CN111026868A - Multi-dimensional public opinion crisis prediction method, terminal device and storage medium - Google Patents
Multi-dimensional public opinion crisis prediction method, terminal device and storage medium Download PDFInfo
- Publication number
- CN111026868A CN111026868A CN201911230765.3A CN201911230765A CN111026868A CN 111026868 A CN111026868 A CN 111026868A CN 201911230765 A CN201911230765 A CN 201911230765A CN 111026868 A CN111026868 A CN 111026868A
- Authority
- CN
- China
- Prior art keywords
- text data
- emotion
- heat
- attribute
- attributes
- 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
- 238000000034 method Methods 0.000 title claims abstract description 27
- 230000008451 emotion Effects 0.000 claims abstract description 101
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 9
- 230000002996 emotional effect Effects 0.000 claims description 27
- 238000004364 calculation method Methods 0.000 claims description 23
- 238000004590 computer program Methods 0.000 claims description 16
- 230000006870 function Effects 0.000 claims description 9
- 238000007619 statistical method Methods 0.000 claims description 6
- 238000004458 analytical method Methods 0.000 description 9
- 238000010801 machine learning Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 230000036528 appetite Effects 0.000 description 1
- 235000019789 appetite Nutrition 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000006735 deficit Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000007935 neutral effect Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012552 review Methods 0.000 description 1
- 239000007787 solid Substances 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
- G06F16/30—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
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/01—Social networking
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Computational Linguistics (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Animal Behavior & Ethology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computing Systems (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention relates to a multidimensional public opinion crisis prediction method, terminal equipment and a storage medium, wherein the method comprises the following steps: s1: collecting public sentiment text data within a certain time, and calculating a negative sentiment heat degree total index of each text data according to the attributes of each text data in different dimensions; s2: classifying the text data through a clustering algorithm according to various public opinion crisis events stored in a public opinion crisis knowledge base, and calculating the relevance of each text data and a clustering center thereof; s3: and calculating the crisis degree of each text data according to the relevance of each text data and the clustering center thereof and the negative emotion heat total index of the text data. The invention calculates the negative emotion heat total index through attributes of different dimensions, and clusters the negative emotion heat total index with various historical public opinion crisis events to obtain the crisis degree of each text data, thereby realizing prediction of major negative public opinions and improving the accuracy and timeliness of public opinion prediction.
Description
Technical Field
The invention relates to the field of public opinion analysis, in particular to a multidimensional public opinion crisis prediction method, terminal equipment and a storage medium.
Background
The network public opinion is a opinion and a comment which are transmitted through the Internet and have strong influence and tendency on some problems in real life by the public, is realized mainly through media such as news comments, forum postings, blogs, microblogs and the like, and intensively reflects the network public opinion in a time period.
The conventional emotion analysis algorithm is still high in error rate, a certain error exists in a frequently-used snownnlp algorithm, emotion analysis calculation is executed by a set of manually-formulated rules, and emotion analysis calculation is executed by learning from data by means of a machine learning technology, but the methods have some defects, and due to lack of background knowledge and context connection, the data accuracy is low, the recall rate is low, and emotion analysis indexes cannot be visually embodied in a time sequence. Although some improvements can be made by adding more rules and training in the sample library to improve accuracy and recall, both are often not compatible.
The multidimensional public opinion crisis prediction is sensitive in timeliness, the possibility of public opinion crisis outbreak is increased along with the time, the characteristics in the time dimension are required to be brought into the emotion analysis range, and the low-dimension emotion analysis also causes the multidimensional public opinion crisis prediction to be difficult to form, so that the ideal effect is difficult to achieve.
Disclosure of Invention
In view of the above problems, the present invention is directed to a method, a terminal device, and a storage medium for predicting a multidimensional public opinion crisis.
The specific scheme is as follows:
a multi-dimensional public opinion crisis prediction method comprises the following steps:
s1: collecting public sentiment text data within a certain time, and calculating a negative sentiment heat degree total index of each text data according to the attributes of each text data in different dimensions;
s2: classifying the text data through a clustering algorithm according to various public opinion crisis events stored in a public opinion crisis knowledge base, and calculating the relevance of each text data and a clustering center thereof;
s3: and calculating the crisis degree of each text data according to the relevance of each text data and the clustering center thereof and the negative emotion heat total index of the text data.
Further, the calculation process of the negative emotion heat total index of each text data comprises the following steps:
s11: setting a plurality of emotion attributes, an emotion coefficient corresponding to each emotion attribute, a plurality of heat attributes and a heat coefficient corresponding to each heat attribute of the text data;
s12: calculating a negative emotion value and a popularity value of the text data according to the following formulas;
Ai＝f(si,ri)
Bj＝h(1-ej,qj)
wherein A isiExpressing the heat value of the ith heat attribute, f expressing the heat value calculation function, siDenotes the ith Heat Attribute, riRepresents the heat coefficient corresponding to the ith heat attribute, BjNegative emotion value representing jth emotion attribute, h represents negative emotion value calculation function, ejDenotes the jth emotional Attribute, qjRepresenting the emotion coefficient corresponding to the jth emotion attribute;
s13: calculating the negative emotion heat index W of the text data according to the following formula:
W＝A+B
wherein n represents the total number of the heat attributes, i represents the serial number of the heat attributes, m represents the total number of the emotion attributes, and j represents the serial number of the emotion attributes;
s14: calculating the attribute weight P of the text data according to the emotion attribute and the heat attribute hit by the text data:
wherein, p and k respectively represent the sequence numbers of the hit emotion attributes and the hit heat attributes, and N and M respectively represent the total numbers of the hit emotion attributes and the hit heat attributes;
s15: and adding the negative emotion popularity index W of the text data and the attribute weight P to obtain a negative emotion popularity total index WP of the text data.
Further, the emotional attributes include: a polar emotional attribute; a theme emotion attribute; opinion holder emotional attributes; view emotion attributes; a type sentiment attribute; a level sentiment attribute; fine-grained emotional attributes; learning the emotional attribute of the matching result by a sample machine; matching the result emotion attributes with the emotion dictionary; and matching the emotion knowledge map with the result emotion attributes.
Further, the heat attribute includes: the attribute of the popularity of the website; a content classification heat attribute; a content-related geothermal attribute; number of hot attributes of postings, forwarding, and likes; a single keyword popularity attribute; the keywords are combined with the heat attribute.
Further, step S1 further includes: and carrying out sentiment value calculation on each text data, judging whether the text data meets the requirements or not by a statistical method, and if not, rejecting the text data.
Further, the statistical method includes dividing the text data into a plurality of sub-texts, calculating the emotion value of each sub-text, calculating the average number and the median number of the emotion values of all the sub-texts, judging whether the difference value between the average number and the median number is larger than a difference threshold value, and if so, judging that the text data do not meet the requirement.
A multidimensional public opinion crisis prediction terminal device comprises a processor, a memory 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 steps of the method of the embodiment of the invention.
A computer-readable storage medium, in which a computer program is stored, which, when being executed by a processor, carries out the steps of the method according to an embodiment of the invention as described above.
According to the technical scheme, the negative emotion heat total index is calculated through attributes of different dimensions and is clustered with various historical public opinion crisis events to obtain the crisis degree of each text data, prediction of major negative public opinions is achieved, accuracy and timeliness of public opinion prediction can be greatly improved, meanwhile, recall rate of data can be guaranteed, and data loss caused by data condition filtering is avoided.
Drawings
Fig. 1 is a schematic flow chart according to a first embodiment of the present invention.
Detailed Description
To further illustrate the various embodiments, the invention provides the accompanying drawings. The accompanying drawings, which are incorporated in and constitute a part of this disclosure, illustrate embodiments of the invention and, together with the description, serve to explain the principles of the embodiments. Those skilled in the art will appreciate still other possible embodiments and advantages of the present invention with reference to these figures.
The invention will now be further described with reference to the accompanying drawings and detailed description.
The first embodiment is as follows:
referring to fig. 1, the invention provides a multidimensional public opinion crisis prediction method, which includes the following steps:
s1: public sentiment text data in a certain time are collected, and the negative emotion heat total index of each text data is calculated according to the attributes of each text data in different dimensions.
In this embodiment, the text data is obtained by formatting comment/article/post information on a network collected by a tool such as an internet crawler.
The calculation process of the negative emotion heat total index of each text data comprises the following steps:
s11: a plurality of emotion attributes, emotion coefficients corresponding to the emotion attributes, a plurality of heat attributes and heat coefficients corresponding to the heat attributes of the text data are set.
In this example, the following settings were made
(1) The emotional attributes specifically include:
e 1: polar emotional attributes, such as speakers expressing positive or negative opinions;
e 2: topic sentiment attributes, such as the thing in question;
e 3: opinion holders emotional attributes, such as individuals or entities expressing opinions;
e 4: opinion emotional attributes, such as subjective (opinion) or objective (fact);
e 5: type sentiment attributes such as substantivity and comparability, deficits and implications;
e 6: and the level emotional attributes such as the main note, the comment and the like are forwarded and correspond to different levels, and in addition, the expression in the comment is counted and is included in the calculation.
e 7: fine-grained emotional attributes: very positive, neutral, negative, very negative (5-star rating).
e 8: and learning the emotional attribute of the matching result by a sample machine.
e 9: the emotion dictionary matches the resultant emotion attributes.
e 10: and matching the emotion knowledge map with the result emotion attributes.
(2) The heat attribute specifically includes:
s 1: and the popularity attribute of the website where the article is located. The corresponding heat attributes of different websites are different.
s 2: the article content is classified into a heat attribute. Articles of different content subject types have different corresponding popularity attributes.
s 3: the article content relates to the local heat attribute. The time of occurrence in different places corresponds to different heat attributes, for example, the heat attribute of an event occurring in a first-line city is greater than that of a third-line city.
s 4: the article follow-up, forwarding and endorsement quantity heat attributes. Differences in the number of posts, forwards, praise indicate differences in the number of people concerned.
The specific value corresponding to each of the four heat attributes may be set by a person skilled in the art according to experience and historical data.
In addition to the above four heat attributes, the embodiment further includes two heat attributes related to the keyword, which are respectively:
s 5: single keyword popularity attribute
s 6: keyword combination heat attribute
The two heat attributes need to judge whether the article contains a single keyword or a plurality of keywords corresponding to the industry or the scene to which the article belongs in the heat keyword dictionary, and then in the calculation of the heat, if the article only contains a single keyword, the calculation is carried out according to the heat attribute of the single keyword corresponding to the single keyword, and if the article contains a keyword combination, the calculation is carried out according to the heat attribute of the single keyword corresponding to each keyword in the keyword combination, and the calculation is carried out according to the heat attribute of the keyword combination.
The hot keyword dictionary needs to be constructed in advance and updated and maintained frequently, and the contents in the hot keyword dictionary are increased, decreased or adjusted properly.
The emotion attribute and the heat attribute are all implemented, and in other embodiments, a person skilled in the art may increase, decrease, and modify the emotion attribute and the heat attribute according to an actual situation, which is not limited herein.
Since different emotional attributes and different heat attributes have different degrees of influence on data emotional tendency and heat influence, it is necessary to set an emotional coefficient q for each of the emotional attributes and the heat attributesjAnd coefficient of heat riIn the embodiment, the value ranges of the emotion coefficient q and the heat coefficient r are set to be 0-10, and in specific application, the fieldThe skilled person can make adjustments based on empirical data and actual conditions.
S12: calculating a negative emotion value and a popularity value of the text data according to the following formulas;
Ai＝f(si,ri)
Bj＝h(1-ej,qj)
wherein A isiExpressing the heat value of the ith heat attribute, f expressing the heat value calculation function, siDenotes the ith Heat Attribute, riRepresents the heat coefficient corresponding to the ith heat attribute, BjNegative emotion value representing jth emotion attribute, h represents negative emotion value calculation function, ejDenotes the jth emotional Attribute, qjAnd expressing the emotion coefficient corresponding to the j-th emotion attribute.
S13: calculating the negative emotion heat index W of the text data according to the following formula:
W＝A+B
where n represents the total number of heat attributes, i represents the number of heat attributes, m represents the total number of emotion attributes, and j represents the number of emotion attributes.
S14: calculating the attribute weight P of the text data according to the emotion attribute and the heat attribute hit by the text data:
wherein p and k respectively represent the sequence numbers of the hit emotion attributes and the hit heat attributes, and N and M respectively represent the total numbers of the hit emotion attributes and the hit heat attributes.
E.g. matching articles to key sites s1Combinations of keywords s6Artificially judging the feedback feeling fine particlesDegree e7Sample machine learning results e8Emotion dictionary e9Emotional knowledge map e10At this time, the weighting calculation is performed, and the calculation formula of the weighting value P is:
P＝k(s1r1)+k(s6r6)+m(1-e7q7)+m(1-e8q8)+m(1-e9q9)+m(1-e10q10)
s15: adding the negative emotion popularity index W of the text data and the attribute weight P to obtain a negative emotion popularity total index WP of the text data, namely:
WP＝W+P
further, in order to eliminate the text data that does not meet the requirement, the embodiment further includes: and carrying out sentiment value calculation on each text data, judging whether the text data meets the requirements or not by a statistical method, and if not, rejecting the text data.
The emotional value calculation can adopt the existing emotional value calculation algorithm, such as SnowNLP.
The statistical method can be used for obtaining the overall trend of the emotion value of each text data according to the average number and the median number so as to judge whether the text data meets the requirement.
For example, an article contains 5 comments, the specific content is shown in table 1, after the emotion value of each comment is calculated through a SnowNLP algorithm, the average number and the median of all emotion values are calculated, if the difference value between the average number and the median is greater than a threshold value, it is indicated that the article contains malicious comments or comments which do not accord with the emotion of the article, and the article is judged to be not accord with the requirement.
If the text data contains 5 comments,
TABLE 1
| Serial number | Comments | Date | Emotional value |
| 1 | The chafing dish which is most popular to the children needs to be eaten once a week. | 2019-05-14 | 0.833198 |
| 2 | The Nth time comes, or the Nth time likes. | 2019-04-25 | 0.833289 |
| 3 | Aunt country birthday, sister, who adds the bunk of restaurant A. | 2019-05-01 | 1.000000 |
| 4 | The serving store of restaurant a is the same. | 2019-05-10 | 0.756952 |
| 5 | Poor appetite and poor comment. | 2019-06-0.3 | 0.005536 |
The average of the 5 reviews was 0.61114, with a median of 0.95662. The difference between the two is 0.34548 which is larger than the set threshold value of 0.3.
S2: classifying the text data through a clustering algorithm according to various public opinion crisis events stored in a public opinion crisis knowledge base, and calculating the relevance of each text data and the clustering center thereof.
The public opinion crisis knowledge base stores various classified high-crisis events, the type of each text data can be obtained through a clustering algorithm, and the possible degree of each text data belonging to the public opinion crisis event can be obtained through the correlation degree with a clustering center.
S3: and calculating the crisis degree R of each text data according to the relevance of each text data and the clustering center thereof and the negative emotion heat total index of the text data. Specifically, it can be calculated by the following formula:
R＝Z(S,WP)
wherein S represents a degree of correlation, and Z represents a crisis degree calculation function.
When the calculated crisis degree R of the text data is higher than the crisis threshold, corresponding early warning processing can be carried out.
According to the embodiment of the invention, the negative emotion heat total index is calculated through attributes of different dimensions, and is clustered with various historical public opinion crisis events to obtain the crisis degree of each text data, so that the prediction of major negative public opinions is realized, the accuracy and timeliness of public opinion prediction can be greatly improved, the recall rate of data can be ensured, and data loss caused by data condition filtering can be avoided.
According to the embodiment of the invention, through multi-dimensional emotion analysis, emotion popularity analysis related technologies such as rules, expression libraries, word cloud libraries, machine learning, emotion dictionaries, emotion knowledge maps combined with contexts and the like are matched with user manual judgment feedback, and finally, related event collision is combined, so that public opinion crisis prediction is realized, and probability is increased according to increasing of negative emotion popularity indexes of related events.
Example two:
the invention also provides a multidimensional public opinion crisis prediction terminal device, which 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 steps of the method embodiment of the first embodiment of the invention.
Further, as an executable scheme, the multidimensional public opinion crisis prediction terminal device may be a computing device such as a desktop computer, a notebook, a palm computer, and a cloud server. The multidimensional public opinion crisis prediction terminal equipment can comprise, but is not limited to, a processor and a memory. Those skilled in the art will understand that the above-mentioned structure of the multidimensional public opinion crisis prediction terminal device is only an example of the multidimensional public opinion crisis prediction terminal device, and does not constitute a limitation on the multidimensional public opinion crisis prediction terminal device, and may include more or less components than the above, or combine some components, or different components, for example, the multidimensional public opinion crisis prediction terminal device may further include an input/output device, a network access device, a bus, and the like, which is not limited in the embodiment of the present invention.
Further, as an executable solution, the processor may be a Central Processing Unit (CPU), other general purpose processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, a discrete Gate or transistor logic device, a discrete hardware component, and the like. The general processor can be a microprocessor or the processor can be any conventional processor and the like, the processor is a control center of the multidimensional public opinion crisis prediction terminal equipment, and various interfaces and lines are utilized to connect all parts of the whole multidimensional public opinion crisis prediction terminal equipment.
The memory can be used for storing the computer program and/or the module, and the processor can realize various functions of the multidimensional public opinion crisis prediction terminal equipment by running or executing the computer program and/or the module stored in the memory and calling data stored in the memory. The memory can mainly comprise a program storage area and a data storage area, wherein the program storage area can store an operating system and an application program required by at least one function; the storage data area may store data created during the execution of the program, and the like. In addition, the memory may include high speed random access memory, and may also include non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), at least one magnetic disk storage device, a Flash memory device, or other volatile solid state storage device.
The invention also provides a computer-readable storage medium, in which a computer program is stored, which, when being executed by a processor, carries out the steps of the above-mentioned method of an embodiment of the invention.
The multidimensional public opinion crisis prediction terminal device integrated module/unit can be stored in a computer readable storage medium if the module/unit is realized in the form of a software functional unit and sold or used as an independent product. Based on such understanding, all or part of the flow of the method according to the embodiments of the present invention may also be implemented by a computer program, which may be stored in a computer-readable storage medium, and when the computer program is executed by a processor, the steps of the method embodiments may be implemented. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, usb disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-only Memory (ROM ), Random Access Memory (RAM), software distribution medium, and the like.
While the invention has been particularly shown and described with reference to a preferred embodiment, it will be understood by those skilled in the art that various changes in form and detail may be made therein without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (8)
1. A multidimensional public opinion crisis prediction method is characterized in that: the method comprises the following steps:
s1: collecting public sentiment text data within a certain time, and calculating a negative sentiment heat degree total index of each text data according to the attributes of each text data in different dimensions;
s2: classifying the text data through a clustering algorithm according to various public opinion crisis events stored in a public opinion crisis knowledge base, and calculating the relevance of each text data and a clustering center thereof;
s3: and calculating the crisis degree of each text data according to the relevance of each text data and the clustering center thereof and the negative emotion heat total index of the text data.
2. The multi-dimensional public opinion crisis prediction method according to claim 1, characterized in that: the calculation process of the negative emotion heat total index of each text data comprises the following steps:
s11: setting a plurality of emotion attributes, an emotion coefficient corresponding to each emotion attribute, a plurality of heat attributes and a heat coefficient corresponding to each heat attribute of the text data;
s12: calculating a negative emotion value and a popularity value of the text data according to the following formulas;
Ai＝f(si,ri)
Bj＝h(1-ej,qj)
wherein A isiExpressing the heat value of the ith heat attribute, f expressing the heat value calculation function, siDenotes the ith Heat Attribute, riRepresents the heat coefficient corresponding to the ith heat attribute, BjNegative emotion value representing jth emotion attribute, h represents negative emotion value calculation function, ejDenotes the jth emotional Attribute, qjRepresenting the emotion coefficient corresponding to the jth emotion attribute;
s13: calculating the negative emotion heat index W of the text data according to the following formula:
W＝A+B
wherein n represents the total number of the heat attributes, i represents the serial number of the heat attributes, m represents the total number of the emotion attributes, and j represents the serial number of the emotion attributes;
s14: calculating the attribute weight P of the text data according to the emotion attribute and the heat attribute hit by the text data:
wherein, p and k respectively represent the sequence numbers of the hit emotion attributes and the hit heat attributes, and N and M respectively represent the total numbers of the hit emotion attributes and the hit heat attributes;
s15: and adding the negative emotion popularity index W of the text data and the attribute weight P to obtain a negative emotion popularity total index WP of the text data.
3. The multi-dimensional public opinion crisis prediction method according to claim 2, characterized in that: the emotional attributes include: a polar emotional attribute; a theme emotion attribute; opinion holder emotional attributes; view emotion attributes; a type sentiment attribute; a level sentiment attribute; fine-grained emotional attributes; learning the emotional attribute of the matching result by a sample machine; matching the result emotion attributes with the emotion dictionary; and matching the emotion knowledge map with the result emotion attributes.
4. The multi-dimensional public opinion crisis prediction method according to claim 2, characterized in that: the heat attributes include: the attribute of the popularity of the website; a content classification heat attribute; a content-related geothermal attribute; number of hot attributes of postings, forwarding, and likes; a single keyword popularity attribute; the keywords are combined with the heat attribute.
5. The multi-dimensional public opinion crisis prediction method according to claim 1, characterized in that: step S1 further includes: and carrying out sentiment value calculation on each text data, judging whether the text data meets the requirements or not by a statistical method, and if not, rejecting the text data.
6. The multi-dimensional public opinion crisis prediction method according to claim 5, characterized in that: the statistical method comprises the steps of dividing text data into a plurality of sub-texts, calculating the emotion value of each sub-text, calculating the average number and the median of the emotion values of all the sub-texts, judging whether the difference value between the average number and the median is larger than a difference threshold value, and if so, judging that the text data do not meet the requirement.
7. The utility model provides a multidimensional public opinion crisis prediction terminal equipment which characterized in that: comprising a processor, a memory and a computer program stored in the memory and running on the processor, the processor implementing the steps of the method according to any one of claims 1 to 6 when executing the computer program.
8. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911230765.3A CN111026868B (en) | 2019-12-05 | 2019-12-05 | Multi-dimensional public opinion crisis prediction method, terminal device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911230765.3A CN111026868B (en) | 2019-12-05 | 2019-12-05 | Multi-dimensional public opinion crisis prediction method, terminal device and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111026868A true CN111026868A (en) | 2020-04-17 |
| CN111026868B CN111026868B (en) | 2022-07-15 |
Family
ID=70204263
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911230765.3A Active CN111026868B (en) | 2019-12-05 | 2019-12-05 | Multi-dimensional public opinion crisis prediction method, terminal device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111026868B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113157871A (en) * | 2021-05-27 | 2021-07-23 | 东莞心启航联贸网络科技有限公司 | News public opinion text processing method, server and medium applying artificial intelligence |
| 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 |
| CN113779258A (en) * | 2021-11-10 | 2021-12-10 | 上海蜜度信息技术有限公司 | Method for analyzing public satisfaction, storage medium and electronic device |
| CN117494897A (en) * | 2023-11-14 | 2024-02-02 | 西安康奈网络科技有限公司 | Single public opinion event development tendency judging method |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070294230A1 (en) * | 2006-05-31 | 2007-12-20 | Joshua Sinel | Dynamic content analysis of collected online discussions |
| CN104408157A (en) * | 2014-12-05 | 2015-03-11 | 四川诚品电子商务有限公司 | Funnel type data gathering, analyzing and pushing system and method for online public opinion |
| CN109145215A (en) * | 2018-08-29 | 2019-01-04 | 中国平安保险(集团)股份有限公司 | Internet public opinion analysis method, apparatus and storage medium |
| CN109684481A (en) * | 2019-01-04 | 2019-04-26 | 深圳壹账通智能科技有限公司 | The analysis of public opinion method, apparatus, computer equipment and storage medium |
| CN109783815A (en) * | 2018-12-28 | 2019-05-21 | 华南理工大学 | A kind of various dimensions network public-opinion big data comparative analysis method |
| CN110096652A (en) * | 2019-05-06 | 2019-08-06 | 上海汽车集团股份有限公司 | Public sentiment wind vane index calculation method and device, readable storage medium storing program for executing |
-
2019
- 2019-12-05 CN CN201911230765.3A patent/CN111026868B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070294230A1 (en) * | 2006-05-31 | 2007-12-20 | Joshua Sinel | Dynamic content analysis of collected online discussions |
| CN104408157A (en) * | 2014-12-05 | 2015-03-11 | 四川诚品电子商务有限公司 | Funnel type data gathering, analyzing and pushing system and method for online public opinion |
| CN109145215A (en) * | 2018-08-29 | 2019-01-04 | 中国平安保险(集团)股份有限公司 | Internet public opinion analysis method, apparatus and storage medium |
| CN109783815A (en) * | 2018-12-28 | 2019-05-21 | 华南理工大学 | A kind of various dimensions network public-opinion big data comparative analysis method |
| CN109684481A (en) * | 2019-01-04 | 2019-04-26 | 深圳壹账通智能科技有限公司 | The analysis of public opinion method, apparatus, computer equipment and storage medium |
| CN110096652A (en) * | 2019-05-06 | 2019-08-06 | 上海汽车集团股份有限公司 | Public sentiment wind vane index calculation method and device, readable storage medium storing program for executing |
Non-Patent Citations (1)
| Title |
|---|
| 孙培星: "基于情感倾向性的网络舆情分析及演化预测研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113157871A (en) * | 2021-05-27 | 2021-07-23 | 东莞心启航联贸网络科技有限公司 | News public opinion text processing method, server and medium applying artificial intelligence |
| CN113157871B (en) * | 2021-05-27 | 2021-12-21 | 宿迁硅基智能科技有限公司 | News public opinion text processing method, server and medium applying artificial intelligence |
| 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 |
| CN113779258A (en) * | 2021-11-10 | 2021-12-10 | 上海蜜度信息技术有限公司 | Method for analyzing public satisfaction, storage medium and electronic device |
| CN113779258B (en) * | 2021-11-10 | 2022-03-11 | 上海蜜度信息技术有限公司 | Method for analyzing public satisfaction, storage medium and electronic device |
| CN117494897A (en) * | 2023-11-14 | 2024-02-02 | 西安康奈网络科技有限公司 | Single public opinion event development tendency judging method |
| CN117494897B (en) * | 2023-11-14 | 2024-05-17 | 西安康奈网络科技有限公司 | Single public opinion event development tendency judging method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111026868B (en) | 2022-07-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111026868B (en) | Multi-dimensional public opinion crisis prediction method, terminal device and storage medium | |
| CN106980692B (en) | Influence calculation method based on microblog specific events | |
| Sharif et al. | Sentiment analysis of Bengali texts on online restaurant reviews using multinomial Naïve Bayes | |
| US10394830B1 (en) | Sentiment detection as a ranking signal for reviewable entities | |
| US8671040B2 (en) | Credit risk mining | |
| CN110297988B (en) | Hot topic detection method based on weighted LDA and improved Single-Pass clustering algorithm | |
| CN105183833B (en) | Microblog text recommendation method and device based on user model | |
| US7949643B2 (en) | Method and apparatus for rating user generated content in search results | |
| US9201880B2 (en) | Processing a content item with regard to an event and a location | |
| CN103870973B (en) | Information push, searching method and the device of keyword extraction based on electronic information | |
| US20210056571A1 (en) | Determining of summary of user-generated content and recommendation of user-generated content | |
| WO2017024884A1 (en) | Search intention identification method and device | |
| Shi et al. | Learning-to-rank for real-time high-precision hashtag recommendation for streaming news | |
| WO2018157625A1 (en) | Reinforcement learning-based method for learning to rank and server | |
| CN112348629A (en) | Commodity information pushing method and device | |
| US20150317390A1 (en) | Computer-implemented systems and methods for taxonomy development | |
| US20230237055A1 (en) | Method and system for analytic based connections among user types in an online platform | |
| CN107943910B (en) | Personalized book recommendation method based on combined algorithm | |
| CN110825868A (en) | Topic popularity based text pushing method, terminal device and storage medium | |
| WO2019041528A1 (en) | Method, electronic apparatus, and computer readable storage medium for determining polarity of news sentiment | |
| KR101326313B1 (en) | Method of classifying emotion from multi sentence using context information | |
| CN109344232B (en) | Public opinion information retrieval method and terminal equipment | |
| US20140272842A1 (en) | Assessing cognitive ability | |
| CN111737607B (en) | Data processing method, device, electronic equipment and storage medium | |
| WO2020057237A1 (en) | Influence detection method applicable to object of interest, and electronic terminal and storage medium |
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 |