A candidate network support degree calculation method based on propaganda strength statistics

Abstract

The application provides a candidate network support degree calculation method based on propaganda strength statistics, comprising the following steps: through dynamic statistical analysis on the propaganda strength of high-influence propagandists with the same stand tendency as the candidate, a candidate network support degree calculation model is constructed, so that dynamic analysis and calculation of the candidate network support degree are realized. When the candidate network support degree is calculated, the calculation method is novel and flexible in perspective, is innovative, and ensures the accuracy of the calculation result.

Description

Technical Field

[0001] The present invention relates to the technical field of candidate network support calculation, and in particular to a candidate network support calculation method based on publicity intensity statistics. Background Art

[0002] In the middle and late stages of the candidacy, the race becomes increasingly tense. Various sources not only intensify their promotional efforts but also begin to exploit the other candidate's weaknesses and negative information in their critical coverage. Online reports and comments about the candidates range from supportive to opposing, and the candidates' online presence is mixed. Online presence isn't always the same as online support, making it difficult to accurately assess a candidate's online support based solely on their online presence, and thus, to accurately predict the outcome. Summary of the Invention

[0003] The present invention aims to provide a method for calculating candidate network support based on publicity intensity statistics, so as to solve the above-mentioned problem that it is difficult to reasonably judge the candidate's network support simply by relying on the candidate's network voice, and thus it is difficult to accurately predict the candidate results.

[0004] The present invention provides a method for calculating candidate network support based on publicity intensity statistics, comprising:

[0005] By conducting dynamic statistical analysis on the propaganda efforts of highly influential propagandists who have the same stance as the candidates, a candidate network support calculation model is constructed, thereby realizing dynamic analysis and calculation of candidate network support.

[0006] Furthermore, the method for calculating candidate network support based on publicity intensity statistics includes the following steps:

[0007] S10, define candidates, categorize their positions and tendencies, and sort out the propagandists for each type of position and tendencies;

[0008] S20, collecting public statements of promoters and identifying the promoters’ reports on the candidates and the promoters’ reports on the candidates;

[0009] S30, inputting the promoter's reports on the candidate and the promoter's reports on the candidate into the candidate network support calculation model, and the candidate network support calculation model completes the calculation of the candidate network support and outputs the candidate network support.

[0010] Furthermore, step S10 includes the following sub-steps:

[0011] S11, define candidates:

[0012] Candidates refer to those who have registered and passed the qualification review. For a certain region, there are m candidates, defined as candidate a, candidate b, ..., candidate m.

[0013] S12, breakdown of candidates’ positions and tendencies:

[0014] Classify the candidate's position tendencies, including position tendencies A, position tendencies B, ..., position tendencies X;

[0015] S13, Promoter’s summary:

[0016] We manually sorted out the propagandists of various types and tendencies, including:

[0017] The propagandists under the stance A include propagandist A1, propagandist A2, …, propagandist An;

[0018] The propagandists under the stance B include propagandist B1, propagandist B2, …, propagandist Bn;

[0019] …

[0020] The propagandists with stance X include propagandist X1, propagandist X2, ..., propagandist Xn.

[0021] Furthermore, step S20 includes the following sub-steps:

[0022] S21, data collection on the public statements of propagandists;

[0023] S22, using topic recognition technology to automatically identify and extract the public statements of the propagandists regarding the candidate from the public statements collected, and form a first data set; the first data set includes the propagandists' reports on the candidate;

[0024] S23, using character recognition technology, automatically identifies and extracts reports about candidates who share the same stance as the propagandist in the propagandist's statements about the candidate, and forms a second dataset; the second dataset includes the propagandist's reports about the candidate.

[0025] Furthermore, in step S21, data collection is performed on the public statements of the promoter according to the set update frequency.

[0026] Furthermore, step S30 includes the following sub-steps:

[0027] S31, assigning coverage weights to promoters;

[0028] S32, constructing a calculation model of the propagandist's propaganda efforts on the candidate based on the reporting situation;

[0029] S33, a candidate network support degree calculation model is constructed based on the propagator weight and a propagator publicity strength calculation model of the candidate;

[0030] S34, the propagator report on the candidate and the propagator report on the candidate are input into the candidate network support degree calculation model, the calculation of the candidate network support degree is completed by the candidate network support degree calculation model, and the candidate network support degree is output.

[0031] Further, the method for assigning the propagator report weight in step S31 is:

[0032] The report weight of the propagator is denoted as W, and the report weight of each propagator is manually assigned, wherein the sum of the report weights of the propagators under a certain stand tendency is 1.

[0033] Further, in step S32, a propagator An and a candidate a are recorded, and the constructed propagator publicity strength calculation model of the candidate is represented as:

[0034]

[0035] Among them, represents the publicity strength of the propagator An to the candidate a under the stand tendency A, i is the number of public opinion reports of the propagator An on the candidate, which is obtained by statistical analysis on the report of the propagator on the candidate; - is the number of public opinion reports of the propagator An to the candidate a, which is obtained by statistical analysis on the report of the propagator on the candidate.

[0036] Further, in step S33, the constructed candidate network support degree calculation model is represented as:

[0037]

[0038] Among them, represents the network support degree of the candidate a under the stand tendency A; , , …, The report weights of the propagator A1, the propagator A2, …, and the propagator An are represented respectively. , , …, The publicity strengths of the propagator A1, the propagator A2, …, and the propagator An to the candidate a are represented respectively.

[0039] As described above, due to the adoption of the above technical scheme, the beneficial effects of the present application are:

[0040] When calculating the candidate network support, the present invention not only has a novel and clever calculation method perspective and is innovative, but also ensures the accuracy of the calculation results. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings in the embodiments will be briefly introduced below. It should be understood that the following drawings only illustrate certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without paying any creative work.

[0042] Figure 1 Flowchart of a method for calculating candidate network support based on publicity intensity statistics in an embodiment of the present invention.

[0043] Figure 2 Schematic diagram of manual sorting of candidates and promoters in an embodiment of the present invention. DETAILED DESCRIPTION

[0044] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions of the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings herein can be arranged and designed in various different configurations.

[0045] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention as claimed, but rather merely represents selected embodiments of the present invention. All other embodiments derived by persons of ordinary skill in the art based on the embodiments of the present invention without creative effort are intended to fall within the scope of protection of the present invention.

[0046] Example

[0047] like Figure 1 As shown, this embodiment proposes a method for calculating candidate network support based on publicity intensity statistics, including:

[0048] By conducting dynamic statistical analysis on the propaganda efforts of highly influential propagandists who have the same stance as the candidates, a candidate network support calculation model is constructed, thereby realizing dynamic analysis and calculation of candidate network support.

[0049] In this embodiment, the method for calculating candidate network support based on publicity statistics includes the following steps:

[0050] S10, define the candidate, classify the candidate's stance tendency, and sort out the propagandists under each type of stance tendency; for example, Figure 2 Specifically,

[0051] S11, define the candidate:

[0052] The candidate refers to the person who participates in the candidate registration and passes the qualification examination; for a certain area, there are m candidates, respectively defined as candidate a, candidate b, …, candidate m;

[0053] S12, subdivide the candidate's stance tendency:

[0054] Classify the candidate's stance tendency, and the specific categories of stance tendency include stance tendency A, stance tendency B, …, stance tendency X;

[0055] S13, propagandist sorting:

[0056] Artificially sort out the propagandists under each type of stance tendency, including:

[0057] The propagandists under stance tendency A include propagandist A1, propagandist A2, …, propagandist An;

[0058] The propagandists under stance tendency B include propagandist B1, propagandist B2, …, propagandist Bn;

[0059] …

[0060] The propagandists under stance tendency X include propagandist X1, propagandist X2, …, propagandist Xn.

[0061] S20, collect the public statements of the propagandists, and identify the propagandist's reporting on the candidate and the propagandist's reporting on the candidate; specifically:

[0062] S21, collect data from the propagandist's public statements (which can be updated according to the set frequency);

[0063] S22, in the collected propagandist's public statements, use topic recognition technology to automatically identify and extract the candidate's statements in the propagandist's public statements, and form a data set one; the data set one contains the propagandist's reporting on the candidate; for example, the public statement set of propagandist A1 about the candidate under stance tendency A is {A11, A12, …, A1 i}, where A1 i is the i-th public statement of propagandist A1 about the candidate.

[0064] S23, using character recognition technology, automatically identifies and extracts reports on candidates with the same stance as the propagandist from the propagandist's statements about the candidate, and forms a second dataset; the second dataset contains the propagandist's reports on the candidate. For example, for candidate a, propagandist A1 has the same stance as candidate a. From the public statements of propagandist A1 about the candidate {A11, A12, ..., A1 i}, extract the public statements involving candidate a to form a data set ,in, is the jth public statement made by promoter A1 about candidate a.

[0065] S30: Input the promoter's reports on the candidate and the promoter's reports on the candidate into the candidate network support calculation model, and the candidate network support calculation model calculates the candidate network support and outputs the candidate network support. Specifically:

[0066] S31, assigning reporting weights to propagandists. Different propagandists have different influences on the Internet. Therefore, the reporting weight of the propagandist is recorded as W, and the reporting weight of each propagandist is manually assigned. The sum of the reporting weights of propagandists with a certain stance is 1. For example, propagandists A1, A2, ..., and An with stance A have reporting weights of W and W, respectively. A1 、W A2 ,…,W An , and W A1 +W A2 +…+W An =1.

[0067] S32, based on the reporting situation, construct a calculation model for the promoter's promotional efforts on the candidate. Specifically, let there be a promoter An and a candidate a, then the constructed calculation model for the promoter's promotional efforts on the candidate is expressed as:

[0068]

[0069] in, represents the intensity of the propaganda of the propagandist An for candidate a under the position tendency A; i is the number of public reports on the candidate by the propagandist An, obtained by statistical analysis of the propagandist's reports on the candidate; is the number of reports on the public statements of the promoter An on candidate a, obtained by statistical analysis of the promoter's reports on the candidate.

[0070] For example:

[0071] (1) The intensity of the promotion by promoter A1 for candidate a:

[0072]

[0073] Here, i is the number of public opinion reports about the candidate by propagator A1, is the number of public opinion reports about candidate a by propagator A1.

[0074] (2) Propagator A2's propaganda strength for candidate a:

[0075]

[0076] Here, i is the number of public opinion reports about the candidate by propagator A2, is the number of public opinion reports about candidate a by propagator A2.

[0077] (3) Propagator A1's propaganda strength for candidate b:

[0078]

[0079] Here, i is the number of public opinion reports about the candidate by propagator A1, is the number of public opinion reports about candidate b by propagator A1. (Note: Candidate b and propagator A1 have the same stance tendency).

[0080] S33, based on the propagator weight and the propagator's propaganda strength calculation model for the candidate, a candidate network support calculation model is constructed; for example, for candidate a, the constructed candidate network support calculation model is represented as:

[0081]

[0082] wherein, represents the network support of candidate a under stance tendency A; , , …, respectively represent the reporting weight of propagator A1, propagator A2, …, propagator An; , , …, respectively represent the propaganda strength of propagator A1, propagator A2, …, propagator An for candidate a.

[0083] S34, input the propagator's reporting situation about the candidate and the propagator's reporting situation about the candidate into the candidate network support calculation model, and calculate the candidate network support by the candidate network support calculation model, and output the candidate network support. At this point, by collecting and dynamically analyzing the propagator's reporting situation about the candidate and the propagator's reporting situation about the candidate, the candidate network support can be quickly calculated.

[0084] With regard to the above-mentioned method for calculating candidate network support based on publicity intensity statistics, the beneficial effects and advantages of the present invention are that, firstly, the perspective on the candidate network support calculation method is novel, smart, and innovative. It does not require huge and complex data and algorithm computing power support. On the basis of open source data, it adopts thematic analysis, character recognition and other technologies to realize statistical analysis of the number of relevant public reports on the propagandists, calculates the publicity intensity on this basis, and then derives the candidate network support based on the publicity intensity factor. Secondly, the accuracy of the network support calculation method is relatively high. Through comparative analysis with the candidate results in multiple regions in the past five years, the accuracy of the above-mentioned candidate network support calculation method based on publicity intensity statistics is above 85%.

[0085] In summary, when calculating the candidate network support, the present invention not only has a novel and clever calculation method with innovative perspectives, but also ensures the accuracy of the calculation results.

[0086] The foregoing description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Those skilled in the art will readily appreciate that various modifications and variations of the present invention are possible. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present invention are intended to be within the scope of protection of the present invention.

Claims

1. A method for calculating candidate network support based on publicity statistics, characterized in that: include: By dynamically analyzing the propaganda efforts of influential propagandists who share the candidate's stance and inclination, a candidate network support calculation model is constructed to dynamically analyze and calculate the candidate's network support. The specific steps include the following: S10, define candidates, categorize their positions and tendencies, and sort out the propagandists for each type of position and tendencies; S20, collecting public statements of promoters and identifying the promoters’ reports on the candidates and the promoters’ reports on the candidates; S30, inputting the promoter's reports on the candidate and the promoter's reports on the candidate into the candidate network support calculation model, and the candidate network support calculation model calculates the candidate network support and outputs the candidate network support; Step S20 includes the following sub-steps: S21, data collection on the public statements of propagandists; S22, using topic recognition technology to automatically identify and extract the public statements of the propagandists regarding the candidate from the collected public statements, and form a first dataset; the first dataset is the propagandists' reports on the candidate, and the reports include the set of public statements of the propagandists regarding the candidate from various standpoints; S23, using character recognition technology, automatically identify and extract reports on candidates with the same stance as the propagandist from the propagandist's reports on the candidates, and form a second dataset; the second dataset includes the propagandist's reports on the candidates.

2. The method for calculating candidate network support based on publicity statistics according to claim 1 is characterized in that: Step S10 includes the following sub-steps: S11, define candidates: Candidates refer to those who have registered and passed the qualification review. For a certain region, there are m candidates, defined as candidate a, candidate b, ..., candidate m. S12, breakdown of candidates’ positions and tendencies: Classify the candidate's position tendencies, including position tendencies A, position tendencies B, ..., position tendencies X; S13, Promoter’s summary: We manually sorted out the propagandists of various types and tendencies, including: The propagandists under the stance A include propagandist A1, propagandist A2, …, propagandist An; The propagandists under the stance B include propagandist B1, propagandist B2, …, propagandist Bn; … The propagandists with stance X include propagandist X1, propagandist X2, ..., propagandist Xn.

3. The method for calculating candidate network support based on publicity statistics according to claim 1 is characterized in that: In step S21, data collection is performed on the public statements of the promoter according to the set update frequency.

4. The method for calculating candidate network support based on publicity statistics according to claim 2, characterized in that: Step S30 includes the following sub-steps: S31, assigning coverage weights to promoters; S32, constructing a calculation model of the propagandist's propaganda efforts on the candidate based on the reporting situation; S33, based on the propagandist weight and the propagandist's propaganda intensity calculation model for the candidate, construct a candidate network support calculation model; S34, inputting the promoter's reports on the candidate and the promoter's reports on the candidate into the candidate network support calculation model, and the candidate network support calculation model completes the calculation of the candidate network support and outputs the candidate network support.

5. The method for calculating candidate network support based on publicity statistics according to claim 4 is characterized in that: The method for allocating promoter reporting weights in step S31 is: The reporting weight of the propagandist is denoted as W, and the reporting weight of each propagandist is manually assigned; among which, the sum of the reporting weights of propagandists with a certain stance is 1.

6. The method for calculating candidate network support based on publicity statistics according to claim 5 is characterized in that: In step S32, let there be a promoter An and a candidate a. The constructed calculation model of the promoter's promotional strength on the candidate is expressed as: in, represents the intensity of the propaganda of the propagandist An for candidate a under the position tendency A; i is the number of reports on the public statements of the propagandist An about the candidate, obtained by statistical analysis of the reports of the propagandist on the candidate; is the number of reports on the public statements of the promoter An on candidate a, obtained by statistical analysis of the promoter's reports on the candidate.

7. The method for calculating candidate network support based on publicity statistics according to claim 6 is characterized in that: In step S33, the candidate network support calculation model constructed is expressed as: in, represents the network support of candidate a under position tendency A; 、 、…、 They represent the reporting weights of propagandist A1, propagandist A2, …, propagandist An respectively; 、 、…、 They respectively represent the promotion efforts of promoter A1, promoter A2, …, promoter An on candidate a.

Images