Winning prediction program, device, and method
The win/loss prediction system enhances election forecast accuracy by integrating political party support dynamics into its model, correcting predictions to account for current political winds and candidate susceptibility.
Patent Information
- Application Number
- JP2021055702
- Authority / Receiving Office
- JP · JP
- Patent Type
- Patents
- Current Assignee / Owner
- Filing Date
- 2021-03-29
- Publication Date
- 2024-11-13
- Estimated Expiration
- 2041-03-29
AI Technical Summary
Existing election prediction models suffer from decreased accuracy due to the influence of 'wind' or political party support dynamics, which are not adequately accounted for in predictions based on past election data.
A win/loss prediction system that determines the degree of support for political parties and the influence of these dynamics on candidates, using machine learning to integrate support levels and rule influences, thereby correcting predictions to reflect current political winds.
Improves the accuracy of election outcome predictions by considering the impact of political party support on individual candidates, distinguishing between candidates more and less susceptible to party influences.
Smart Images

Figure 0007582016000002 
Figure 0007582016000003 
Figure 0007582016000004
Abstract
Description
[Technical field]
[0001] The disclosed technology relates to a winning / losing prediction program, a winning / losing prediction device, and a winning / losing prediction method. [Background technology]
[0002] Technologies have been proposed to support the analysis of information related to elections. For example, a system has been proposed that centrally manages various information such as personal history information of predicted election candidates, survey results from opinion polls and opinion surveys, and voting and counting information, and collects, stores, distributes, and correlates various information. This system searches for the centrally managed information, operates election simulations, and performs data management tasks. [Prior art documents] [Patent documents]
[0003] [Patent Document 1] JP 2003-114956 A Summary of the Invention [Problem to be solved by the invention]
[0004] We will generate a model by performing machine learning on the relationship between the characteristics of candidates in past elections and the results of those candidates, and use this model and the characteristics of candidates in future elections to predict whether those candidates will win or lose. Since the outcome of an election is also influenced by the situation at the time of the election, the accuracy of the prediction may decrease if a model generated from past information is used to predict the outcome.
[0005] In one aspect, the disclosed technology aims to improve the accuracy of predicting the outcome of an election. [Means for solving the problem]
[0006] In one aspect, the disclosed technology determines a parameter related to the degree of support for a political party for each political party, and determines the degree of influence of the parameter for each of a plurality of judgment rules, each of which is represented by a combination of one or more features.The disclosed technology then predicts whether the candidate will win or lose an election based on candidate information including at least information on the political party to which the candidate belongs, the parameter, the plurality of judgment rules, and the degree of influence for each of the plurality of judgment rules. Effect of the Invention
[0007] One aspect is that it has the effect of improving the accuracy of predicting the outcome of an election. [Brief description of the drawings]
[0008] [Figure 1] This is a diagram to explain a simple method of reflecting the influence of wind on political parties in predicting the outcome of an election. [Diagram 2] FIG. 2 is a functional block diagram of the winning / losing prediction device. [Diagram 3] FIG. 13 is a diagram illustrating an example of a learning data DB. [Figure 4] FIG. 13 is a diagram illustrating an example of a rule DB. [Diagram 5] FIG. 13 is a diagram showing an example of a learning support level DB. [Figure 6] FIG. 13 is a diagram illustrating an example of a feature influence degree DB. [Figure 7] FIG. 11 is a diagram illustrating an example of a prediction target data DB. [Figure 8] 1 is a block diagram showing a schematic configuration of a computer that functions as a winning / losing prediction device. [Figure 9] 13 is a flowchart showing an example of a learning process. [Figure 10] 13 is a flowchart illustrating an example of a prediction process. [Figure 11] FIG. 11 is a diagram for explaining the effect of the present embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS
[0009] Hereinafter, an example of an embodiment of the disclosed technology will be described with reference to the drawings.
[0010] We consider the relationship between the characteristics of candidates in past elections and the results of those candidates by performing machine learning to generate a model, and then predict whether a candidate will win or lose using this model and the characteristics of candidates in future elections. In order to improve the accuracy of predictions in this case, it is possible to reflect in the prediction the degree of support for the political party to which the candidate belongs, the so-called "wind toward political parties," as the situation at the time of prediction.
[0011] As a method of reflecting the "wind toward political parties" in the prediction, a simple assumed method is to correct the predicted result of the success or failure of each candidate based on the "wind toward political parties" for the political party to which the candidate belongs. For example, as shown in Figure 1, using a model generated by machine learning, it is assumed that the importance of candidate S belonging to party A is predicted to be 1.0, and the importance of candidate T belonging to party B is predicted to be 0.4. Note that the importance is an indicator that the higher the value, the higher the probability of being predicted to "win." Also, the parameter that quantifies the "wind toward political parties" (hereinafter referred to as "support level") is assumed to be "-0.5" for party A and "+0.5" for party B. Note that the higher the value of this support level, the higher the degree of support for the political party. Therefore, in this example, it can be said that party A is facing a headwind and party B is facing a tailwind.
[0012] For example, as shown in Figure 1, if the sum of the pre-correction importance and the support level is taken as the post-correction importance, the importance of candidates S and T, i.e., the prediction of winning or losing, will be reversed before and after correction by reflecting the "party wind" in the importance. However, for example, if candidate S has advantageous characteristics in an election, such as being hereditary and having served as a minister, he can be said to be a candidate who is sure to win regardless of the "party wind." As mentioned above, if the prediction result of the winning or losing of each candidate is corrected based on the "party wind" for the party to which the candidate belongs, the influence of the "party wind" will be reflected in the same way for all candidates belonging to that party. Therefore, predictions for candidates with characteristics such as candidate S above who are not influenced by the "party wind" or who are only slightly influenced by it will be inaccurate.
[0013] Therefore, in this embodiment, the prediction accuracy is improved by taking into account the influence of the "wind toward a political party" for each feature. This embodiment will be described in detail below.
[0014] 2, the winning / losing prediction device 10 includes, as functional units that function during learning, a learning data generation unit 11, a judgment rule generation unit 12, a learning support level determination unit 13, an influence level determination unit 14, and a machine learning unit 15. The winning / losing prediction device 10 also includes, as functional units that function during prediction, a prediction target data generation unit 31, a prediction support level determination unit 33, and a prediction unit 35. A predetermined storage area of the winning / losing prediction device 10 also stores a learning data DB (Database) 16, a learning support level DB 17, a feature influence level DB 18, a rule DB 20, a prediction target data DB 36, and a prediction support level DB 37.
[0015] First, the functional units that function during learning will be described in detail.
[0016] The learning data generation unit 11 acquires learning materials input to the winning / losing prediction device 10, and generates learning data from the learning materials. The learning materials include, for example, materials related to exit polls in past elections, attribute information on candidates, etc. The learning materials include at least information on the political party to which the candidate belongs, and the results of the election. The learning data generation unit 11 extracts information on each candidate from each learning material to generate learning data, and stores the learning data for each candidate in the learning data DB 16. The learning data is an example of "candidate information in past elections whose winning / losing results are known" of the disclosed technology.
[0017] FIG. 3 shows an example of the learning data DB16. In the example of FIG. 3, each row (each record) of the learning data DB16 is learning data for each candidate. In the example of FIG. 3, the learning data includes items such as the candidate's "name", "age", "gender", "political party", "prefecture", "block", "number of times won", "previous term", "exit poll vote share", "hereditary succession", and "ministerial experience", as well as a correct label indicating "win or lose". "Political party" is the name of the political party to which the candidate belongs. "Prefecture" and "block" are information indicating the electoral district in which the candidate ran. "Number of times won" is the number of times the candidate won in past elections. "Previous term" is information indicating whether the candidate is a current incumbent, former incumbent, or newcomer. Note that the items included in the learning data are not limited to the example of FIG. 3, and may include other items such as the content of the claim, educational background, and whether the electoral district is the candidate's hometown or not.
[0018] The item names and values of the items in the learning data other than the candidate's identification information ("Name" in the example of Figure 3) and the correct label "Win or Lose" are the "characteristics" of the candidate. In the following, characteristics are expressed in the format of "item name = (or inequality sign) value".
[0019] The judgment rule generating unit 12 generates a comprehensive combination of features included in the learning data stored in the learning data DB 16. For features whose values are numerical values, the value itself may be used as a feature, or a range to which the value belongs may be used as a feature. For example, the feature for the item "number of times of winning" may be "number of times of winning = 1 time", "number of times of winning = 2 times", "number of times of winning ≧ 3 times", etc. The judgment rule generating unit 12 calculates the contribution degree to the prediction of the election result for each generated combination. The contribution degree may be a value that increases as the number of learning data having the feature of the combination with the correct answer label "winning" increases. The judgment rule generating unit 12 generates a judgment rule by selecting combinations whose contribution degree is a predetermined value or more, or combinations whose contribution degree is a predetermined number of combinations among the comprehensively generated combinations. Therefore, each judgment rule is represented by a combination of one or more features.
[0020] The judgment rule generation unit 12 assigns identification information to the generated judgment rule and stores it in the rule DB 20. An example of the rule DB 20 is shown in Fig. 4. In Fig. 4, "rule ID" is identification information of the judgment rule, and here, the rule IDs are consecutive numbers 1, 2, .... Below, a judgment rule with rule ID j will be represented as "judgment rule j". Note that the details of "impact" and "importance" in Fig. 4 will be described later, but are left blank at this stage.
[0021] The support level determination unit 13 at the time of learning determines the support level for each political party, which is a parameter related to the degree of support for the political party, i.e., the "wind toward a political party." For example, the support level determination unit 13 at the time of learning may determine the support level based on positive or negative opinions about the political party in information on the Internet. Specifically, the support level determination unit 13 extracts pairs of keywords related to the political party and positive or negative keywords from each opinion such as political articles on news sites and posts on SNS (Social Network Service). Keywords related to the political party may be, for example, the name of the political party, the abbreviation of the political party, the name of the party leader, etc. Positive or negative keywords may be keywords related to election promises, gaffes, political views, etc., with information indicating whether the meaning expressed by the keywords is positive or negative.
[0022] The support level determination unit 13 at the time of learning identifies whether the opinion is a positive opinion or a negative opinion based on the frequency of appearance of positive keywords and negative keywords in the extracted keyword set. For example, when the opinion contains more positive keywords, the support level determination unit 13 identifies the opinion as a positive opinion, and when the opinion contains more negative keywords, the support level determination unit 13 identifies the opinion as a negative opinion. The support level determination unit 13 then determines the support level so that the more positive opinions there are, the higher the support level, and the more negative opinions there are, the lower the support level. That is, the support level determination unit 13 determines the support level so that the more positive opinions there are, the higher the support level, and the more negative opinions there are, the lower the support level. For example, the support level determination unit 13 may determine the support level so that the more positive opinions there are, the higher the support level, and the more negative opinions there are, the lower the support level. For example, the support level determination unit 13 may determine the support level so that the more positive opinions there are, the higher the support level, and the more negative opinions there are, the higher the support level, and the lower the support level, and the more negative opinions there are, the higher the support level, the lower the support level.
[0023] Furthermore, the learning support level determination unit 13 may acquire information on the approval rating of a political party as shown in the results of opinion polls, etc., and determine the support level to be higher the higher the trend in the approval rating is increasing, and to be lower the higher the trend in the approval rating is decreasing. In other words, the learning support level determination unit 13 determines the support level to represent a "tailwind" when the trend in the approval rating is increasing, and a "headwind" when the trend in the approval rating is decreasing.
[0024] The learning-time support level determination unit 13 stores the determined support level for each political party in the learning-time support level DB 17. Fig. 5 shows an example of the learning-time support level DB 17. In the example of Fig. 5, a positive support level indicates that the wind is blowing in the party's favor, and a negative support level indicates that the wind is blowing in the party's favor.
[0025] The influence degree determination unit 14 determines an influence degree, which is an index showing the degree of influence of the support degree, for each of the judgment rules stored in the rule DB 20. Specifically, the influence degree determination unit 14 refers to the feature influence degree DB 18 in which the feature influence degree for each feature is defined, and determines the influence degree of the support degree for each judgment rule based on the feature influence degree for each feature included in the judgment rules stored in the rule DB 20.
[0026] FIG. 6 shows an example of the feature influence DB18. In the example of FIG. 6, the feature influence is a value between 0 and 1, and when the feature influence is 1, it indicates that the party is most influenced by the wind, and when the influence is 0, it indicates that the party is not influenced by the wind. For example, "party = *" is a feature that is directly influenced by the wind, so the feature influence is defined as 1. Note that "*" indicates that the feature influence is 1 regardless of which party the value of the item "party" indicates. In addition, since newcomers are more susceptible to the wind of the party, the feature influence may be defined as being larger the fewer the "number of times elected". In addition, for features that are not related to the wind of the party, such as the candidate's age and gender, the influence may be defined as 0. In addition, when the learning data includes items such as the content of the claim, the feature influence may be defined according to the content of the claim, depending on the policies and support groups that are attracting attention in the administration and election at the time.
[0027] The influence determining unit 14, for example, acquires the feature influence of each feature included in the judgment rule from the feature influence DB 18, and determines the average, sum, weighted sum, product, etc. of the acquired feature influences as the influence for the judgment rule. The influence determining unit 14 stores the determined influence in the rule DB 20 in association with the judgment rule.
[0028] The machine learning unit 15 acquires the learning data stored in the learning data DB 16, the support for each political party stored in the learning support DB 17, a plurality of judgment rules stored in the rule DB 20, and the influence for each of the plurality of judgment rules. The machine learning unit 15 uses the acquired information to calculate the importance for each of the plurality of judgment rules by machine learning. Specifically, the machine learning unit 15 calculates the importance such that a value obtained by integrating the importance for the judgment rules satisfied by each learning data, taking into account the support for each political party and its influence, corresponds to the winning or losing indicated by the correct label included in the learning data.
[0029] For example, in the case of a method using logistic regression, the machine learning unit 15 calculates the winning probability of the candidate i as p i Then, the following equation (1) is used as a regression equation to calculate the importance β of the decision rule j (j = 1, 2, . . . , m, where m is the number of decision rules): j Calculate the following: i,j is the influence of decision rule j × the support for the party to which candidate i belongs, x j,i ∈{0,1} represents 1 if the training data of candidate i satisfies decision rule j, and 0 if it does not.
[0030]
number
[0031] For example, the probability of candidate R winning indicated by the learning data in the first row stored in the learning data DB 16 shown in Fig. 3 is assumed to be p. Also, assume that the judgment rules and influence levels stored in the rule DB 20 shown in Fig. 4 and the support levels for each political party stored in the learning support level DB 17 shown in Fig. 5 are used. In this case, the learning data for candidate R satisfies judgment rules 1, 3, and 5 out of the judgment rules. Therefore, the machine learning unit 15 calculates log(p / (1-p))=2 0.8×0.5 β1+0×β2+2 0×0.5 β3+0×β4+2 1×0.5 β5+0×β6≒1.32β1+β3+1.41β5 is obtained. The machine learning unit 15 calculates β j Then, the machine learning unit 15 calculates p by substituting an initial value or a value obtained by repeated calculations into β so that the calculated p corresponds to the correct label “winning” for the candidate R. j The process of updating the value of β is repeatedly performed using the learning data of each candidate. For example, the machine learning unit 15 updates β so that the winning probability p of a candidate whose correct answer label is “successful” is 0.5 or more, and the winning probability p of a candidate whose correct answer label is “lost” is less than 0.5. j Calculate.
[0032] The machine learning unit 15 calculates the importance β of each judgment rule calculated by machine learning. j is stored in the rule DB 20 in association with the judgment rule.
[0033] Next, the functional units that function during prediction will be described in detail.
[0034] The prediction target data generating unit 31 acquires prediction materials input to the winning / losing prediction device 10, and generates prediction target data from the prediction materials. The prediction materials may be, for example, materials similar to the learning materials for the election to be predicted. The prediction target data generating unit 31 extracts information for each candidate from each prediction material to generate prediction target data, and stores the prediction target data for each candidate in the prediction target data DB36. The prediction target data is an example of the "candidate information" of the disclosed technology. FIG. 7 shows an example of the prediction target data DB36. The data configuration of the prediction target data DB36 is the same as the data configuration of the learning data DB16 shown in FIG. 3. However, since the winning / losing of the candidate is unknown for the prediction target data, the item "winning / losing" which is the correct answer label included in the learning data is not included.
[0035] The support level at prediction time determination unit 33, like the support level at learning time determination unit 13, determines the support level for each political party, which is a parameter related to the degree of support for the political party at the time of the election to be predicted, i.e., the "wind toward the political party". The support level at prediction time determination unit 33 stores the determined support level for each political party in the support level at prediction time DB 37. The data structure of the support level at prediction time DB 37 is the same as the data structure of the support level at learning time DB 17 shown in FIG. 5.
[0036] The prediction unit 35 acquires the prediction target data stored in the prediction target data DB 36, the support for each political party stored in the support at prediction DB 37, the multiple judgment rules stored in the rule DB 20, and the influence for each of the multiple judgment rules. The prediction unit 35 predicts the election results of the candidates based on the acquired information. Specifically, the prediction unit 35 corrects the importance of each of the multiple judgment rules with the support and influence determined for each judgment rule. Then, the prediction unit 35 predicts the election results of the candidate based on a value obtained by integrating the corrected importance for the judgment rules that satisfy one or more features extracted from the prediction target data of the candidate.
[0037] For example, when using the regression equation (1), the probability of winning for candidate V indicated by the prediction target data in the first row stored in the prediction target data DB36 shown in FIG. 7 is assumed to be p. Also, the judgment rule, influence, and importance stored in the rule DB20 shown in FIG. 4 are assumed to be used. Furthermore, the support level of Party C stored in the support level at time of prediction DB37 is assumed to be "+0.2". In this case, the prediction target data for candidate V satisfies judgment rules 2 and 4 of the judgment rules. Therefore, the prediction unit 35 calculates log(p / (1-p))=2 0.4×0.2 ×0.4+2 0.5×0.2 × (-0.8) ≒ -0.43, so p ≒ 0.39. γ_i,j β j corresponds to the corrected importance.
[0038] The prediction unit 35 outputs a prediction result of winning or losing for each candidate whose prediction target data is stored in the prediction target data DB 36. The prediction result may be the winning probability calculated as described above, or may output a prediction result of "winning" when the winning probability is 0.5 or more, and "losing" when the winning probability is less than 0.5.
[0039] The winning / losing prediction device 10 can be realized by, for example, a computer 40 shown in FIG. 8. The computer 40 includes a CPU (Central Processing Unit) 41, a memory 42 as a temporary storage area, and a non-volatile storage unit 43. The computer 40 also includes an input / output device 44 such as an input unit and a display unit, and an R / W (Read / Write) unit 45 that controls reading and writing of data to a storage medium 49. The computer 40 also includes a communication I / F (Interface) 46 that is connected to a network such as the Internet. The CPU 41, the memory 42, the storage unit 43, the input / output device 44, the R / W unit 45, and the communication I / F 46 are connected to one another via a bus 47.
[0040] The storage unit 43 can be realized by a hard disk drive (HDD), a solid state drive (SSD), a flash memory, or the like. The storage unit 43 as a storage medium stores a winning / losing prediction program 50 for making the computer 40 function as the winning / losing prediction device 10. The winning / losing prediction program 50 has a learning data generation process 51, a judgment rule generation process 52, a learning support determination process 53, an influence determination process 54, and a machine learning process 55. The winning / losing prediction program 50 also has a prediction target data generation process 61, a prediction support determination process 63, and a prediction process 65. The storage unit 43 also has an information storage area 70 in which information constituting each of the learning data DB 16, the learning support DB 17, the feature influence DB 18, the rule DB 20, the prediction target data DB 36, and the prediction support DB 37 is stored.
[0041] The CPU 41 reads out the winning / losing prediction program 50 from the storage unit 43, expands it in the memory 42, and sequentially executes the processes of the winning / losing prediction program 50. The CPU 41 operates as the learning data generation unit 11 shown in FIG. 2 by executing the learning data generation process 51. The CPU 41 also operates as the judgment rule generation unit 12 shown in FIG. 2 by executing the judgment rule generation process 52. The CPU 41 also operates as the learning support determination unit 13 shown in FIG. 2 by executing the learning support determination process 53. The CPU 41 also operates as the influence determination unit 14 shown in FIG. 2 by executing the influence determination process 54. The CPU 41 also operates as the machine learning unit 15 shown in FIG. 2 by executing the machine learning process 55. The CPU 41 also operates as the prediction target data generation unit 31 shown in FIG. 2 by executing the prediction target data generation process 61. The CPU 41 also operates as the prediction support determination unit 33 shown in FIG. 2 by executing the prediction support determination process 63. 2 by executing a prediction process 65. The CPU 41 also reads information from an information storage area 70, and loads the learning data DB 16, the learning support DB 17, the feature influence DB 18, the rule DB 20, the prediction target data DB 36, and the prediction support DB 37 into the memory 42. As a result, the computer 40 that has executed the winning / losing prediction program 50 functions as the winning / losing prediction device 10. The CPU 41 that executes the program is hardware.
[0042] The functions realized by the winning / losing prediction program 50 can also be realized by, for example, a semiconductor integrated circuit, more specifically, an ASIC (Application Specific Integrated Circuit) or the like.
[0043] Next, the operation of the winning / losing prediction device 10 according to this embodiment will be described. When learning materials are input to the winning / losing prediction device 10 during learning, the winning / losing prediction device 10 executes the learning process shown in FIG. 9. When prediction materials are input to the winning / losing prediction device 10 during prediction, the winning / losing prediction device 10 executes the prediction process shown in FIG. 10. The learning process and prediction process are examples of the winning / losing prediction method of the disclosed technology. Each of the learning process and prediction process will be described below.
[0044] First, the learning process shown in FIG. 9 will be described.
[0045] In step S11, the learning data generation unit 11 acquires the learning materials inputted into the winning / losing prediction device 10, extracts information for each candidate from each learning material to generate learning data, and stores the learning data for each candidate in the learning data DB16.
[0046] Next, in step S12, the determination rule generation unit 12 generates comprehensive combinations of features included in the learning data stored in the learning data DB 16, and calculates the contribution of each generated combination to the prediction of the election outcome. The determination rule generation unit 12 then generates a determination rule by selecting combinations whose contribution degree is equal to or greater than a predetermined value, or combinations whose contribution degrees are the top predetermined number, from among the comprehensively generated combinations. The determination rule generation unit 12 then assigns identification information (rule ID) to the generated determination rule, and stores it in the rule DB 20.
[0047] Next, in step S13, the learning support level determination unit 13 determines the support level, which is a parameter related to "winds toward political parties," for each political party based on the number of positive or negative opinions about the political party in information on the Internet and the trend in support rates for the political party. The learning support level determination unit 13 then stores the determined support level for each political party in the learning support level DB 17. Note that the processing of this step may be performed in a reverse order to steps S11, S12, and S14, or may be performed in parallel with the processing of these steps.
[0048] Next, in step S14, the influence determining unit 14 refers to the feature influence DB 18 in which the feature influence for each feature is defined, and determines the influence of the support for each judgment rule based on the feature influence for each feature included in the judgment rule stored in the rule DB 20. Then, the influence determining unit 14 stores the determined influence in the rule DB 20 in association with the judgment rule.
[0049] Next, in step S15, the machine learning unit 15 acquires the learning data stored in the learning data DB 16, the support for each political party stored in the learning support DB 17, the multiple judgment rules stored in the rule DB 20, and the influence for each of the multiple judgment rules. Then, the machine learning unit 15 uses the acquired information to calculate the importance for each of the multiple judgment rules through machine learning. The machine learning unit 15 stores the calculated importance for each judgment rule in the rule DB 20 in association with the judgment rule, and the learning process ends.
[0050] Next, the prediction process shown in FIG. 10 will be described.
[0051] In step S21, the prediction target data generation unit 31 acquires the prediction materials inputted to the winning / losing prediction device 10, extracts information for each candidate from each prediction material to generate prediction target data, and stores the prediction target data for each candidate in the prediction target data DB 36.
[0052] Next, in step S22, similar to step S13 of the learning process, the prediction support level determiner 33 determines the support level, which is a parameter related to "opinion toward a political party," for each political party, and stores it in the prediction support level DB 37. Note that the order of the processing of this step and step S21 may be interchanged, or the processing of step S21 may be executed in parallel.
[0053] Next, in step S23, the prediction unit 35 acquires the prediction target data stored in the prediction target data DB 36, the support for each political party stored in the prediction time support DB 37, and the multiple judgment rules and their influences stored in the rule DB 20. Then, the prediction unit 35 corrects the importance of each of the multiple judgment rules with the support and influence determined for each judgment rule. In addition, the prediction unit 35 calculates the probability of winning for each candidate using the corrected importance for the judgment rules that satisfy one or more features extracted from the prediction target data of the candidate.
[0054] Next, in step S24, the prediction unit 35 outputs the winning probability calculated in step S23 as a prediction result for each candidate whose prediction target data is stored in the prediction target data DB 36. Alternatively, the prediction unit 35 may output a prediction result in which the winning probability is replaced with "winning" or "losing". Then, the prediction process ends.
[0055] As described above, the winning / losing prediction device according to this embodiment determines a parameter related to the degree of support for a political party, that is, a support level indicating the wind toward a political party, for each political party. In addition, the winning / losing prediction device determines an influence level, which is an index indicating the degree of influence of the support level, for each of a plurality of judgment rules, each of which is represented by a combination of one or more features. Then, the winning / losing prediction device predicts the election result of a candidate based on candidate information including at least information on the political party to which the candidate belongs, the support level, a plurality of judgment rules, and the influence level for each of the plurality of judgment rules. This makes it possible to reflect the influence of the wind toward a political party according to the characteristics of the candidate. In other words, even for candidates of the same political party, it is possible to predict the winning / losing result by distinguishing between candidates who are easily influenced by the wind toward a political party and candidates who are not easily influenced by it. Therefore, it is possible to improve the prediction accuracy of the election result.
[0056] For example, as shown in FIG. 11, it is assumed that the support level indicating the wind for Party A at the time of the election to be predicted is determined to be "-0.5" and the support level indicating the wind for Party B is determined to be "+0.5". In addition, it is assumed that the judgment rules 1, 2, and 3 are generated as judgment rules, and the influence and importance are calculated for each of them. In the example of FIG. 11, the influence level of judgment rule 1 is 0, and the influence levels of judgment rules 2 and 3 are 1. This indicates that the judgment rule 1 is a judgment rule consisting of a combination of features that are not influenced by the wind for political parties, and the judgment rules 2 and 3 are judgment rules consisting of a combination of features that are easily influenced by the wind for political parties. The importance level of each judgment rule is adjusted by adding this influence level to reflect the wind for political parties, resulting in the adjusted importance level. In other words, the adjusted importance level is the importance level adjusted by the influence level and the support level for each judgment rule. Furthermore, as shown in the bottom left diagram of Figure 11, the characteristics of candidate W from Party A in the Aomori electoral district satisfy judgment rule 2, and the characteristics of candidate X from Party B satisfy judgment rule 3. Furthermore, as shown in the bottom right diagram of Figure 11, the characteristics of candidate Y from Party A in the Tokyo electoral district satisfy judgment rule 1, and the characteristics of candidate Z from Party B satisfy judgment rule 3.
[0057] As shown in the figure for the Aomori constituency in the lower left of Figure 11, both candidates W and X satisfy the judgment rule for being easily influenced by the winds of political parties, that is, they have characteristics that make them easily influenced by the winds of political parties. Therefore, for candidate W, he is influenced by the headwinds of his party A, and for candidate X, he is influenced by the tailwinds of his party B, so the predictions of winning and losing are reversed before and after the importance correction. Also, as shown in the figure for the Tokyo constituency in the lower right of Figure 11, candidate Y satisfies the judgment rule for not being influenced by the winds of political parties, that is, he has characteristics that he is not influenced by the winds of political parties. On the other hand, candidate Z satisfies the judgment rule for being easily influenced by the winds of political parties, that is, he has characteristics that he is easily influenced by the winds of political parties. Therefore, while candidate Z is influenced by the tailwinds of his party B, candidate Y is not influenced by the headwinds of his party A, so the predictions of winning and losing are not reversed before and after the importance correction. In this way, even for candidates belonging to the same party A, it is possible to predict the outcome of an election by reflecting whether they are easily influenced by the winds of political parties depending on the characteristics of each candidate.
[0058] In the above embodiment, the case where the functional unit that functions during learning and the functional unit that functions during prediction are realized in one computer has been described, but is not limited to this. For example, the machine learning device having the functional unit that functions during learning and the prediction device having the functional unit that functions during prediction may be realized in different computers.
[0059] In the above embodiment, the winning / losing prediction program is stored (installed) in the storage unit in advance, but the present invention is not limited to this. The program according to the disclosed technology can also be provided in a form stored in a storage medium such as a CD-ROM, a DVD-ROM, or a USB memory.
[0060] The following supplementary notes are further disclosed regarding the above embodiment.
[0061] (Appendix 1) Determine parameters for each political party regarding the degree of support for that party, determining a degree of influence of the parameter for each of a plurality of judgment rules, each of which is represented by a combination of one or more features; predicting whether the candidate will win or lose the election based on candidate information including at least information on the political party to which the candidate belongs, the parameters, the plurality of judgment rules, and the degree of influence for each of the plurality of judgment rules; A program for predicting the results of a lottery by causing a computer to execute a process including the above.
[0062] (Appendix 2) The process of predicting the outcome of an election includes correcting the importance of a judgment rule among the plurality of judgment rules, which is satisfied by one or more features extracted from the candidate information, with respect to the prediction of the outcome of the election, by the parameters and the degree of influence determined for the satisfied judgment rule.
[0063] (Appendix 3) A program for predicting whether a candidate will win or lose, as described in Appendix 2, in which the importance is calculated by machine learning using candidate information from past elections in which the results are known, the parameters, the plurality of judgment rules, and the degree of influence for each of the plurality of judgment rules.
[0064] (Appendix 4) The winning / losing prediction program according to any one of appendices 1 to 3, wherein the process of determining the degree of influence includes determining the degree of influence based on a predetermined degree of influence for each of the features included in the judgment rule.
[0065] (Appendix 5) The process of determining the degree of influence of a winning or losing prediction program described in Appendix 4 includes determining the degree of influence as the average, sum, weighted sum, or product of the influence degrees preset for each of the features included in the judgment rule.
[0066] (Appendix 6) The program for predicting the outcome of an election according to any one of claims 1 to 5, wherein the plurality of judgment rules are combinations of the features selected from among comprehensive combinations of the features, the combinations having a contribution to the prediction of the outcome of the election equal to or greater than a predetermined value, or combinations having a top predetermined number of contributions.
[0067] (Appendix 7) A program for predicting whether a candidate will win or lose, as described in any one of Appendix 1 to Appendix 6, wherein the process of determining the parameters includes determining the parameters based on at least one of positive or negative opinions about the political party in information on the Internet and changes in support rates for the political party.
[0068] (Appendix 8) The process of determining the parameters based on the positive or negative opinions includes extracting pairs of keywords related to the political party and positive or negative keywords from the information on the Internet, and determining the parameters based on the frequency of appearance of the positive and negative keywords in the extracted pairs.
[0069] (Appendix 9) 9. A program for predicting whether a prize will be awarded or not, comprising: a process of determining the parameters such that the degree of support is higher the higher the frequency of appearance of the positive keywords compared to the negative keywords.
[0070] (Appendix 10) A winning / losing prediction program as described in Appendix 7, in which the process of determining the parameters is such that the higher the increasing trend of the support rate, the higher the support level.
[0071] (Appendix 11) a support level determination unit that determines a parameter related to the support level for each political party; an influence degree determining unit that determines an influence degree of the parameter for each of a plurality of judgment rules, each of which is represented by a combination of one or more features; a prediction unit that predicts whether the candidate will win or lose an election based on candidate information including at least information on the political party to which the candidate belongs, the parameters, the plurality of judgment rules, and the degree of influence for each of the plurality of judgment rules; A winning / losing prediction device including:
[0072] (Appendix 12) The prediction unit corrects the importance of a judgment rule among the plurality of judgment rules that is satisfied by one or more features extracted from the candidate information with respect to predicting the outcome of the election using the parameters and the degree of influence determined for the satisfied judgment rule.
[0073] (Appendix 13) The winning / losing prediction device described in Appendix 12, wherein the importance is calculated by machine learning using candidate information from past elections whose winning and losing results are known, the parameters, the plurality of judgment rules, and the degree of influence for each of the plurality of judgment rules.
[0074] (Appendix 14) 14. The winning / losing prediction device according to any one of supplementary notes 11 to 13, wherein the influence degree determination unit determines an influence degree based on a preset influence degree for each of the features included in the judgment rule.
[0075] (Appendix 15) The winning / losing prediction device according to claim 14, wherein the influence determination unit determines the average, sum, weighted sum, or product of the influence levels preset for each of the features included in the judgment rule as the influence level.
[0076] (Appendix 16) The plurality of judgment rules are a selection of comprehensive combinations of the features whose contribution to the prediction of the election outcome is equal to or greater than a predetermined value, or a selection of combinations whose contribution is at the top of a predetermined number.
[0077] (Appendix 17) The winning / losing prediction device according to any one of appendices 11 to 16, wherein the support level determination unit determines the support level based on at least one of positive or negative opinions about the political party in information on the Internet and changes in the support rate for the political party.
[0078] (Appendix 18) The support level determination unit extracts pairs of keywords related to the political party and positive keywords or negative keywords from the information on the Internet, and determines the parameters based on the frequency of appearance of the positive keywords and the negative keywords in the extracted pairs.
[0079] (Appendix 19) Determine parameters for each political party regarding the degree of support for that party, determining a degree of influence of the parameter for each of a plurality of judgment rules, each of which is represented by a combination of one or more features; predicting whether the candidate will win or lose the election based on candidate information including at least information on the political party to which the candidate belongs, the parameters, the plurality of judgment rules, and the degree of influence for each of the plurality of judgment rules; The method includes the steps of:
[0080] (Appendix 20) Determine parameters for each political party regarding the degree of support for that party, determining a degree of influence of the parameter for each of a plurality of judgment rules, each of which is represented by a combination of one or more features; predicting whether the candidate will win or lose the election based on candidate information including at least information on the political party to which the candidate belongs, the parameters, the plurality of judgment rules, and the degree of influence for each of the plurality of judgment rules; A storage medium storing a winning / losing prediction program for causing a computer to execute a process including the above. [Explanation of symbols]
[0081] 10 Winning and losing prediction device 11 Learning data generation unit 12. Judgment rule generation unit 13 Learning support determination unit 14 Impact Determination Section 15 Machine Learning Department 16 Learning Data DB 17 Learning support DB 18 Feature Impact DB 20 Rule DB 31 Prediction target data generation unit 33 Prediction support determination unit 35 Prediction Department 36 Prediction target data DB 37 Prediction support DB 40 Computer 41 CPU 42 Memory 43 Storage section 49 Storage medium 50 Winning and losing prediction program
Claims
1. Determine parameters for each political party regarding the degree of support for that party, determining a degree of influence of the parameter for each of a plurality of judgment rules, each of which is represented by a combination of one or more features; predicting whether the candidate will win or lose the election based on candidate information including at least information on the political party to which the candidate belongs, the parameters, the plurality of judgment rules, and the degree of influence for each of the plurality of judgment rules; A program for predicting the results of a lottery by causing a computer to execute a process including the above.
2. The process of predicting the outcome of an election includes correcting the importance of a judgment rule among the plurality of judgment rules, which is satisfied by one or more features extracted from the candidate information, with respect to the prediction of the outcome of the election, using the parameters and the degree of influence determined for the satisfied judgment rule.
3. The program for predicting whether a candidate will win or lose is described in claim 2, wherein the importance is calculated by machine learning using candidate information from past elections in which the results are known, the parameters, the plurality of judgment rules, and the degree of influence for each of the plurality of judgment rules.
4. The winning / losing prediction program according to any one of claims 1 to 3, wherein the process of determining the degree of influence includes determining the degree of influence based on a predetermined degree of influence for each of the features included in the judgment rule.
5. The winning / losing prediction program of claim 4, wherein the process of determining the degree of influence includes determining the average, sum, weighted sum, or product of the influence degrees preset for each of the features included in the judgment rule as the degree of influence.
6. The program for predicting the outcome of an election described in any one of claims 1 to 5, wherein the plurality of judgment rules are selected from comprehensive combinations of the features, the combinations having a contribution to the prediction of the outcome of the election equal to or greater than a predetermined value, or the combinations having a top predetermined number of contributions.
7. A program for predicting whether an election is going to be held or not, comprising: a step of determining the parameters based on at least one of positive or negative opinions about the political party in information on the Internet and changes in the approval rating of the political party.
8. a support level determination unit that determines a parameter related to the support level for each political party; an influence degree determining unit that determines an influence degree of the parameter for each of a plurality of judgment rules, each of which is represented by a combination of one or more features; a prediction unit that predicts whether the candidate will win or lose an election based on candidate information including at least information on the political party to which the candidate belongs, the parameters, the plurality of judgment rules, and the degree of influence for each of the plurality of judgment rules; A winning / losing prediction device including:
9. Determine parameters for each political party regarding the degree of support for that party, determining a degree of influence of the parameter for each of a plurality of judgment rules, each of which is represented by a combination of one or more features; predicting whether the candidate will win or lose the election based on candidate information including at least information on the political party to which the candidate belongs, the parameters, the plurality of judgment rules, and the degree of influence for each of the plurality of judgment rules; The method includes the steps of:
Citation Information
Patent Citations
Election news report supporting system and device, and method and system for supporting election news report
JP2003114956A
Winning and losing line forecasting system
JP2012038041A
Prediction system of number of seats according to political party based on diet election preliminary survey
JP2015053039A
Predictive Analytical System and Method
US20190205770A1
Device for predicting, from publicly reported polled approval ratings, percentage of election votes that reflect announcement effect
WO2021038675A1
