Scientific and technological journal new media influence evaluation method and system

Abstract

The invention provides a scientific and technological journal new media influence evaluation method and system, and belongs to the technical field of data processing, and the method comprises the steps: collecting basic index data of a new media platform of a scientific and technological journal, and carrying out the standardization processing of the basic index data, and generating standardized index data; performing data weight correction on the standardized index data according to time nodes based on an exponential decay function to generate final index data; constructing a hierarchical evaluation model of the new media influence, and determining the subjective weight of the new media platform and the fusion weight of the indexes fusing the subjective weight of the new media platform and the objective weight of the indexes; and calculating single-platform influence and cross-platform influence of the science and technology periodicals by utilizing the final index data based on the structure and weight setting of the hierarchical evaluation model. The problems that in the prior art, the relevance between the science and technology journal new media influence and the science and technology journal academic influence is weak, and the science and technology journal new media influence evaluation is not comprehensive are solved.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a method and system for evaluating the new media influence of scientific and technological journals. Background Art

[0002] As an innovative way of publishing that can effectively enhance the influence of scientific and technological journals, new media is increasingly widely used in publishing practice and has become one of the important means for scientific and technological journals to achieve high-quality development in the new era. For academic journals, new media publishing means combining the content advantages of traditional academic publishing with the dissemination advantages of digital media, breaking the original single model of paper publishing, and disseminating innovative scientific research results through multiple channels and three-dimensional methods through a variety of enhanced publishing methods, so as to achieve the purpose of expanding the influence of scientific research results, promoting exchanges among scientific researchers, and popularizing science among the public.

[0003] At present, there are many new media communication platforms used by scientific and technological journals, and there are large differences in the indicator data of each platform. Some domestic public opinion monitoring companies have formulated corresponding new media communication indexes for different platforms, but these indexes did not take into account the academic influence of the journals during the design process, resulting in a weak correlation between the new media communication index and the academic influence of the journal. At present, there is no scientific and reasonable evaluation system to unify the data of each platform, and it is impossible to quantitatively judge the relationship between the new media influence and the academic influence of scientific and technological journals.

[0004] Therefore, it is urgent to design a technical solution for evaluating the new media influence of scientific journals. Summary of the invention

[0005] The present invention provides a method and system for evaluating the new media influence of scientific and technological journals, which are used to solve the defects of the prior art, such as the weak correlation between the new media influence and the academic influence of the journal, and the incomplete evaluation of the new media influence.

[0006] In a first aspect, the present invention provides a method for evaluating the new media influence of a scientific journal, comprising: collecting basic indicator data of a new media platform of a scientific journal, and performing standardization processing on the basic indicator data to generate standardized indicator data; the new media platform includes multiple social media platforms opened by the journal, and an official website platform of the journal; Based on the exponential decay function, the data weight of the standardized indicator data is modified according to the time node to generate the final indicator data; Construct a hierarchical evaluation model of new media influence, and determine the subjective weight of the new media platform, as well as the fusion weight of the indicator that combines the subjective weight of the new media platform and the objective weight of the indicator; the hierarchical evaluation model includes a target layer and a platform layer, the target layer is used to output the new media influence of cross-platform scientific journals, and the platform layer includes multiple new media platforms, and each new media platform has multiple indicators; Based on the structure and weight setting of the hierarchical evaluation model, the final indicator data is used to calculate the single-platform influence and cross-platform influence of scientific journals.

[0007] According to a method for evaluating the new media influence of a scientific journal provided by the present invention, after calculating the single-platform influence of the scientific journal, it also includes: using preset influence parameters to verify the correlation of the cross-platform influence and calculate the correlation coefficient; determining whether the calculation result of the cross-platform influence meets the requirements based on the range of the correlation coefficient; if it does not meet the requirements, adjusting the indicators and / or indicator weights.

[0008] According to a method for evaluating the new media influence of a scientific journal provided by the present invention, basic indicator data of the new media platform of the scientific journal is collected, and the basic indicator data is standardized to generate standardized indicator data, including: using a web crawler tool or a third-party data monitoring platform to obtain the basic indicator data of the new media platform of the scientific journal; the basic indicator data of the social media platform includes: the number of fans, the number of readings, the number of likes, the number of reposts and the number of comments, and the basic indicator data of the official website platform of the journal includes the number of visits, the number of independent visitors, the number of pages visited each time and the number of page views; the basic indicator data is normalized to generate standardized indicator data.

[0009] According to a method for evaluating the new media influence of scientific journals provided by the present invention, data weights of standardized indicator data are corrected according to time nodes based on an exponential decay function to generate final indicator data, including: using an exponential decay function to assign time weights to data at different time nodes; based on the time weights, the standardized indicator data are adjusted to generate final indicator data.

[0010] According to a method for evaluating the new media influence of scientific journals provided by the present invention, the subjective weight of the new media platform and the fusion weight of the indicator that combines the subjective weight of the new media platform and the objective weight of the indicator are determined, including: using the hierarchical analysis method to determine the first M Subjective weight of new media platforms and, pursuant to M The first new media platform i This scientific journal j The information entropy of each indicator is used to calculate the objective weight ; Calculate subjective weight With objective weight The difference of the indicators is calculated, and the average difference of all indicators is determined to set the power function index according to the average difference; based on the power function index, the preset power function is set to the subjective weight With objective weight Perform nonlinear fusion to generate fusion weights .

[0011] According to a method for evaluating the new media influence of a scientific journal provided by the present invention, the preset power function is: ; in, is the power function exponent, n for i The maximum value of .

[0012] According to a method for evaluating the new media influence of a scientific journal provided by the present invention, based on the structure and weight setting of a hierarchical evaluation model, the single-platform influence and cross-platform influence of a scientific journal are calculated using the final indicator data, including: calculating the first i This scientific journal is in M The influence of a single platform under the new media platform:

[0013] in, is the normalized indicator data of the final indicator data, and L is the total number of indicators; According to i The cross-platform influence of this scientific journal is calculated based on the single-platform influence of each new media platform and the subjective weight of the new media platform.

[0014] In a second aspect, the present invention further provides a new media influence evaluation system for scientific and technological journals, comprising: A data collection module is used to collect basic indicator data of the new media platform of scientific and technological journals, and to standardize the basic indicator data to generate standardized indicator data; the new media platform includes multiple social media platforms opened by the journal, and the official website platform of the journal; A data correction module is used to correct the data weight of the standardized indicator data according to the time node based on the exponential decay function to generate the final indicator data; A hierarchical evaluation model construction module is used to construct a hierarchical evaluation model of new media influence, and determine the subjective weight of the new media platform, and the fusion weight of the indicator that integrates the subjective weight of the new media platform and the objective weight of the indicator; the hierarchical evaluation model includes a target layer and a platform layer, the target layer is used to output the new media influence of cross-platform scientific and technological journals, and the platform layer includes multiple new media platforms, and each new media platform has multiple indicators; The impact evaluation module is used to calculate the single-platform influence and cross-platform influence of scientific journals based on the structure and weight setting of the hierarchical evaluation model and using the final indicator data.

[0015] In a third aspect, the present invention provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps of the method for evaluating the new media influence of scientific journals as described in any one of the above are implemented.

[0016] In a fourth aspect, the present invention further provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of any of the above-described methods for evaluating the new media influence of scientific journals.

[0017] The method and system for evaluating the new media influence of scientific and technological journals provided by the present invention achieve the purpose of formulating different new media influence evaluation methods for different types of scientific and technological journals, solve the problems of data irrelevance across new media platforms and weak matching between new media influence and journal influence, and at the same time, through the nonlinear fusion of subjective and objective weights (two types of weights, namely, analytic hierarchy process and entropy method), retain the professionalism of subjective judgment and incorporate the objectivity of data, balance subjective and objective information, improve the scientific nature of weights, reduce the bias of the calculated new media influence of scientific and technological journals, achieve dynamic, adaptable and high-precision evaluation requirements, solve the problem of incomplete new media influence evaluation, and enable it to evaluate the size of the new media influence of cross-platform scientific and technological journals from the perspective of HowNet influence that scientific and technological journal workers are more concerned about, as well as the degree of influence of various numerical indicators, so as to guide journals to improve academic quality and expand the influence of journal platforms and academic influence. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0019] Figure 1 It is a flow chart of the new media influence evaluation method of scientific and technological journals provided by the present invention; Figure 2 It is a structural schematic diagram of the new media influence evaluation system of scientific and technological journals provided by the present invention; Figure 3 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0020] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0021] It should be noted that, in the description of the embodiments of the present invention, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "include one..." do not exclude the existence of other identical elements in the process, method, article or device including the elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to the specific circumstances.

[0022] In addition, "and / or" means at least one of the connected objects, and the character " / " generally means that the previously and subsequently associated objects are in an "or" relationship.

[0023] Combine the following Figure 1-Figure 3 The present invention describes a method and system for evaluating the new media influence of scientific and technological journals provided in an embodiment of the present invention.

[0024] Figure 1 : is a flow chart of the method for evaluating the new media influence of scientific and technological journals provided by the present invention, such as Figure 1 As shown, including but not limited to the following steps: Step 101: Collect basic indicator data of the new media platform of the scientific journal, and standardize the basic indicator data to generate standardized indicator data; the new media platform includes multiple social media platforms opened by the journal, and the official website platform of the journal.

[0025] (1) Data collection: Use web crawler tools or third-party data monitoring platforms to obtain basic indicator data of new media platforms of scientific journals.

[0026] (2) Basic indicator data of new media platforms: The basic indicator data of new media platforms are divided into two categories. The first category is the social media platforms opened by the journal, such as WeChat public accounts, Douyin, Xiaohongshu, etc. The corresponding basic indicator data include the number of fans, reading volume, number of likes, number of reposts, number of comments, etc.; the second category is the official website platform of the journal, and the basic indicator data include the number of visits, number of independent visitors, number of pages per visit, number of page views, etc.

[0027] (3) Normalize the basic indicator data to generate standardized indicator data: Use the maximum and minimum normalization data preprocessing method to map the basic indicator data to the specified interval [0,1] to eliminate the dimensional differences between different features. The formula is:

[0028] in: x For the original data ，x min and x max are the minimum and maximum values ​​of the indicator respectively. The index data is standardized.

[0029] Step 102: Based on the exponential decay function, the data weight of the standardized indicator data is corrected according to the time node to generate the final indicator data.

[0030] Specifically, according to the timeliness characteristics of information in communication, the exponential decay function is used to assign time weights to data at different time nodes. The formula is: ; in, is the time weight, The larger it is, the smaller the weight; The time interval between the data generation time and the current time, the unit can be month; is the attenuation coefficient, which can be adjusted according to the data characteristics to determine the optimal value.

[0031] Based on the time weight, the standardized indicator data is adjusted to generate the final indicator data, and the formula is: =

[0032] in, The final indicator data.

[0033] Step 103: Construct a hierarchical evaluation model for the influence of new media, and determine the subjective weight of the new media platform and the fusion weight of the indicator that combines the subjective weight of the new media platform and the objective weight of the indicator.

[0034] (1) The structure of the hierarchical evaluation model of new media influence: The hierarchical evaluation model includes a target layer and a platform layer. The target layer is used to output the new media influence of cross-platform scientific journals. The platform layer includes multiple new media platforms, and each new media platform has multiple indicators.

[0035] (2) Use the analytic hierarchy process to determine the M Subjective weight of new media platforms : Considering the importance of different new media platforms, the analytic hierarchy process (AHP) was used. Since the communication value of different platforms (such as journal official websites, WeChat public accounts, Douyin, and Xiaohongshu) varies greatly, it is necessary to rely on experts to make subjective judgments on the platform weights. For example, the official website focuses more on the dissemination of academic papers (depth), while the WeChat public account focuses on the dissemination of popular science knowledge (breadth).

[0036] Construct a judgment matrix by comparing the importance of the platforms pairwise (1-9 scale method) through experts. .

[0037]

[0038] in: For expert judgment M New media platforms and N The impact of new media platforms on the target (new media influence), M The value range is 1~ N; when M=N hour, ， It means that both platforms are equally important; ,express M Compare N Slightly more important; ,express M Compare N Extremely important; The value range is 1~9.

[0039] The weight vector is calculated using the eigenvector method and normalized by column:

[0040] Take the average by row and calculate the average value of each row to get the initial weight vector:

[0041] Calculate the weight vector and the maximum eigenvalue of the matrix λ max , calculate the subjective weight of the normalized feature vector: ; in, For the M The subjective weight of new media platforms.

[0042] Consistency check, calculation of consistency index CI * =(λ max - n ) / ( n -1), calculate CR = CI * / RI ,in RI is the random consistency index, which can be obtained by looking up the table. CR<0.1 , then the test is passed, otherwise the judgment matrix needs to be adjusted.

[0043] (3) According to Article M The first new media platform i This scientific journal j The information entropy of each indicator is used to calculate the objective weight :Using the entropy method for objective weighting, the data dispersion of indicators within the platform (such as the number of fans and the number of reposts) can objectively reflect the value of the indicator. For example, if the data difference of the "number of likes" of a WeChat public account is large, a higher weight will be given.

[0044] Each indicator in the platform is standardized and converted into a probability distribution to obtain ,in i Indicates i This journal, i The value range is 1~ n; j Indicates i This journal j indicators, j The value range is 1~ m , Indicates the time weight correction after i This journal j The value of an indicator.

[0045] Calculate information entropy, ,like =0, definition =0.

[0046] Calculate objective weights, .

[0047] (4) Calculation of subjective weight With objective weight The difference of the indicators is calculated and the average difference of all indicators is determined to set the power function exponent according to the average difference.

[0048] In the process of weighting the new media communication influence indicators of scientific and technological journals, the introduction of nonlinear combination strategies to integrate subjective and objective weights can solve the problem that the linear superposition of subjective and objective weights cannot reflect the complex relationship between indicators (such as threshold effect and synergy effect). The dynamic adaptive power function is used to amplify the influence of key indicators (such as the number of high entropy forwarding) and suppress the integration of subjective and objective weights of low-value indicators (such as the number of fans).

[0049] For each indicator, calculate the difference between subjective and objective weights , take the average value of all indicator differences , introducing the power function exponent , dynamically adjust the fusion ratio of subjective and objective weights according to the difference:

[0050] in: is the sensitivity coefficient (usually 10), is the benchmark difference (can be set to 0.1), when > hour, Approaching 0, it is more dependent on objective weights; when < hour, Approaching 1, it relies more on subjective weights.

[0051] (5) Based on the power function index, set the preset power function for subjective weight With objective weight Perform nonlinear fusion to generate fusion weights .

[0052] The preset power function is specifically:

[0053] in, is the power function exponent, n for i The maximum value of .

[0054] Step 104: Based on the structure and weight setting of the hierarchical evaluation model, the final indicator data is used to calculate the single-platform influence and cross-platform influence of the scientific journal.

[0055] Calculate the i This scientific journal is in M The influence of a single platform under a new media platform :

[0056] in, is the normalized indicator data of the final indicator data, and L is the total number of indicators; According to i The single-platform influence of this scientific journal on each new media platform and the subjective weight of the new media platform are used to calculate the cross-platform influence : ; in, K Indicates the number of platform layers.

[0057] Based on the content of the above embodiment, after calculating the single-platform influence of the scientific journal, it also includes: using the preset influence parameter (HowNet CI, i.e. HowNet influence index) to verify the correlation of the cross-platform influence and calculate the correlation coefficient; according to the range of the correlation coefficient, determine whether the calculation result of the cross-platform influence meets the requirements; if it does not meet the requirements, adjust the indicators and / or indicator weights.

[0058] Specifically, the Pearson correlation coefficient between the cross-platform influence of computing technology journals and CNKI CI r :

[0059] in: For the i The cross-platform influence of this scientific journal; For the i The CNKI impact index of this scientific journal; is the average cross-platform impact of all scientific journals, ; is the average value of the CNKI impact index of all journals, .

[0060] When the Pearson correlation coefficient r >0.7, indicating strong correlation, indicating that the selected indicators are relatively reasonable. S Highly correlated with academic influence; when 0.3≤ r ≤0.7, indicating moderate correlation; r <0.3 indicates weak correlation, which may be due to unreasonable selection of indicator parameters. In this case, it is necessary to readjust the parameters and then calculate again. P ≤0.05 , This indicates that the correlation is statistically significant. P> 0.05, indicating that the correlation is not significant and that there is no linear correlation between the variables.

[0061] In order to explain the above technical solution more clearly, taking the scientific and technological journals in the water conservancy industry as an example, according to the influence index (CloutIndex, CI) published in the "Annual Report of Chinese Academic Journal Impact Factors (Natural Science and Engineering Technology·2024 Edition)", some journals that did not adopt new media platforms or had not been updated for a long time were screened out, and a total of 18 representative water conservancy science and technology journals in Q1 and Q2 areas were selected for analysis, and the relationship between their new media influence and influence index CI was calculated.

[0062] WeChat public accounts, Tik Tok, Xiaohongshu, and Weibo are classified as WeChat-type platforms, and official websites are classified as website platforms.

[0063] Taking May to October 2024 as the research period, the WeChat platform indicator data (basic indicator data) was searched through web crawlers, Qingbo platform and other means to obtain the total number of tweets, total number of readings, total number of likes, total number of reposts, and estimated number of fans on the WeChat platform. Because most of the 18 selected water conservancy science and technology journals have not opened Douyin, Xiaohongshu, and Weibo accounts, the calculation process is simplified and only the WeChat public account indicator data is counted, as shown in Table 1.

[0064] Taking May to October 2024 as the research period, the website platform indicator data is found through web crawlers, similarweb and other means to obtain indicator data such as monthly visits to the website platform, monthly independent visitors, number of pages visited per time, and number of page views.

[0065] The Min-Max normalization data preprocessing method is used to linearly map the new media indicator data to the specified interval [0,1] to eliminate the dimensional differences between different features and form standardized indicator data.

[0066] Due to space constraints, the following calculations take "People's Yangtze River" and "Water Conservancy and Hydropower Express" as examples to calculate the total reading volume and monthly visit volume indicators respectively.

[0067] Normalize the “Total Reading Volume” indicator in WeChat public accounts: The maximum value = 46888, the minimum value = 725, the normalized value of the total reading volume of "People's Yangtze River" = (19985-725) / (46888-725) = 0.4172, and the normalized value of the total reading volume of "Water Conservancy and Hydropower Express" = (26969-725) / (46888-725) = 0.5685.

[0068] Normalize the "monthly visits" indicator in the website indicator: The maximum value = 33714, the minimum value = 224, the normalized value of monthly visits to "People's Yangtze River" = (1723-224) / (33714-224) = 0.0448, and the normalized value of monthly visits to "Water Conservancy and Hydropower Express" = (511-224) / (33714-224) = 0.0086.

[0069] Table 1 Evaluation index table of academic influence of water conservancy science and technology journals

[0070] According to the timeliness of information in communication, an exponential decay function is used to assign weights to data at different time nodes. , because the time dimension selected for each indicator in this example is consistent, so in this calculation =0, =1.

[0071] After normalization, the data Multiply by the time weight , get the adjusted index value, that is, the final index data = Total number of readers of People's Yangtze River =0.417, total number of readings of Water Resources and Hydropower News =0.569; Monthly visits of People's Yangtze River =0.0448, monthly visits of Water Resources and Hydropower News .

[0072] Considering the importance of different new media platforms, the analytic hierarchy process (AHP) was used for weighting, and 5 industry experts were invited to judge the strategic positioning of the platforms. The content of the expert judgment matrix (1-9 degrees) is shown in Table 2: Table 2 Contents of the expert judgment matrix

[0073] Among them: "1" means that the two elements have exactly the same impact on the target; "3" means that the former is slightly more important than the latter, but the difference is small. The results show that experts believe that official website data is slightly more important than WeChat public account data.

[0074] The eigenvector weights are calculated as T (Through consistency test, CR=0<0.1), where the feature weight of the official website , the feature weight of WeChat public account .

[0075] The entropy method is used for objective weighting, because the data dispersion of indicators within the platform (such as the number of fans and the number of reposts) can objectively reflect the value of the indicator. Weighting is based on the degree of data dispersion. The greater the degree of variation (the smaller the entropy value), the higher the indicator differentiation and the greater the weight.

[0076] Each indicator in the platform is standardized and converted into a probability distribution to obtain : Total number of readings of People's Yangtze River =0.0982, total number of readings of Water Resources and Hydropower News =0.1338; Monthly visits of "People's Yangtze River" =0.0126, monthly visits to Water Resources and Hydropower News 0.0024.

[0077] Calculate the information entropy of each journal’s internal indicators. ,Calculated, the information entropy of the index data of the official website of scientific and technological journals, the number of visits, the number of unique visitors, the number of pages visited each time, and the number of page views are 0.7822, 0.7669, 0.9096, and 0.8498 respectively; the information entropy of the total number of tweets, the total number of readings, the total number of likes, the total number of reposts, and the estimated number of fans in the WeChat public account are 0.8362, 0.7865, 0.7666, 0.7535, and 0.7459 respectively. Among them, the entropy value of the estimated number of fans is the smallest, and the greater the degree of variation, the greater the entropy value.

[0078] Calculate the objective weight of each indicator, The objective weights of the total number of tweets, total number of readings, total number of likes, total forwardings, and estimated number of fans in WeChat public accounts are 0.4339, 0.4254, 0.5046, and 0.4714, respectively; the objective weights of the total number of tweets, total number of readings, total number of likes, total forwardings, and estimated number of fans in WeChat public accounts are 0.4638, 0.4363, 0.4253, 0.4180, and 0.4138, respectively.

[0079] In the process of weighting the new media communication influence indicators of scientific and technological journals, a nonlinear combination strategy is introduced to integrate subjective and objective weights. For each indicator, the difference between subjective and objective weights is calculated:

[0080] Take the average of all indicator differences =0.1753.

[0081] Introducing the power function exponent , dynamically adjust the fusion ratio of subjective and objective weights according to the difference =0.6798 in: is the sensitivity coefficient (usually 10), is the benchmark difference (can be set to 0.1), when > hour, Approaching 0, it is more dependent on objective weights; when < hour, Approaching 1, it relies more on subjective weights.

[0082] The preset power function is used to perform nonlinear fusion of subjective and objective weights:

[0083] The calculations show that:

[0084] Integrate platform weights, indicator weights, and time decay factors to generate dynamic evaluation results, and calculate the single-platform influence and cross-platform influence (i.e., new media influence) of the i-th scientific journal.

[0085] The calculation results in this embodiment are shown in Table 3: Table 3 shows the calculation results of new media influence

[0086] SPSS 27 software was used to conduct a correlation analysis on the CI values ​​of new media influence and academic influence of scientific journals, and the Pearson correlation was 0.540. * (“*” indicates significant correlation at the 0.05 level), P =0.021<0.05, indicating that the correlation is statistically significant.

[0087] Table 4 is the result of linear regression analysis of new media influence and CI value

[0088] Taking the new media influence of cross-platform scientific journals as the independent variable and the CI value as the dependent variable, the correlation is observed, as shown in Table 4. The results of linear regression analysis show that there is a strong positive correlation between new media influence and CI value (p<0.05).

[0089] The new media influence of the Water Conservancy Science and Technology Journal calculated according to the above process meets the design requirements, is significantly correlated with the academic influence, and passes the linear regression test, indicating that it can be used to evaluate the new media influence of scientific and technological journals, and to quantitatively analyze the relationship between various new media indicators and academic influence. It can be used to guide journal publishing, adjust journal operation strategies, and ultimately enhance the academic influence of journals.

[0090] Compared with the prior art, the present invention provides a method for calculating the new media influence of scientific and technological journals. The basic indicator data of specific new media is obtained by using a web crawler or a third-party data monitoring platform, and the derived basic indicator data is normalized by using the Min-Max normalized data preprocessing method. At the same time, the timeliness of information in communication is considered, and an exponential decay function is introduced to weight the data at different time nodes, and the normalized data is corrected for time decay. The nonlinear combination weighting method (subjective weighting + objective weighting) is used to determine the weights of each media platform and indicator data, and finally a cross-platform scientific and technological journal new media influence calculation formula is obtained. The rationality of the calculation formula is verified by performing a correlation analysis between the new media influence calculation formula and the journal CNKI composite influence CI. At the same time, the corresponding indicator weights can be adjusted according to the different types of scientific and technological journals (such as popular science journals and academic journals), so that the new media influence calculation formula of scientific and technological journals is always related to the CNKI composite influence CI, so as to achieve the purpose of evaluation. This patent achieves the purpose of formulating different new media influence evaluation methods for different types of scientific and technological journals, solves the problems of data uncorrelation across new media platforms and weak matching between new media influence and journal influence, and at the same time, through the nonlinear fusion of two types of weights, the analytic hierarchy process (AHP) and the entropy method, it not only retains the professionalism of subjective judgment, but also incorporates the objectivity of data, balances subjective and objective information, improves the scientific nature of weights, reduces the bias of the calculated new media influence of scientific and technological journals, and realizes the dynamic, adaptable and high-precision evaluation requirements, solves the problems of incomplete new media influence evaluation, and enables it to evaluate the size of the new media influence of cross-platform scientific and technological journals from the perspective of HowNet influence, which is of great concern to scientific and technological journal workers, as well as the degree of influence of various numerical indicators, to guide journals to improve academic quality, expand the influence of publication platforms and academic influence.

[0091] To sum up, the present invention has the advantages of comprehensive information collection, balanced subjective and objective information, good adaptability, high precision, and strong correlation. It can comprehensively and truly reflect the influence of new media of scientific and technological journals, and can be used as a reference to guide journal publishing and enhance the academic influence of journals.

[0092] On the other hand, the present invention also provides a new media influence evaluation system for scientific and technological journals. Figure 2 is a schematic diagram of the structure of the new media influence evaluation system for scientific and technological journals provided by the present invention. Figure 2 As shown, the system includes: a data collection module 210, a data correction module 220, a hierarchical evaluation model construction module 230 and an influence evaluation module 240.

[0093] The data collection module 210 is used to collect basic indicator data of the new media platform of the scientific journal, and to perform standardization processing on the basic indicator data to generate standardized indicator data; the new media platform includes multiple social media platforms opened by the journal, and the official website platform of the journal; A data correction module 220 is used to correct the data weight of the standardized indicator data according to the time node based on the exponential decay function to generate the final indicator data; A hierarchical evaluation model construction module 230 is used to construct a hierarchical evaluation model of new media influence, and determine the subjective weight of the new media platform, and the fusion weight of the indicator that combines the subjective weight of the new media platform and the objective weight of the indicator; the hierarchical evaluation model includes a target layer and a platform layer, the target layer is used to output the new media influence of cross-platform scientific journals, and the platform layer includes multiple new media platforms, and each new media platform has multiple indicators; The influence evaluation module 240 is used to calculate the single-platform influence and cross-platform influence of scientific journals based on the structure and weight setting of the hierarchical evaluation model and using the final indicator data.

[0094] It should be noted that the system for evaluating the new media influence of scientific journals provided in the embodiment of the present invention can execute the method for evaluating the new media influence of scientific journals described in any of the above embodiments during specific operation, which will not be elaborated in this embodiment.

[0095] Figure 3 is a schematic diagram of the structure of the electronic device provided by the present invention, such as Figure 3 As shown, the electronic device may include: a processor 310, a communication interface 320, a memory 330 and a communication bus 340, wherein the processor 310, the communication interface 320 and the memory 330 communicate with each other through the communication bus 340. The processor 310 may call the logic instructions in the memory 330 to execute the new media influence evaluation method of scientific and technological journals.

[0096] On the other hand, the present invention also provides a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium, and the computer program includes program instructions. When the program instructions are executed by a computer, the computer can execute the new media influence evaluation method of scientific and technological journals provided in the above-mentioned embodiments.

[0097] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the new media influence evaluation method for scientific and technological journals provided in the above-mentioned embodiments.

[0098] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0099] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for evaluating the new media influence of scientific and technological journals, characterized in that: include: Collect basic indicator data of new media platforms of scientific and technological journals, and standardize the basic indicator data to generate standardized indicator data; the new media platforms include multiple social media platforms opened by the journals, as well as the official website platform of the journals; Based on the exponential decay function, the data weight of the standardized indicator data is modified according to the time node to generate the final indicator data; Construct a hierarchical evaluation model of new media influence, and determine the subjective weight of the new media platform, as well as the fusion weight of the indicator that combines the subjective weight of the new media platform and the objective weight of the indicator; the hierarchical evaluation model includes a target layer and a platform layer, the target layer is used to output the new media influence of cross-platform scientific journals, and the platform layer includes multiple new media platforms, and each new media platform has multiple indicators; Based on the structure and weight setting of the hierarchical evaluation model, the final indicator data is used to calculate the single-platform influence and cross-platform influence of scientific journals.

2. The method for evaluating the new media influence of scientific and technological journals according to claim 1 is characterized in that: After using the final indicator data to calculate the single-platform influence and cross-platform influence of scientific journals, it also includes: Use preset influence parameters to verify the correlation of cross-platform influence and calculate the correlation coefficient; Determine whether the calculation results of cross-platform influence meet the requirements based on the range of the correlation coefficient; In case of non-compliance with the requirements, the indicators and / or indicator weights shall be adjusted.

3. The method for evaluating the new media influence of scientific and technological journals according to claim 1 is characterized in that: Collect the basic indicator data of the new media platform of scientific and technological journals, and standardize the basic indicator data to generate standardized indicator data, including: Use web crawler tools or third-party data monitoring platforms to obtain basic indicator data of new media platforms of scientific journals; basic indicator data of social media platforms include: number of fans, number of readings, number of likes, number of reposts and number of comments; basic indicator data of journal official website platforms include number of visits, number of unique visitors, number of pages visited per time and number of page views; The basic indicator data are normalized to generate standardized indicator data.

4. The method for evaluating the new media influence of scientific and technological journals according to claim 1 is characterized in that: Based on the exponential decay function, the standardized indicator data is weighted according to the time node to generate the final indicator data, including: Use exponential decay function to assign time weights to data at different time nodes; Based on the time weight, the standardized indicator data is adjusted to generate the final indicator data.

5. The method for evaluating the new media influence of scientific and technological journals according to claim 1 is characterized in that: Determine the subjective weight of the new media platform and the integrated weight of the indicator that integrates the subjective weight of the new media platform and the objective weight of the indicator, including: Use the analytic hierarchy process to determine the M Subjective weight of new media platforms and, pursuant to M The first new media platform i This scientific journal j The information entropy of each indicator is used to calculate the objective weight ; Calculating subjective weights With objective weight The difference of the indicators is calculated, and the average difference of all indicators is determined to set the power function index according to the average difference; Based on the power function exponent, set the preset power function for subjective weight With objective weight Perform nonlinear fusion to generate fusion weights .

6. The method for evaluating the new media influence of scientific and technological journals according to claim 5 is characterized in that: The preset power function is: ； in, is the power function exponent, n for i The maximum value of .

7. The method for evaluating the new media influence of scientific and technological journals according to claim 5 is characterized in that: Based on the structure and weight setting of the hierarchical evaluation model, the final indicator data is used to calculate the single-platform influence and cross-platform influence of scientific journals, including: Calculate the i This scientific journal is in M The influence of a single platform under the new media platform: in, is the normalized indicator data of the final indicator data, and L is the total number of indicators; According to i The cross-platform influence of this scientific journal is calculated based on the single-platform influence of each new media platform and the subjective weight of the new media platform.

8. A new media influence evaluation system for scientific and technological journals, characterized by: include: A data collection module is used to collect basic indicator data of the new media platform of scientific and technological journals, and to standardize the basic indicator data to generate standardized indicator data; the new media platform includes multiple social media platforms opened by the journal, and the official website platform of the journal; A data correction module is used to correct the data weight of the standardized indicator data according to the time node based on the exponential decay function to generate the final indicator data; A hierarchical evaluation model construction module is used to construct a hierarchical evaluation model of new media influence, and determine the subjective weight of the new media platform, and the fusion weight of the indicator that integrates the subjective weight of the new media platform and the objective weight of the indicator; the hierarchical evaluation model includes a target layer and a platform layer, the target layer is used to output the new media influence of cross-platform scientific and technological journals, and the platform layer includes multiple new media platforms, and each new media platform has multiple indicators; The impact evaluation module is used to calculate the single-platform influence and cross-platform influence of scientific journals based on the structure and weight setting of the hierarchical evaluation model and using the final indicator data.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the steps of the method for evaluating the new media influence of scientific journals as described in any one of claims 1 to 7 are implemented.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for evaluating the new media influence of scientific journals as described in any one of claims 1 to 7 are implemented.

Images