object of the present invention is to provide an information data processing terminal including a memory and a processor, the memory storing a computer program, the computer program, when executed by the processor, causing the processor to execute a method of calculating a degree of focus and an evolutionary relationship of the cyber public sentiment topic.
By combining all the technical schemes, the invention has the advantages and positive effects that:
the system realizes omnibearing, deepened and intelligent monitoring, meets the monitoring and analyzing requirements of the focusing degree of the network public opinion topics of different user social platforms, overcomes the defects of the existing network public opinion monitoring system and technology, provides support for public opinion research and judgment, and efficiently meets the network public opinion monitoring requirements of dynamic change.
In practical application tests, the technical scheme plays an important role in the public sentiment information and social event analysis process of the social network platform in certain areas of China. During the experiment monitoring process of three consecutive months in 2020, six times of the variable power overall trend peak value, one time of the public opinion power peak value and five times of the evolution power peak value are monitored for a certain research target social network platform. The peak signal information provided by the zoom degree monitoring data is checked and analyzed by combining other public opinion analysis indexes and social news events to display the result, the public opinion zoom degree, the two-level index public opinion focal power thereof and the abnormal peak value of the public opinion performance degree can establish strong corresponding relation with the important public events in the real society, and can reveal hidden relations among a plurality of focus topics associated with the same social public event to a certain extent, including the appearance rules, the advance or lag time periods and the like of different types of topics before and after the event occurs.
In contrast, the existing public opinion focus analysis technical means based on the user-defined topic keyword tag highly depends on the opening degree of the user behavior and the social network platform data, and is not convenient for relevant departments to actively carry out public opinion monitoring analysis. Moreover, the daily hot topic ranking list based on the topic keywords can only show the static topic focusing situation, but cannot show the time variation trend of the topic focusing degree, and cannot show the hidden association relationship between the focused topics. Therefore, the technical scheme can more effectively, accurately and comprehensively serve relevant government monitoring departments, and supports monitoring, studying and judging and even early warning of public events of the major society through public opinion zooming degree index analysis of focal topics and incidence relations thereof changing along with time.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and together with the description, serve to explain the principles of the disclosure.
Fig. 1 is a diagram of a social network public opinion wind direction zooming index system according to an embodiment of the present invention.
Fig. 2 is a flow chart of public opinion power calculation according to an embodiment of the present invention.
Fig. 3 is a flow chart of public opinion evolution calculation according to an embodiment of the present invention.
Fig. 4 is a flow chart of public opinion zoom level calculation according to an embodiment of the present invention.
Fig. 5 is a flowchart of comprehensive analysis and index calculation of the network public opinion topic focusing degree and evolution relationship according to an embodiment of the present invention.
Detailed Description
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in detail below. In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention. This invention may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein, but rather should be construed as broadly as the present invention is capable of modification in various respects, all without departing from the spirit and scope of the present invention.
It will be understood that when an element is referred to as being "secured to" another element, it can be directly on the other element or intervening elements may also be present. When an element is referred to as being "connected" to another element, it can be directly connected to the other element or intervening elements may also be present. As used herein, the terms "vertical," "horizontal," "left," "right," and the like are for purposes of illustration only and are not intended to represent the only embodiments.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The terminology used in the description of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used herein, the term "and/or" includes any and all combinations of one or more of the associated listed items.
The social network public opinion wind direction variable power index system is composed of two main secondary indexes of public opinion power and public opinion evolution degree, wherein the public opinion power reflects the focusing degree of the whole public opinion atmosphere of the social network on the hot topic of the front rank on the whole network public opinion; the degree of public sentiment change reflects the degree of association between public opinion hot topics. The two secondary indexes are calculated through historical data by applying an entropy weight method to obtain respective weights, the overall public sentiment variation degree is obtained through weighting and calculation, and the comprehensive condition of the focusing degree and the evolution relation of the social network public sentiment topics is reflected quantitatively.
1. Public opinion focal power calculating process and method
For the calculation of public opinion focal power, the total posting amount of the social network platform on the day is counted firstly, and all posting content information of the social network platform on the day is crawled. And performing text clustering and topic extraction by using a machine learning algorithm based on a natural language processing technology according to the collected posting content information. And forming a hot topic ranking list of the current day according to the topic extraction result, selecting the hot topics of the top N positions of the ranking list according to user-defined parameters, and calculating the proportion of the number of posts contained in the top N hot topics to the total post volume of the social network platform of the current day as an index value of the N-order public opinion power of the current day.
The public opinion focal power calculation formula is as follows:
the post _ count (i) is the number of posts included in the ith topic named on the hot topic ranking list, and the post _ count _ all is the total posting volume of the social network platform on the current day.
2. Public opinion performance variable degree calculating process and method
And the public opinion performance degree is calculated based on the extraction of hot topics N before the ranking of the hot topic ranking list of the current day in the public opinion focal power calculation process. After determining the hot topics with N top ranks in the hot topic ranking list of the current day, analyzing and extracting K keywords in the post content corresponding to each topic in the hot topics with N top ranks by using a text word segmentation technology of natural language processing according to a user-defined parameter K. Then, for each K-element hot word set of the hot topics with N top ranks, calculating the ratio of the number of intersection elements to the number of union elements, and generating the total number
And summing the calculation results to obtain the (N, K) order public opinion evolution degree index value of the current day.
The public opinion performance degree calculation formula is as follows:
wherein word _ setK(x) And representing a set of K keywords extracted from all the post contents corresponding to the x-th topic on the ranking list of the hot topic on the day.
3. Public opinion variable power calculating process and method
The public opinion focal power is calculated by calculating respective weights of the public opinion focal power and public opinion evolution degree data of each day in a given time range by using an entropy weight method on the basis of the calculation of the public opinion focal power index and the public opinion evolution degree index value of each day, and calculating the weighted sum of the public opinion focal power and the public opinion evolution degree of each day according to the weighting result of the entropy weight method to obtain the current comprehensive public opinion zoom degree index value.
The public sentiment variable power calculation formula is as follows:
focus_diffusion_index
＝weight(focus_index)×focus_index
+weight(diffusion_index)×diffusion_index
wherein, weight (x) represents the weight of index x after weighting by entropy weighting method.
In the implementation process of the technical scheme, all posting content information of the social network platform on the same day needs to be crawled and the total posting amount is counted. And performing text clustering analysis on all crawled paste text contents by utilizing a natural language processing technology in machine learning, so as to extract common topics contained in the paste text. And further, the number of the stickers contained in each topic is sequenced, and hot topics N bits before the number of the stickers on the day are counted. And for any positive integer N defined by the user, summing the number of the posts contained in the ith hot topic when the discrete variable i takes all values from 1 to N, and calculating the ratio of the total number of the posts of the hot topic to the total number of all the posts crawled on the day to serve as the public opinion power index on the day.
Meanwhile, according to the number K of the keywords defined by the user, extracting K keywords from each of the N hot topics in the current day by using a natural language processing technology. And calculating the ratio of the number of intersection elements to the number of union elements between every two generated K-element keyword sets, summing the calculated ratios, wherein the calculated result is the public opinion evolution degree index of the current day and reflects the proportion of the number of common keywords between the focal topics of the current day to the total number of the keywords of the focal topics.
On the basis of calculating public opinion focal power and public opinion performance degree, weighting is carried out on the public opinion focal power and the public opinion performance degree by an entropy weight method according to historical data in a period of time, and the weighted sum of the public opinion focal power and the public opinion performance degree is calculated to be used as a public opinion zoom degree index on the current day.
Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This application is intended to cover any variations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.
It will be understood that the present disclosure is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure should be limited only by the attached claims.
Claims (10)
1. A method for calculating the focusing degree and the evolution relation of an online public opinion topic is characterized by being applied to an information data processing terminal and comprises the following steps:
the method comprises the steps of firstly, introducing public opinion evolution degree into a social platform network public opinion topic focusing degree monitoring system;
step two, the focus degree index calculation based on the absolute value of the posting heat degree is converted into more reasonable relative ratio calculation;
thirdly, monitoring and capturing hot topics by utilizing a text clustering and topic extraction model based on a machine learning natural language processing algorithm;
and fourthly, obtaining a hot topic monitoring mode of the topic ranking list focused by the user focus points by counting and counting the behaviors of the users concerned with the topic labels, such as text pasting, forwarding, comment and approval of the user concerned.
2. The method for calculating the internet public opinion topic focus degree and evolution relation according to claim 1, wherein in the second step, the calculation of the focus degree index includes the following steps:
counting the total posting amount of the current social network platform, and crawling all posting content information of the current social network platform;
according to the collected posting content information, text clustering and topic extraction are carried out by utilizing a machine learning algorithm based on a natural language processing technology;
and forming a hot topic ranking list of the current day according to the topic extraction result, selecting the hot topics of the top N positions of the ranking list according to user-defined parameters, and calculating the proportion of the number of posts contained in the top N hot topics to the total post volume of the social network platform of the current day as an index value of the N-order public opinion power of the current day.
3. The method for calculating the degree of focusing and the evolution relationship of the internet public opinion topic according to claim 2, wherein the public opinion power calculation formula is:
the post _ count (i) is the number of posts included in the ith topic named on the hot topic ranking list, and the post _ count _ all is the total posting volume of the social network platform on the current day.
4. The method for calculating the degree of focusing and the evolution relation of the network public opinion topics as claimed in claim 1, wherein in the step one, the public opinion evolution degree is calculated based on the extraction of the hot topics N before the ranking list of the hot topics of the current day in the public opinion power calculation process;
after determining the hot topics with N positions before ranking in the ranking list of the hot topics on the current day, analyzing and extracting K key words in the post text content corresponding to each topic in the hot topics with N positions before ranking by using a text word segmentation technology processed by natural language according to a user-defined parameter K;
calculating the ratio of the number of intersection elements to the number of union elements between every two K-element hot word sets of each hot topic with N top ranks, and generating the sum
And summing the calculation results to obtain the (N, K) order public opinion evolution degree index value of the current day.
5. The method for calculating the degree of focusing and the evolution relation of the internet public opinion topics as claimed in claim 4, wherein the public opinion evolution degree calculation formula is as follows:
wherein word _ setK(x) And representing a set of K keywords extracted from all the post contents corresponding to the x-th topic on the ranking list of the hot topic on the day.
6. The method as claimed in claim 1, wherein the method for calculating the degree of focusing on the internet public sentiment topic and the degree of evolution thereof comprises calculating a daily public sentiment power index and a public sentiment evolution index value by a public sentiment power, calculating respective weights of the daily public sentiment power and the public sentiment evolution data in a given time range by an entropy power method, and calculating a weighted sum of the daily public sentiment power and the public sentiment evolution according to the weighting result of the entropy power method to obtain the daily comprehensive public sentiment zoom index value.
7. The method for calculating the degree of focusing and the evolution relationship of the internet public sentiment topic according to claim 6, wherein the public sentiment zoom degree calculation formula is as follows:
focus_diffusion_index
＝weight(focus_index)×focus_index
+weight(diffusion_index)×diffusion_index
wherein, weight (x) represents the weight of index x after weighting by entropy weighting method.
8. A system for realizing the method for calculating the focusing degree and the evolution relation of the network public opinion topics as claimed in any one of claims 1 to 7, characterized in that the system for calculating the focusing degree and the evolution relation of the network public opinion topics is provided with a public opinion zooming degree unit, the public opinion zooming degree unit calculates respective weights by applying an entropy method through historical data, calculates an overall public opinion zooming degree according to the weights and the calculation, and quantitatively reflects the comprehensive situation of the focusing degree and the evolution relation of the social network public opinion topics.
9. The computing system of degree of focusing and evolutionary relationship of internet public opinion topics as claimed in claim 8, wherein the public opinion varying power unit comprises:
the public opinion power calculating unit reflects the focusing degree of the overall public opinion atmosphere of the social network on the hot topics with the front rank on the overall network public opinion;
and the public opinion performance variation degree calculating unit reflects the correlation degree between the public opinion hot topics.
10. An information data processing terminal, characterized in that the information data processing terminal comprises a memory and a processor, the memory stores a computer program, and the computer program, when executed by the processor, causes the processor to execute the method of calculating the degree of focus and the evolution relation of the internet public opinion topic according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110309223.6A CN113065975B (en) | 2021-03-23 | 2021-03-23 | Method, system and terminal for calculating focusing degree and evolution relation of network public sentiment topics |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110309223.6A CN113065975B (en) | 2021-03-23 | 2021-03-23 | Method, system and terminal for calculating focusing degree and evolution relation of network public sentiment topics |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113065975A true CN113065975A (en) | 2021-07-02 |
| CN113065975B CN113065975B (en) | 2023-02-28 |
Family
ID=76563173
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110309223.6A Active CN113065975B (en) | 2021-03-23 | 2021-03-23 | Method, system and terminal for calculating focusing degree and evolution relation of network public sentiment topics |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113065975B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117093762A (en) * | 2023-07-18 | 2023-11-21 | 南京特尔顿信息科技有限公司 | Public opinion data evaluation analysis system and method |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104598450A (en) * | 2013-10-30 | 2015-05-06 | 北大方正集团有限公司 | Popularity analysis method and system of network public opinion event |
| US20150193482A1 (en) * | 2014-01-07 | 2015-07-09 | 30dB, Inc. | Topic sentiment identification and analysis |
| CN105068991A (en) * | 2015-07-30 | 2015-11-18 | 成都鼎智汇科技有限公司 | Big data based public sentiment discovery method |
| CN111783456A (en) * | 2020-07-14 | 2020-10-16 | 北京伯乐互联科技发展有限公司 | Public opinion analysis method using semantic analysis technology |
-
2021
- 2021-03-23 CN CN202110309223.6A patent/CN113065975B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104598450A (en) * | 2013-10-30 | 2015-05-06 | 北大方正集团有限公司 | Popularity analysis method and system of network public opinion event |
| US20150193482A1 (en) * | 2014-01-07 | 2015-07-09 | 30dB, Inc. | Topic sentiment identification and analysis |
| CN105068991A (en) * | 2015-07-30 | 2015-11-18 | 成都鼎智汇科技有限公司 | Big data based public sentiment discovery method |
| CN111783456A (en) * | 2020-07-14 | 2020-10-16 | 北京伯乐互联科技发展有限公司 | Public opinion analysis method using semantic analysis technology |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117093762A (en) * | 2023-07-18 | 2023-11-21 | 南京特尔顿信息科技有限公司 | Public opinion data evaluation analysis system and method |
| CN117093762B (en) * | 2023-07-18 | 2024-02-13 | 南京特尔顿信息科技有限公司 | Public opinion data evaluation analysis system and method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113065975B (en) | 2023-02-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Chen et al. | Call attention to rumors: Deep attention based recurrent neural networks for early rumor detection | |
| US7685091B2 (en) | System and method for online information analysis | |
| US8538955B2 (en) | Ranking expert responses and finding experts based on rank | |
| CN103177090B (en) | A kind of topic detection method and device based on big data | |
| CN111382361B (en) | Information pushing method, device, storage medium and computer equipment | |
| CN106251174A (en) | Information recommendation method and device | |
| CN103399891A (en) | Method, device and system for automatic recommendation of network content | |
| US11620283B2 (en) | Method and system for analytic based connections among user types in an online platform | |
| Kewsuwun et al. | A sentiment analysis model of agritech startup on Facebook comments using naive Bayes classifier. | |
| CN101211368B (en) | Method for classifying search term, device and search engine system | |
| CN104933475A (en) | Network forwarding behavior prediction method and apparatus | |
| Iqbal et al. | A distance-based methodology for increased extraction of information from the roof matrices in QFD studies | |
| Gong et al. | A new approach of stock price prediction based on logistic regression model | |
| CN113065975B (en) | Method, system and terminal for calculating focusing degree and evolution relation of network public sentiment topics | |
| CN110245816B (en) | Visual evaluation method for user work efficiency based on browser history record | |
| Darena et al. | Machine learning-based analysis of the association between online texts and stock price movements | |
| CN110019763B (en) | Text filtering method, system, equipment and computer readable storage medium | |
| Ravi et al. | Sentiment analysis applied to Educational Sector | |
| WO2020057237A1 (en) | Influence detection method applicable to object of interest, and electronic terminal and storage medium | |
| CN116010696A (en) | News recommendation method, system and medium integrating knowledge graph and long-term interest of user | |
| CN116450924A (en) | Analysis module and method of intelligent environment-friendly platform ecological environment public opinion monitoring system | |
| US11463461B2 (en) | Unequal probability sampling based on a likelihood model score to evaluate prevalence of inappropriate entities | |
| CN112632218A (en) | Network public opinion monitoring method for enterprise crisis public customs | |
| Fong et al. | Text analytics for predicting question acceptance rates | |
| Niu | Sports Training Strategies Based on Data Mining Technology |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |