CN112434933A - Quantitative evaluation method for media influence of public social platform - Google Patents
Quantitative evaluation method for media influence of public social platform Download PDFInfo
- Publication number
- CN112434933A CN112434933A CN202011313264.4A CN202011313264A CN112434933A CN 112434933 A CN112434933 A CN 112434933A CN 202011313264 A CN202011313264 A CN 202011313264A CN 112434933 A CN112434933 A CN 112434933A
- Authority
- CN
- China
- Prior art keywords
- index
- weight
- media
- evaluated
- text
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 91
- 238000011158 quantitative evaluation Methods 0.000 title claims abstract description 10
- 238000011156 evaluation Methods 0.000 claims abstract description 17
- 230000002996 emotional effect Effects 0.000 claims description 21
- 238000013278 delphi method Methods 0.000 claims description 16
- 230000000694 effects Effects 0.000 claims description 13
- 230000008909 emotion recognition Effects 0.000 claims description 9
- 230000005540 biological transmission Effects 0.000 claims description 4
- 230000007935 neutral effect Effects 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 238000012552 review Methods 0.000 claims description 3
- 230000006855 networking Effects 0.000 claims 3
- 238000013139 quantization Methods 0.000 abstract description 2
- 230000006870 function Effects 0.000 description 5
- 230000008451 emotion Effects 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 230000015572 biosynthetic process Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000000644 propagated effect Effects 0.000 description 1
- 238000011002 quantification Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Educational Administration (AREA)
- Operations Research (AREA)
- Marketing (AREA)
- Game Theory and Decision Science (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a quantitative evaluation method for media influence of a public social platform, which comprises the following steps: (1) acquiring a Delphi weight of each primary index and each secondary index for evaluating the influence of the media; (2) collecting each secondary index of each media account to be evaluated; (3) calculating the entropy weight value of each secondary index according to the entropy weight method; (4) and (4) integrating the entropy weight method weight and the Delphi weight method, respectively weighting each primary index and each secondary index, and calculating to obtain the influence of each media account to be evaluated. The method and the device can solve the technical problems of evaluation result deviation caused by the fact that the evaluation indexes do not utilize text content, the timeliness of the evaluation indexes is not considered, the evaluation indexes cannot be quantized and the quantization is not accurate.
Description
Technical Field
The invention belongs to the field of internet propagation, and particularly relates to a quantitative evaluation method for media influence of a public social platform.
Background
The rapid development of the internet and the mobile internet greatly promotes the diversification of media and changes the format of the media, and new network media become mainstream, wherein the influence of a public social platform is gradually increased. For example, microblogs and twitter are typical representatives in public social platforms, attract a large number of various users to join, and produce massive data. The social contact platforms have strong information transmission capability to unspecified audiences and strong public influence; on the other hand, the information is continuously output to a specific audience such as a concerned person, and a deeper information positive feedback effect is achieved; in addition, various types of information are mixed, which provides great challenge to the management of network space. The method is particularly important for scientifically and objectively quantitatively evaluating the media influence of the public social platform, enhancing the management and guidance of high-influence media and further influencing the specific crowds and radiating the specific crowds to wider crowds through the media influence; therefore, the method for evaluating the influence of the media has important practical significance and certain theoretical significance.
In the existing media influence assessment method, basic means for realizing quantification mainly comprise basic quantity indexes and network relations, wherein the basic quantity indexes mainly comprise a number of messages, a number of followers, a number of forwarding numbers and the like, the network relations generally construct a user network by using user relations, and influence of each node is calculated by using a complex network correlation theory or a link relation. The conventional media influence quantitative evaluation system construction method is constructed based on basic quantity indexes or a certain processing mode based on basic data; there are also methods based on machine learning and related methods based on network structure relationships.
However, the prior art has the following problems:
the first problem, the media impact assessment index only uses the original basic quantity data or the network structure, but does not use the text data; if only the number of texts sent, the number of praise and the like are considered, the content level of the article is not related, or the comment content of the user and the like are not related;
the second problem is that the timeliness problem of the media influence evaluation index is not considered, and part of the index system cannot adapt to the current actual situation;
the third problem is that the media influence evaluation index cannot be quantized and has no operability;
the fourth problem is that there is a problem in quantifying the media impact assessment index, resulting in a large deviation in the assessment result.
Disclosure of Invention
Aiming at the defects or improvement requirements of the prior art, the invention provides a quantitative evaluation method for media influence of a public social platform, and aims to solve the technical problems of evaluation result deviation caused by the fact that evaluation indexes do not utilize text content, the timeliness of the evaluation indexes is not considered, the evaluation indexes cannot be quantized and the quantization is inaccurate.
To achieve the above object, according to one aspect of the present invention, there is provided a method for quantitatively evaluating media influence of a public social platform, comprising the steps of:
(1) obtaining a Delphi weight W of each primary index and each secondary index for evaluating the media influence of the public social platformkAnd
wherein k is [1, 3 ]]，j∈[1，10]；
The first-level index is a comprehensive evaluation index of the influence of the media, and comprises productivity, transmission capacity and identity; the secondary index is a data record of the media, can be obtained by operation data statistics of a public social platform and is subordinate to the primary index;
(2) carrying out data acquisition on N media accounts to be evaluated of a public social platform to obtain each media account P to be evaluatednOf each secondary index fn，jWhere N is [1, N ]]；
(3) The value f of each secondary index of the N media accounts to be evaluated of the public social platform acquired in the step (2)n，jCalculating the weight of entropy weight of each secondary index according to the entropy weight method
(4) According to the entropy weight value of each secondary index calculated in the step (3)
And the Delphi weight W of each primary index and each secondary index obtained in the step (1)kAnd
and (3) each media account P to be evaluated acquired in step (2)nOf each secondary index fn，jIn combination with a predetermined entropyThe weight of the weight index and the weight of the Delphi method index are added, each weight of the entropy weight method and the Delphi method weight and each value of the secondary index are cumulatively weighted, and the obtained weighted sum is used as each media account P to be evaluatednInfluence of (I)n。
Preferably, the secondary index comprises emotion recognition, the emotion recognition is used for measuring the recognition degree of an audience to the content of the text sent by the media account, and the more audience comments consistent with the emotional state expressed by the content of the text sent by the media account, the higher the emotion recognition is.
Preferably, the value f of said emotional consentn，10The method specifically comprises the following steps:
wherein f isn，1Is the media account number PnThe amount of the hair text; ciIs the media account number PnNumber of reviews of the ith issue; v. oficIs the media account number PnThe c comment of the ith sentence of (1);
the ith text diIs denoted as si＝S(di) C.c.comment of the ith texticIs denoted as sic＝S(vic) (ii) a And S (x) is an emotional state function, the return value of the function is 0, 1 or 2, different emotional states are represented, wherein 0 represents negative direction, 1 represents neutral, 2 represents positive direction, and parameter x represents a text to be calculated.
Preferably, the obtaining of each media account P to be evaluatednOf each secondary index fn，jThe method comprises the following specific steps:
(2-1) acquiring the nth media account P to be evaluatednAmount of hair text fn，1The number of attendees fn，6And an attention amount fn，8；
(2-2) for the nth media account number P to be evaluatednF of (a)n，1For each text, the praise number cl of the collection cut-off time of each text is obtainediNumber of comments criAnd forwarding number cfiCount all fn，1Praise amount f of textn，2Amount of comments fn，3And a forwarding quantity fn，5Where i ∈ [1, f ]n，1]；
(2-3) for the nth media account number P to be evaluatednF of (a)n，1For each text, obtaining the hot text index of each text, and counting the hot text amount f of all the texts with the hot text index exceeding a specified threshold valuen，4；
(2-4) according to the nth media account number P to be evaluatednNumber of attendees fn，6The number of the attendees who send out the text and the number of the comments are counted, and the number f of the active attendees whose attendee activity index exceeds a specified threshold value is countedn，7；
(2-5) counting the nth media account P to be evaluatednMentioned quantity f in all the text of the public social platformn，9；
(2-6) reading the nth media account P to be evaluated according to the audiencenThe emotional state expressed by each comment after the text is sent, and the number of the two emotional states which are consistent is counted as the value f of the emotional identityn，10。
Preferably, in step (2-2)
The amount of like fn，2In particular to
The evaluation amount fn，3In particular to
The forwarding amount fn，5In particular to
Preferably, the thermal energy f in step (2-3)n，4Refers to the index of hot text HiExceeds a threshold value HtThe article number of (1) is specifically:
wherein d isiThe ith text representing the media account number,
heat index H of the ith textiThe method specifically comprises the following steps:
Hi＝α1cri+α2cfi+(1-α1-α2)cli
wherein alpha is1As a weight of the number of comments, α2Is the weight of the forwarding number, (1-alpha)1-α2) Is the weight of praise number and has alpha1、α2∈[0，1]，0≤α1+α2≤1。
Preferably, the number of active attendees f in steps (2-4)n，7Index of activity of person concerned AaExceeds a specified threshold AtThe number of the concerned persons in (1) is specifically:
wherein u isaThe a-th person of interest is represented,
the attention person activity index refers to the statistic t1To t2The weighted average of the number of texts and the number of comments of the attendee, the a-th attendee activity index AaThe method specifically comprises the following steps:
wherein a is ∈ [1, f ]n，6]Beta is the weight of the number of the texts of the concerned person, 1-beta is the weight of the number of the comments of the concerned person, and beta belongs to [0, 1 ∈]，
Respectively at t for the a-th attendee2、t1The number of the messages sent at the moment,
respectively at t for the a-th attendee2、t1Number of comments at time.
Preferably, the value f of each secondary index in step (3)n，jEntropy weight method of
The method specifically comprises the following steps:
wherein EjThe entropy of the jth secondary index is represented,
Pnjthe value representing the jth secondary index is a proportion,
f′n，jindicating Min-Max normalization of the value of the j-th secondary index,
preferably, in the step (4), each medium to be evaluated is calculated by directly adopting the secondary indexesBody account number PnInfluence of (I)nThe method comprises the following steps:
(4-1) using the Delphi method weight W of each first-level index obtained in the step (1)kEntropy weight method weight value of each secondary index calculated in the step (3)
And the Delphi weight value of each secondary index obtained in the step (1)
Weighting respectively to obtain the comprehensive entropy weight of each secondary index
And the integrated Delphi weight
Weighting the two indexes respectively by using preset entropy weight method index weight and Delphi method index weight to obtain a comprehensive weight w of each secondary indexjThe method specifically comprises the following steps:
wherein
Alpha is an entropy weight method index weight value, 1-alpha is a Delphi index weight value, and alpha belongs to [0, 1]]；
(4-2) Using the comprehensive weight w of each secondary indexjFor each media account P to be evaluated acquired in the step (2)nOf each secondary index fn，jWeighting is carried out, and each media account P to be evaluated is obtained after the weighted sum of all secondary indexes is obtainednInfluence of (I)nThe method specifically comprises the following steps:
preferably, in the step (4), each media account P to be evaluated is calculated by directly adopting the primary indexnInfluence of (I)nThe method comprises the following steps:
(4' -1) entropy weight value of each secondary index calculated in the step (3)
And the Delphi weight value of each secondary index obtained in the step (1)
For each media account P to be evaluated acquired in the step (2)nOf each secondary index fn，jWeighting, weighting the weighted sum of each secondary index by using a preset entropy weight method index weight and a preset Delphi method index weight, and summing to obtain each media account P to be evaluatednValue F of the primary index ofn，kThe method specifically comprises the following steps:
wherein alpha is an entropy weight method index weight, 1-alpha is a Delphi index weight, and alpha belongs to [0, 1 ];
(4' -2) using the Delphi weight W of each first-level index obtained in the step (1)kFor each primary index value Fn，kWeighting is carried out, and the weighted sum of all the first-level indexes is obtained to obtain each media account P to be evaluatednInfluence of (1) onnThe method specifically comprises the following steps:
in general, compared with the prior art, the above technical solution contemplated by the present invention can achieve the following beneficial effects:
(1) the invention provides a quantitative evaluation index of media influence, which is designed aiming at a public social platform according to media and data characteristics of the public social platform and based on objectivity, acquirability, computability and universality principles and in combination with the aspects of the formation of the media influence of the public social platform, the effective propagation of the media of the public social platform and the influence of the media of the public social platform on audiences; particularly, emotion recognition indexes are designed, through a text emotion analysis technology, the text content of the media account is analyzed from a microscopic level, the influence of the thought and the viewpoint of the media account is evaluated, the significance of the influence based on general surface data is surpassed, and the influence of media of a public social platform can be quantitatively evaluated more reasonably.
(2) The invention provides a method for determining the weight of each index by combining a Delphi method and an entropy weight method, and further calculates to obtain the influence of the media of the public social platform, thereby not only judging the influence of the media of the public social platform from a subjective level, but also evaluating the influence of the media of the public social platform on audiences from objective data, avoiding the purely subjective judgment and avoiding the influence of the data too frequently, and therefore, the method for combining the Delphi method and the entropy weight method is adopted to obtain more reasonable quantitative evaluation of the influence.
Drawings
FIG. 1 is a flow chart of the method of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail with reference to the following embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention. In addition, the technical features involved in the embodiments of the present invention described below may be combined with each other as long as they do not conflict with each other.
A method for quantitatively evaluating media influence of a public social platform comprises the following steps:
(1) obtaining a Delphi weight W of each first-level index for evaluating the media influence of a public social platformkAnd the Delphi weight of each secondary index
Wherein k is [1, 3 ]]，j∈[1，10]；
The first-level index is a comprehensive evaluation index of the influence of the media, and comprises productivity, transmission capacity and identity; the secondary index is a data record of the media, can be obtained by operation data statistics of a public social platform, and is subordinate to the primary index. Specifically, the primary index corresponds to the secondary index.
The secondary indexes corresponding to the productivity of the primary indexes comprise a text sending amount, a praise amount, a comment amount and a hot text amount; the secondary indexes corresponding to the primary index propagation force comprise forwarding amount, the number of the attendees, the number of active attendees and the amount of attendees; and the secondary indexes corresponding to the primary index identity degree comprise the mentioned amount and the emotion identity degree.
The weight W of the Delphi methodkAnd
obtained by the delphi method.
The primary index is determined based on the formation of the media influence of the public social platform, the effective propagation of the media of the public social platform and the influence of the media of the public social platform on the audience; the influence is mainly formed by content, namely a text, the productivity of the media of the public social platform is reflected, the text volume evaluates the performance of the productivity on volume, and the praise volume, the appraisal volume and the hot text volume evaluate the performance of the productivity on quality; the effective propagation mainly depends on the attention people, and the effective propagation is propagated to other users through the attention and forwarding of the attention people, so that the propagation force of the media of the public social platform is reflected; the influence on the audience comprises macroscopic index data, namely the mentioned quantity, and microscopic influence degree, namely emotional acceptance, on other users, and the acceptance of the media of the social public platform.
The value of the secondary index is made according to the following principle:
the value of the secondary indicator is based on objective data;
the value of the secondary index is automatically obtained, namely the data is obtained by an automatic means without intervention of manpower;
the value of the secondary index is directly or indirectly calculated, namely the data is finally presented as a numerical type;
the value of the secondary index is strong in universality, namely, the data of all media under the public social platform is provided.
(2) Carrying out data acquisition on N media accounts to be evaluated of a public social platform to obtain each media account P to be evaluatednOf each secondary index fn，jWhere N is [1, N ]]；
Acquiring each media account P to be evaluatednOf each secondary index fn，jThe method comprises the following specific steps:
(2-1) acquiring the nth media account P to be evaluatednAmount of hair text fn，1The number of attendees fn，6And an attention amount fn，8；
The data acquisition mode is acquired through an Application Programming Interface (API) of a public social platform, or through self-development of a web crawler program, or through a mode of combining the two.
(2-2) for the nth media account number P to be evaluatednF of (a)n，1For each text, the praise number cl of the collection cut-off time of each text is obtainediNumber of comments criAnd forwarding number cfiCount all fn，1Praise amount f of textn，2Amount of comments fn，3And a forwarding quantity fn，5Where i ∈ [1, f ]n，1]；
The method comprises the steps that the ending time is acquired for each text, and is the time when the variation amplitude of the praise number, the comment number and the forwarding number of each text is smaller than a preset threshold value;
the amount of like fn，2In particular to
The evaluation amount fn，3In particular to
The forwarding amount fn，5In particular to
(2-3) for the nth media account number P to be evaluatednF of (a)n，1For each text, obtaining the hot text index of each text, and counting the hot text amount f of all the texts with the hot text index exceeding a specified threshold valuen，4；
The index of the hot text is the number cr of comments on each starting text at the collection cutoff timeiForwarding number cfiAnd like number cliCarrying out weighted sampling;
heat index H of the ith textiThe method specifically comprises the following steps:
Hi＝α1cri+α2cfi+(1-α1-α2)cli
wherein alpha is1As a weight of the number of comments, α2Is the weight of the forwarding number, (1-alpha)1-α2) Is the weight of praise number and has alpha1、α2∈[0，1]，0≤α1+α2Less than or equal to 1; preferred value of alpha1＝0.4、α2＝0.5；
The thermal text fn，4Index of heat index HiThe number of articles exceeding the threshold Ht is specifically:
wherein d isiThe ith text representing the media account number,
preferred value Ht＝100；
(2-4) according to the nth media account number P to be evaluatednNumber of attendees fn，6The number of the attendees who send out the text and the number of the comments are counted, and the number f of the active attendees whose attendee activity index exceeds a specified threshold value is countedn，7；
The attention person activity index refers to the statistic t1To t2The weighted average of the number of texts and the number of comments of the attendee, the a-th attendee activity index AaThe method specifically comprises the following steps:
wherein a is ∈ [1, f ]n，6]Beta is the weight of the number of the texts of the concerned person, 1-beta is the weight of the number of the comments of the concerned person, and beta belongs to [0, 1 ∈]，
Respectively at t for the a-th attendee2、t1The number of the messages sent at the moment,
respectively at t for the a-th attendee2、t1Number of comments at the time; preferred values β ═ 0.7, t2-t1Is 7 days;
the number of active attendees fn，7Index of activity of person concerned AaExceeds a specified threshold AtThe number of the concerned persons in (1) is specifically:
wherein u isaThe a-th person of interest is represented,
the threshold value is preferably At＝0.5；
(2-5) counting the nth media account P to be evaluatednMentioned quantity f in all the text of the public social platformn，9The method specifically comprises the following steps:
wherein L (T)b，Pn) Text T representing a public social platformbIncludes a media account number PnBy searching for "P" in the text of the public social platformn"is available, B is the number of all texts of the public social platform;
(2-6) reading the nth media account P to be evaluated according to the audiencenThe emotional state expressed by each comment after the text is sent, and the number of the two emotional states which are consistent is counted as the value f of the emotional identityn，10；
The emotional state is represented by a function S (x), the return value of the function is 0, 1 or 2, different emotional states are represented, wherein 0 represents negative direction, 1 represents neutral, 2 represents positive direction, and x represents a text to be calculated; the emotional state can be obtained through an emotional tendency analysis function provided by the intelligent open platform;
the value f of the emotion recognitionn，10The method specifically comprises the following steps:
wherein C isiIs the media account number PnNumber of reviews of the ith issue; v. oficIs the media account number PnThe c comment of the ith sentence of (1); the ith text diIs expressed assi＝S(di) C.c.comment of the ith texticIs denoted as sic＝S(vic)；
The emotion recognition degree is used for measuring the recognition degree of the audience to the text contents of the media account, the text contents of the media account are analyzed from a microscopic level through a text emotion analysis technology, and the thought and the viewpoint of the media account are evaluated to be consistent with the thought and the viewpoint expressed after the audience receives the text contents. The index quantifies the influence of the media account on the thought and the view of the audience, and reflects the influence of the media account in a more essential way.
(3) The values f of all secondary indexes of the N media accounts to be evaluated of the public social platform obtained in the step (2)n，jCalculating the value f of each secondary index according to the entropy weight methodn，jEntropy weight method of
The method specifically comprises the following steps:
wherein EjThe entropy of the jth secondary index is represented,
Pnjthe value representing the jth secondary index is a proportion,
f′n，jindicating Min-Max normalization of the value of the j-th secondary index,
(4) according to the entropy weight value of each secondary index calculated in the step (3)
And the Delphi method weight W of each first-level index obtained in the step (1)kAnd the Delphi weight of each secondary index
And (3) each media account P to be evaluated acquired in step (2)nOf all secondary indexes fn，jAnd cumulatively weighting each entropy weight, each Delphi weight and each secondary index value by combining preset entropy weight index weight and Delphi weight index weight, wherein the obtained weighted sum is used as each media account P to be evaluatednInfluence of (I)n；
When directly adopting the secondary indexes to calculate the nth media account P to be evaluatednInfluence of (I)nThe method comprises the following steps:
(4-1) using the Delphi method weight W of each first-level index obtained in the step (1)kEntropy weight method weight value of each secondary index calculated in the step (3)
And the Delphi weight value of each secondary index obtained in the step (1)
Weighting respectively to obtain the comprehensive entropy weight of each secondary index
And the integrated Delphi weight
Then the data are respectively indicated by a preset entropy weight methodWeighting the standard weight and the Delphi method index weight to obtain a comprehensive weight w of each secondary indexj；
The comprehensive weight w of each secondary indexjThe method specifically comprises the following steps:
wherein
Alpha is an entropy weight method index weight value, 1-alpha is a Delphi index weight value, and alpha belongs to [0, 1]]；
(4-2) Using the comprehensive weight w of each secondary indexjFor each media account P to be evaluated acquired in the step (2)nOf each secondary index fn，jWeighting is carried out, and each media account P to be evaluated is obtained after the weighted sum of all secondary indexes is obtainednInfluence of (I)n；
Each media account P to be evaluatednInfluence of (I)nThe method specifically comprises the following steps:
when the nth media account P to be evaluated is calculated by directly adopting the primary indexnInfluence of (I)nThe method comprises the following steps:
(4' -1) entropy weight value of each secondary index calculated in the step (3)
And the Delphi weight value of each secondary index obtained in the step (1)
For each media account P to be evaluated acquired in the step (2)nOf each secondary index fn，jWeighting, and using the preset entropy weight method index weightWeighting the weighted sum of each secondary index by the value and the Delphi index weight value respectively, and summing to obtain each media account P to be evaluatednValue F of the primary index ofn，k；
Each media account P to be evaluatednValue F of the primary index ofn，kThe method specifically comprises the following steps:
wherein alpha is an entropy weight method index weight, 1-alpha is a Delphi index weight, and alpha belongs to [0, 1 ];
(4' -2) using the Delphi weight W of each first-level index obtained in the step (1)kFor each primary index value Fn，kWeighting is carried out, and the weighted sum of all the first-level indexes is obtained to obtain each media account P to be evaluatednInfluence of (1) onn；
Each media account P to be evaluatednInfluence of (I)nThe method specifically comprises the following steps:
the influence calculation of the media account combines a Delphi method and an entropy weight method, not only contains subjective evaluation, but also contains objective data, weight values are respectively determined for the first-level index and the second-level index, and the influence of the media account can be more reasonably evaluated by adopting a mode of combining the first-level index and the second-level index.
Preferably, when the influence of the media account of the public social platform in a specified time period needs to be evaluated,obtaining the values f of all secondary indexes of the media accounts of the public social platform in the step (2)n，jWherein the amount of the message fn，1F, amount of praisen，2Amount of comments fn，3Thermal energy fn，4A forwarding amount fn，5The number of attendees fn，6Number of active attendees fn，7Attention amount fn，8And the mentioned amount fn，9The value f of emotion recognition is the incremental value of the corresponding index in a specified time periodn，10And calculating according to the texts and the comments in the specified time period.
It will be understood by those skilled in the art that the foregoing is only a preferred embodiment of the present invention, and is not intended to limit the invention, and that any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (10)
1. A method for quantitatively evaluating media influence of a public social platform is characterized by comprising the following steps:
(1) obtaining a Delphi weight W of each primary index and each secondary index for evaluating the media influence of the public social platformkAnd
wherein k is [1, 3 ]]，j∈[1，10]；
The first-level index is a comprehensive evaluation index of the influence of the media, and comprises productivity, transmission capacity and identity; the secondary index is a data record of the media, can be obtained by operation data statistics of a public social platform and is subordinate to the primary index;
(2) carrying out data acquisition on N media accounts to be evaluated of a public social platform to obtain each media account P to be evaluatednOf each secondary index fn，jWhere N is [1, N ]]；
(3) The value f of each secondary index of the N media accounts to be evaluated of the public social platform acquired in the step (2)n，jAccording to the entropy weight methodCalculating the weight of entropy weight method of each secondary index
(4) According to the entropy weight value of each secondary index calculated in the step (3)
And the Delphi weight W of each primary index and each secondary index obtained in the step (1)kAnd
and (3) each media account P to be evaluated acquired in step (2)nOf each secondary index fn，jAnd cumulatively weighting each entropy weight, each Delphi weight and each secondary index value by combining preset entropy weight index weight and Delphi weight index weight, wherein the obtained weighted sum is used as each media account P to be evaluatednInfluence of (I)n。
2. The method as claimed in claim 1, wherein the secondary index includes emotional recognition, and the emotional recognition is used to measure the recognition degree of the audience to the content of the media account sent by the user; the more audience comments are consistent with the emotional state expressed by the text content, the higher the emotion recognition degree is.
3. The method of claim 2, wherein the sentiment recognition value f is a quantitative evaluation of the media influence of the social networking services platformn，1sThe method specifically comprises the following steps:
wherein f isn，1Is the media account number PnThe amount of the hair text; ciIs thatMedia account number PnNumber of reviews of the ith issue; v. oficIs the media account number PnThe c comment of the ith sentence of (1);
the ith text diIs denoted as si＝S(di) C.c.comment of the ith texticIs denoted as sic＝S(vic) (ii) a And S (x) is an emotional state function, the return value of the function is 0, 1 or 2, different emotional states are represented, wherein 0 represents negative direction, 1 represents neutral, 2 represents positive direction, and parameter x represents a text to be calculated.
4. The method as claimed in claim 1, wherein the method for quantitatively evaluating media influence of the social contact platform comprises the step of obtaining each media account P to be evaluatednOf each secondary index fn，jThe method comprises the following specific steps:
(2-1) acquiring the nth media account P to be evaluatednAmount of hair text fn，1The number of attendees fn，6And an attention amount fn，8；
(2-2) for the nth media account number P to be evaluatednF of (a)n，1For each text, the praise number cl of the collection cut-off time of each text is obtainediNumber of comments criAnd forwarding number cfiCount all fn，1Praise amount f of textn，2Amount of comments fn，3And a forwarding quantity fn，5Where i ∈ [1, f ]n，1]；
(2-3) for the nth media account number P to be evaluatednF of (a)n，1For each text, obtaining the hot text index of each text, and counting the hot text amount f of all the texts with the hot text index exceeding a specified threshold valuen，4；
(2-4) according to the nth media account number P to be evaluatednNumber of attendees fn，6The number of the spotters in (1) andnumber of comments, number of active attendees f whose statistical attendee activity index exceeds a specified thresholdn，7；
(2-5) counting the nth media account P to be evaluatednMentioned quantity f in all the text of the public social platformn，9；
(2-6) reading the nth media account P to be evaluated according to the audiencenThe emotional state expressed by each comment after the text is sent, and the number of the two emotional states which are consistent is counted as the value f of the emotional identityn，1s。
5. The method of claim 4, wherein in the step (2-2), the media influence of the social networking platform is quantitatively evaluated
The amount of like fn，2In particular to
The evaluation amount fn，3In particular to
The forwarding amount fn，5In particular to
6. The method of claim 4, wherein the thermal vector f in step (2-3) is evaluated quantitativelyn，4Refers to the index of hot text HiExceeds a threshold value HtThe article number of (1) is specifically:
wherein d isiThe ith text representing the media account number,
heat index H of the ith textiThe method specifically comprises the following steps:
Hi＝α1cri+α2cfi+(1-α1-α2)cli
wherein alpha is1As a weight of the number of comments, α2Is the weight of the forwarding number, (1-alpha)1-α2) Is the weight of praise number and has alpha1、α2∈[0，1]，0≤α1+α2≤1。
7. The method of claim 4, wherein the number of active attendees f in steps (2-4) is set asn，7Index of activity of person concerned AaExceeds a specified threshold AtThe number of the concerned persons in (1) is specifically:
wherein u isaThe a-th person of interest is represented,
the attention person activity index refers to the statistic t1To t2The weighted average of the number of texts and the number of comments of the attendee, the a-th attendee activity index AaThe method specifically comprises the following steps:
wherein a is ∈ [1, f ]n，6]Beta is the weight of the number of the texts of the concerned person, 1-beta is the weight of the number of the comments of the concerned person, and beta belongs to [0, 1 ∈]，
Respectively at t for the a-th attendee2、t1The number of the messages sent at the moment,
respectively at t for the a-th attendee2、t1Number of comments at time.
8. The method of claim 1, wherein the value f of each secondary index in step (3) is determined by a quantitative evaluation method of the media influence of the social networking services platformn，jEntropy weight method of
The method specifically comprises the following steps:
wherein EjThe entropy of the jth secondary index is represented,
Pnjthe value representing the jth secondary index is a proportion,
f′n，jindicating Min-Max normalization of the value of the j-th secondary index,
9. a process as claimed in claim 1The method for quantitatively evaluating the media influence of the public social platform is characterized in that in the step (4), each media account P to be evaluated is calculated by directly adopting a secondary indexnInfluence of (I)nThe method comprises the following steps:
(4-1) using the Delphi method weight W of each first-level index obtained in the step (1)kEntropy weight method weight value of each secondary index calculated in the step (3)
And the Delphi weight value of each secondary index obtained in the step (1)
Weighting respectively to obtain the comprehensive entropy weight of each secondary index
And the integrated Delphi weight
Weighting the two indexes respectively by using preset entropy weight method index weight and Delphi method index weight to obtain a comprehensive weight w of each secondary indexjThe method specifically comprises the following steps:
wherein
Alpha is an entropy weight method index weight value, 1-alpha is a Delphi index weight value, and alpha belongs to [0, 1]]；
(4-2) Using the comprehensive weight w of each secondary indexjFor each media account P to be evaluated acquired in the step (2)nOf each secondary index fn，jWeighting to obtain the weighted sum of all secondary indexes to obtain each media to be evaluatedAccount number PnInfluence of (I)nThe method specifically comprises the following steps:
10. the method for quantitatively evaluating media influence of a public social platform as claimed in claim 1, wherein in the step (4), each media account P to be evaluated is calculated by directly adopting a primary indexnInfluence of (I)nThe method comprises the following steps:
(4' -1) entropy weight value of each secondary index calculated in the step (3)
And the Delphi weight value of each secondary index obtained in the step (1)
For each media account P to be evaluated acquired in the step (2)nOf each secondary index fn，jWeighting, weighting the weighted sum of each secondary index by using a preset entropy weight method index weight and a preset Delphi method index weight, and summing to obtain each media account P to be evaluatednValue F of the primary index ofn，kThe method specifically comprises the following steps:
wherein alpha is an entropy weight method index weight, 1-alpha is a Delphi index weight, and alpha belongs to [0, 1 ];
(4' -2) using the Delphi weight W of each first-level index obtained in the step (1)kFor each primary index value Fn，kWeighting is carried out, and the weighted sum of all the first-level indexes is obtained to obtain each media account P to be evaluatednInfluence of (1) onnThe method specifically comprises the following steps:
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011313264.4A CN112434933A (en) | 2020-11-20 | 2020-11-20 | Quantitative evaluation method for media influence of public social platform |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011313264.4A CN112434933A (en) | 2020-11-20 | 2020-11-20 | Quantitative evaluation method for media influence of public social platform |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112434933A true CN112434933A (en) | 2021-03-02 |
Family
ID=74694466
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011313264.4A Pending CN112434933A (en) | 2020-11-20 | 2020-11-20 | Quantitative evaluation method for media influence of public social platform |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112434933A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113139735A (en) * | 2021-04-30 | 2021-07-20 | 福建广电网络集团股份有限公司 | Propagation analysis method and device for county-level converged media center |
| CN113887584A (en) * | 2021-09-16 | 2022-01-04 | 同济大学 | Emergency traffic strategy evaluation method based on social media data |
| NL2027700B1 (en) * | 2021-03-03 | 2022-09-22 | Wenzhou Institute Of Tech | Method for Evaluating MicroBlog Influence Based on Emotional Identity |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20170037709A (en) * | 2015-09-25 | 2017-04-05 | 충북대학교 산학협력단 | Method and System for determination of social network hot topic in consideration of users influence and time |
| CN106875277A (en) * | 2017-01-16 | 2017-06-20 | 星云纵横（北京）大数据信息技术有限公司 | A kind of determination methods of social media account influence power |
| WO2020000847A1 (en) * | 2018-06-25 | 2020-01-02 | 中译语通科技股份有限公司 | News big data-based method and system for monitoring and analyzing risk perception index |
| CN111340396A (en) * | 2020-03-24 | 2020-06-26 | 中国传媒大学 | Method for evaluating transmission power of converged media |
-
2020
- 2020-11-20 CN CN202011313264.4A patent/CN112434933A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20170037709A (en) * | 2015-09-25 | 2017-04-05 | 충북대학교 산학협력단 | Method and System for determination of social network hot topic in consideration of users influence and time |
| CN106875277A (en) * | 2017-01-16 | 2017-06-20 | 星云纵横（北京）大数据信息技术有限公司 | A kind of determination methods of social media account influence power |
| WO2020000847A1 (en) * | 2018-06-25 | 2020-01-02 | 中译语通科技股份有限公司 | News big data-based method and system for monitoring and analyzing risk perception index |
| CN111340396A (en) * | 2020-03-24 | 2020-06-26 | 中国传媒大学 | Method for evaluating transmission power of converged media |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| NL2027700B1 (en) * | 2021-03-03 | 2022-09-22 | Wenzhou Institute Of Tech | Method for Evaluating MicroBlog Influence Based on Emotional Identity |
| CN113139735A (en) * | 2021-04-30 | 2021-07-20 | 福建广电网络集团股份有限公司 | Propagation analysis method and device for county-level converged media center |
| CN113887584A (en) * | 2021-09-16 | 2022-01-04 | 同济大学 | Emergency traffic strategy evaluation method based on social media data |
| CN113887584B (en) * | 2021-09-16 | 2022-07-05 | 同济大学 | Emergency traffic strategy evaluation method based on social media data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112434933A (en) | Quantitative evaluation method for media influence of public social platform | |
| CN108304867B (en) | Information popularity prediction method and system for social network | |
| WO2016180127A1 (en) | Network performance evaluation method and system | |
| CN107527240B (en) | System and method for identifying public praise marketing effect of operator industry product | |
| CN114091443B (en) | Network information propagation index system construction and evaluation method based on deep learning | |
| CN109829114B (en) | Topic popularity prediction system and method based on user behaviors | |
| Cole et al. | The European gonococcal antimicrobial surveillance programme (Euro-GASP) appropriately reflects the antimicrobial resistance situation for Neisseria gonorrhoeae in the European Union/European Economic Area | |
| Röchert et al. | Opinion-based homogeneity on YouTube: Combining sentiment and social network analysis | |
| CN104484359B (en) | A kind of the analysis of public opinion method and device based on social graph | |
| CN109636467A (en) | A kind of comprehensive estimation method and system of the internet digital asset of brand | |
| CN109657962A (en) | A kind of appraisal procedure and system of the volume assets of brand | |
| CN116468300A (en) | Army general hospital discipline assessment method and system based on neural network | |
| Berkhout et al. | No borders, no bias? Comparing advocacy group populations at the national and transnational levels | |
| CN112836137B (en) | Character network support degree computing system and method, terminal, equipment and storage medium | |
| Willetts et al. | Does remarriage matter? The well-being of adolescents living with cohabiting versus remarried mothers | |
| CN105303194A (en) | Power grid indicator system establishing method, device and computing apparatus | |
| CN110136001A (en) | A kind of data processing method, calculates equipment and storage medium at device | |
| Shin et al. | Learning through online participation: A longitudinal analysis of participatory budgeting using Big Data indicators | |
| WO2021134944A1 (en) | Mobile news client-based evaluation method and system therefor | |
| CN112396313B (en) | Method for optimizing telephone sales performance by using smart watch | |
| Chan et al. | Detecting concurrent mood in daily contact networks: an online participatory cohort study with a diary approach | |
| Xia et al. | Analysis and prediction of telecom customer churn based on machine learning | |
| CN114969560A (en) | Crisis information pushing method and system based on event situation and user cognition | |
| Jin et al. | Research on the evaluation model of rural information demand based on big data | |
| Triantafillidou et al. | Ε-Government, dialogic communication principles and social media engagement: an empirical investigation of Greek smart cities |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |