CN106471494B - Program, apparatus and method for analyzing effect of promotion site on user's psychological state transition - Google Patents
Program, apparatus and method for analyzing effect of promotion site on user's psychological state transition Download PDFInfo
- Publication number
- CN106471494B CN106471494B CN201580034569.2A CN201580034569A CN106471494B CN 106471494 B CN106471494 B CN 106471494B CN 201580034569 A CN201580034569 A CN 201580034569A CN 106471494 B CN106471494 B CN 106471494B
- Authority
- CN
- China
- Prior art keywords
- psychological
- score
- state
- comment text
- mental state
- 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.)
- Expired - Fee Related
Links
- 230000007704 transition Effects 0.000 title claims abstract description 59
- 230000000694 effects Effects 0.000 title claims abstract description 30
- 238000000034 method Methods 0.000 title claims description 39
- 230000006996 mental state Effects 0.000 claims abstract description 92
- 230000001737 promoting effect Effects 0.000 claims abstract description 20
- 230000009471 action Effects 0.000 claims description 15
- 230000006870 function Effects 0.000 abstract description 4
- 238000010586 diagram Methods 0.000 description 14
- 230000008569 process Effects 0.000 description 13
- 230000008859 change Effects 0.000 description 7
- 230000006399 behavior Effects 0.000 description 6
- 238000004891 communication Methods 0.000 description 4
- 238000012552 review Methods 0.000 description 4
- 230000005540 biological transmission Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 208000003443 Unconsciousness Diseases 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 230000001174 ascending effect Effects 0.000 description 1
- 230000003542 behavioural effect Effects 0.000 description 1
- 230000001149 cognitive effect Effects 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000008451 emotion Effects 0.000 description 1
- 230000003340 mental effect Effects 0.000 description 1
- 230000003924 mental process Effects 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 230000035790 physiological processes and functions Effects 0.000 description 1
- 230000008433 psychological processes and functions Effects 0.000 description 1
- 238000011002 quantification Methods 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Tourism & Hospitality (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
There is provided a program for analyzing the effect of a promotion site for a product or service on a target keyword, which effect acts on a user's mental state transition, based on a set of comment texts transmitted by each contributor. The program causes the computer to function as: a psychological state determiner that outputs a psychological state of psychological keywords included in the comment text transmitted by each contributor; a score memory that stores, for each promotion site address, a score set for each psychological state; and a score updater that instructs the score memory to increase the score of the mental state of the standard comment text including the site address in a case where the mental state is different between the standard comment text and one or more previous comment texts, and/or that instructs the score memory to increase the score of the mental state of one or more subsequent comment texts in a case where the mental state is different between the standard comment text including the site address and one or more subsequent comment texts. The program enables identification of the mental state transition caused by the promotional site address.
Description
Technical Field
The present invention relates to a technique for analyzing comment texts posted to a communication site server such as an SNS (Social Networking Service) site server.
The present application claims priority rights under the paris convention for japanese patent application No. 2014-145050, filed on 7/15/2014, which is incorporated herein by reference according to PCT regulation 20.6.
Background
In recent years, many unspecified persons actively post their own comments (text information) through the SNS site server. The SNS site server discloses comment texts thrown by the users of the group to many other users in the group. Typical examples of the SNS are Facebook (registered trademark), Twitter (registered trademark), Google + (registered trademark), and Mixi (registered trademark), which are also called mini blog sites.
The comment text transmitted from the user often reflects the psychological state of the user in a conscious or unconscious manner. In particular, in marketing, it is preferable to analyze such a comment reflecting the user's psychological state generated by the product or service. The specific method for analyzing the user comment is as follows: comment texts made by users and the user's profile information are obtained, and then the content trends of a plurality of comment texts are analyzed according to each profile item. The method is based on the fact that: the content of the mentioned comment text about the product or the like may differ according to the user profile information about, for example, generation, sex, and interest.
As an example associated with the above-described technology, patent document 1 discloses a technology of analyzing the effect of a banner advertisement on a web page by using an online behavior log of a user. As a behavioral log, it is possible to employ, for example, the number of clicks on banner advertisements or a transition to purchasing behavior performed after clicking on an advertiser's site. The advertiser sets the link destination to identify the banner advertisement provided on the link source web page to identify which banner advertisement is active.
Further, for example, patent document 2 discloses a technique of collecting a posted article that mentions entertainment content and then retrieving reputation information on the entertainment content. Reputation information in this technique is defined as a numerical value that evaluates the positive/negative impression given by an advertisement.
Further, for example, patent document 3 discloses a technique of analyzing an advertisement effect using an AIDMA model, which is an economic model of purchasing behavior. General knowledge in economics: the user's psychological state concerning purchasing behavior has a tendency to sequentially change to stages of a (attention), I (interest), D (desire), M (memory), and a (action). In the technique described in patent document 3, one stage of the AIDMA model is assigned for each type of advertisement/action (e.g., TV advertisement, magazine advertisement, e-mail, web page, click banner, bookmark, get coupon, etc.), and then their number (number of TV advertisements, number of click banners, etc.) is measured, which quantifies the influence of the advertisement on each stage of the AIDMA model.
Further, for example, patent document 4 discloses a technique of collecting past submissions of a specific user in an SNS and then estimating profile information (for example, about generation and gender) of the user based on features of words appearing in these submissions. The techniques can estimate profile information for any user.
Reference list
Patent document
Patent document 1: japanese patent laid-open publication No. 2012-088994
Patent document 2: japanese patent No. 4359787
Patent document 3: japanese patent laid-open publication No. 2003-044738
Patent document 4: japanese patent laid-open publication No. 2013-196070
Disclosure of Invention
Problems to be solved by the invention
Even in the case where a news article or an SNS comment text causes access to a purchase site, the technique described in patent document 1 has difficulty in identifying a web page including the news article or the comment text. That is, it is impossible to identify the relationship between the web page delivered by the third person and the site of the actual store, which makes quantification of the influence on the online promotion site difficult.
Further, the reputation of the promotion site determined by the technique described in patent document 2 does not have to be directly linked to the purchasing behavior of the user. For example, even a promotional site that gives a positive impression cannot enable a user to purchase a product unless the site provides sufficient and specific description of the product. Conversely, if a site is impressive to the user, even a promotional site that gives a negative impression may cause a product to be purchased.
Further, the technique described in patent document 3 does not assume a technique of estimating the psychological state of the AIDMA model based on the comment text given to the SNS. Also, the technique described in patent document 4 does not assume a temporal change in profile information.
In the face of such a situation, the inventors of the present invention considered the possibility of finding a promotion site having a contribution to the transition of the psychological state of the user based on the comment text on the product or service posted to the SNS. Further, the possibility of accumulating a score representing the degree of contribution to the mental state transition of the user regarding the product or service for each promotion site has been considered. It is assumed that these scores enable a determination of which type of promotional site is effective in marketing.
It is, therefore, an object of the present invention to provide a program, apparatus and method for analyzing the effect of a promotion site on a user's mental state transition using comment text transmitted by the user.
Means for solving the problems
According to the present invention, there is provided a program executed by a computer installed on an apparatus that analyzes an effect of a promotion site for a product or service on a target keyword, which effect acts on a psychological state transition of a user, based on a set of comment texts transmitted by each contributor, the program causing the computer to function as:
a psychological keyword dictionary through which one or more psychological keywords are registered for each psychological state in advance;
a comment text obtainer that obtains, for each contributor, comment texts each including the target keyword and arranged in time series;
a psychological state determiner that outputs a psychological state for which the included psychological keyword is registered, in a case where the obtained comment text of the contributor includes the psychological keyword registered to the psychological keyword dictionary;
a score memory that stores, for each promotion site address, a score set for each psychological state; and
a score updater that instructs the score memory to increase the score of the mental state of the standard comment text if the mental state between the standard comment text including the site address and one or more previous comment texts generated before the standard comment text is different, and/or that instructs the score memory to increase the score of the mental state of one or more subsequent comment texts generated after the standard comment text if the mental state between the standard comment text including the site address and the one or more subsequent comment texts is different.
The program is characterized in that: enabling identification of the mental state transition caused by the promotional site address.
As an embodiment of the program executed by the computer according to the present invention, it is preferable that the psychological keyword dictionary sets the psychological states according to an AIDMA (attention, interest, expectation, memory, action) model, and holds one or more registered psychological keywords corresponding to the target keyword for each psychological state.
As another embodiment of the program executed by the computer according to the present invention, it is also preferable that:
assigning each mental state a value that increases in the order of A, I, D, M and A;
the transition of the time-series mental states is set to the mental state values arranged according to the time series; and is
The score updater sets each of the time-series arranged values as a moving average derived through a predetermined range.
As another embodiment of the program executed by a computer according to the present invention, it is also preferable that the score updater sets the weight wb of the psychological state of the standard comment text and the weight wa of the psychological state of the subsequent comment text to values different from each other, and increases the score by using the weights.
As another embodiment of the program executed by a computer according to the present invention, it is also preferable that the score updater sets a weight wb of the psychological state of the standard comment text and a weight wa of the psychological state of the subsequent comment text, sets the weight wb to a different value for each psychological state, and sets the weight wa to a different value for each psychological state, and increases the score by using the weights.
As another embodiment of the program executed by the computer according to the present invention, it is also preferable that:
setting in advance a weight wb of each psychological state in the psychological states aid m (attention, interest, expectation, memory) to a value larger than a weight wb of the psychological state a' (action); and is
The weight wa of each of the psychological states aid m (attention, interest, expectation, memory) is set in advance to a value smaller than the weight wa of the psychological state a' (action).
As another embodiment of the program executed by a computer according to the present invention, it is also preferable that the score updater sets the smaller weight wa when a posting time interval between the standard comment text and one or more subsequent comment texts generated after the standard comment becomes longer in a case where a psychological state between the standard comment and the subsequent comment text is different.
As another embodiment of the program executed by the computer according to the present invention, it is also preferable that:
the target keyword is a keyword based on the product or the service, and
the site address is a URL (uniform resource locator) of the promotional site for the product or the service.
As another embodiment of the program executed by a computer according to the present invention, it is also preferable that the program further causes the computer to function as a promotion effect notifier that transmits, for each site address, a score for each mental state stored in the score memory.
According to the present invention, there is also provided an apparatus for analyzing an effect of a promotion site for a product or service on a target keyword, which effect acts on a psychological state transition of a user, based on a set of comment texts transmitted by each contributor, and the apparatus comprising:
a psychological keyword dictionary through which one or more psychological keywords are registered for each psychological state in advance;
a comment text obtainer that obtains, for each contributor, comment texts each including the target keyword and arranged in time series;
a psychological state determiner that outputs a psychological state for which the included psychological keyword is registered, in a case where the obtained comment text of the contributor includes the psychological keyword registered to the psychological keyword dictionary;
a score memory that stores, for each promotion site address, a score set for each psychological state; and
a score updater that instructs the score memory to increase the score of the mental state of the standard comment text if the mental state between the standard comment text including the site address and one or more previous comment texts generated before the standard comment text is different, and/or that instructs the score memory to increase the score of the mental state of one or more subsequent comment texts generated after the standard comment text if the mental state between the standard comment text including the site address and the one or more subsequent comment texts is different.
The device is characterized in that: enabling identification of the mental state transition caused by the promotional site address.
According to the present invention, there is further provided a method performed by using an apparatus, which analyzes an effect of a promotion site for a product or service on a target keyword, which effect acts on a psychological state transition of a user, based on a set of comment texts transmitted by each contributor,
the device includes:
a psychological keyword dictionary through which one or more psychological keywords are registered for each psychological state in advance; and
a score memory that stores, for each promotion site address, a score set for each psychological state, and
the method comprises the following steps:
obtaining comment texts for each contributor, each of the comment texts including the target keyword and being arranged in a time series;
in a case where the obtained comment text of the contributor includes a psychological keyword registered to the psychological keyword dictionary, outputting a psychological state for which the included psychological keyword is registered; and
instructing the scoring memory to increase the score of the mental state of the standard comment text if the mental state between the standard comment text including the site address and one or more previous comment texts generated before the standard comment text is different, and/or instructing the scoring memory to increase the score of the mental state of the subsequent comment text(s) if the mental state between the standard comment text including the site address and one or more subsequent comment texts generated after the standard comment text is different.
The method is characterized in that: enabling identification of the mental state transition caused by the promotional site address.
Advantageous effects of the invention
The program, apparatus and method according to the present invention allow the use of comment text transmitted by a user to analyze the effect of a promotion site on the user's mental state transition.
Drawings
Presenting the attached drawings, wherein:
FIG. 1 is a schematic diagram illustrating one embodiment of a system including an apparatus according to the present invention;
FIG. 2 is a functional block diagram illustrating one embodiment of a psychological transition analysis device in accordance with the present invention;
fig. 3A, 3B, and 3C are schematic diagrams for explaining an example of comment text;
fig. 4 is a schematic diagram for explaining a first score updating process in the present invention;
fig. 5 is a schematic diagram for explaining a second score updating process in the present invention;
FIG. 6 is a diagram for explaining a first score updating process using weights in the present invention, and
fig. 7 is a schematic diagram for explaining a second score updating process using weights in the present invention.
Detailed Description
Illustrative embodiments of the invention will now be described with reference to the accompanying drawings.
Fig. 1 is a schematic diagram illustrating one embodiment of a system comprising a device according to the present invention.
As shown in fig. 1, connected to the internet is a psychological transition analysis apparatus 1. The psychological transition analysis device 1 is configured to communicate with the SNS site server 2 through the internet. The apparatus 1 can obtain the comment text transmitted by each contributor from the SNS site server 2 through an API (application programming interface). The API is a protocol interface adaptive to a function using an application service prepared according to a server type.
The psychological transition analysis apparatus 1 may accumulate the comment text in advance in the database. That is, the apparatus 1 may select communication with the SNS site server 2.
A third person who is not specified can use his/her own terminal 3 to transmit the comment text to the SNS site server 2 through the internet. The psychological transition analysis apparatus 1 is configured to analyze the psychological state transition of the contributor caused by the promotion site related to the product or service on the target keyword using a set of review papers transmitted by each contributor.
The target keyword is a keyword regarding a product or service. Also, in the set of comment texts, a comment text including a promotion site address on the product or service is mixed. The promotional site address is the URL of the promotional site.
(step S11) for example, the user sees a new site by using the terminal 3. Then, the user transmits the following comment text including the URL of the new site to the SNS site server 2.
"new project release for smartphone by α corporation. http:// news. html "
The psychological transition analysis device 1 obtains the above comment text thrown by the user. The apparatus 1 analyzes the psychological state reflected in the comment text about "smartphone of α corporation", thereby judging that the psychological state of the user changes to a psychological state having little "attention" to only the smartphone of α corporation.
(step S12) after that, the user sees, for example, a product introduction site, and then transmits the following comment text including the URL of the product introduction site to the SNS site server 2.
"I see the smartphone of the alpha company placed on the HP. http:// hp. html "
The psychological transition analysis device 1 obtains the above comment text thrown by the user. The apparatus 1 analyzes the psychological state reflected in the comment text about "smartphone of α corporation", thereby determining that the psychological state of the user changes to a psychological state in which the user has "interest" in the smartphone of α corporation.
As described above, when the psychological state of the user changes from the psychological state before seeing the site after seeing the promotion site, the apparatus 1 judges that the promotion site contributes to the psychological state transition. The accumulation of the determination results enables estimation of the effect of the promotion site on the transition of the mental state.
Fig. 2 is a functional block diagram illustrating an embodiment of a psychological transition analysis apparatus according to the present invention.
The psychological transition analysis apparatus 1 according to the present invention is configured to analyze the psychological state transition caused by the promotion site with respect to the target keyword using the comment text of each contributor. The apparatus 1 is configured to include a psychological keyword dictionary 101, a score memory 102, a comment text obtainer 11, a psychological state determiner 12, a score updater 13, and a promotion effect notifier 14 in addition to the communication interface. In addition to the communication interface, these functional units are embodied by executing corresponding programs on a computer installed on the apparatus. In addition, the flow in these functional units may be understood as a method for analyzing a psychological transition performed in the device.
(psychological keyword dictionary 101) the psychological keyword dictionary 101 is configured to record one or more psychological keywords for each psychological state in advance. According to the AIDMA model, the psychological state is considered to change with the following time series.
A cognitive stage: attention is drawn to (A) — (A)
An emotion stage: interest (I) —)
Expectation (D) - >
Memory (M) -memory
An action stage: action (A) -action
The AIDMAA model is a model for describing the psychological process of consumers on advertisements. This economic model of purchasing mental state transitions is able to estimate the mental process by tracking specific user opinions about target keywords such as target products or services in a time series.
The psychological keyword dictionary 101 records one or more psychological keywords regarding keywords such as "smartphone of α corporation" for each of the psychological states (A, I, D, M and a). For example,
the attention state: releases, commercials, new items, new products, … …;
the interest state is as follows: product line, brochure, HP, friends, … …;
the expected state is as follows: want, price, specification, design, … …;
and (3) memorizing the state: store, display, actual product, preview, … …; and
the action state is as follows: purchase, get, discard, model change … …
Registration is performed in a dictionary form including feature words with respect to the corresponding psychological states of the target keyword.
Note that the psychological keyword dictionary 101 is generally prepared manually. However, by using manually recorded psychological keywords as seeds (teacher data), statistical indexes (such as X) can be used2(chi-squared) value or Ackeck Information Criterion (AIC)) to determine characteristic words about the corresponding mental state.
(comment text obtainer 11) the comment text obtainer 11 is configured to obtain comment texts in time series from the SNS site server 2 by using a target keyword (for example, "smartphone of α corporation") as a retrieval key for each contributor (each user ID). The target keyword may be a name of a product or service. The obtained comment text is output to the psychological state determiner 12.
Fig. 3A, 3B, and 3C are schematic diagrams for explaining an example of comment text.
As shown in fig. 3A, various comment texts on a target keyword (smartphone of α corporation) are obtained for many users. In the comment text, a comment text including a promotion site address (URL) about a product or a service is mixed. According to the present invention, the promotion site address is included to enable an estimation of the effect of the promotion site on the mental state transition of the user.
According to fig. 3B, the comment text on the target keyword (smartphone of α corporation) is narrowed down to the comment text on the target keyword for the user AAA.
(mind state determiner 12) returning to fig. 2, the mind state determiner 12 is configured to output a mind state corresponding to the included mind keywords when the comment text of each contributor includes the mind keywords registered to the mind keyword dictionary. For example, by using comment text including "smartphone of α corporation" as a target keyword and "new item" as a psychological keyword, the psychological state determiner 12 can estimate that the user is in the state of attention (a). Also, based on the comment text including "smartphone of α corporation" as a target keyword and "commercial" as a psychological keyword, it can be estimated that the user is in the state of attention (a). Further, based on the comment text including "smartphone of α corporation" as the target keyword and "HP" as the psychological keyword, it can be estimated that the user is in the state of interest (I). Further, by using the comment text including "smartphone of α corporation" as the target keyword and "want" as the psychological keyword, the psychological state determiner 12 can estimate that the user is in the desired (D) state. Further, it can be estimated that the user is in a memory (M) state from the comment text including "smartphone of α corporation" as a target keyword and "shop" as a psychological keyword.
As shown in fig. 3C, the mental state is estimated for each comment text of the user AAA on the target keyword (smartphone of α corporation).
Alternatively, in a case where a plurality of psychological keywords are included in one comment text, a psychological state corresponding to the entire comment text may be determined based on the frequency of occurrence of each of the plurality of psychological keywords. Further, a discriminator (e.g., a support vector machine) may be used to determine a mental state based on the tendency of the words in the teacher data to appear. Furthermore, the physiological state can be analyzed by using the likelihood and the AIDMAs model.
New project release on smart phones by α corporation ";
"new item" ═ a, "issue" ═ a,
A＝2，I＝0，D＝0，M＝0，A＝0
thus, the probability of a is 100% (one hundred percent)
(scoring memory 102) the scoring memory 102 is configured to store a score for each mental state for each site address.
(score updater 13) the score updater 13 is configured to perform two main steps: a "psychological transition determination step" and a "score update step".
(psychological transition determination step) score updater 13 is adapted to estimate a psychological transition, which is data in which mental states are arranged in time series for each contributor. For example, the following psychological transitions are estimated;
A，A，I，A，I，I，D，I，D，D，M，M，M
here, each psychological transition is preferably assigned a series of values, each of which becomes larger in the order of A, I, D, M, A (a- > I- > D- > M- > a). This assignment of values represents the mental transitions as a time series of values, each of which corresponds to a mental state. The amount of values in the time series can be understood as an index indicating whether a transition of the next mental state occurs.
A＝0，I＝1，D＝2，M＝3
A，A，I，A，I，I，D，I，D，D，M，M，M
0，0，1，0，1，1，2，1，2，2，3，3，3
In such a psychological transition, the psychological states will naturally occur in a front-to-back order.
< modification of psychological transition by moving average > the score updater 13 is adapted to modify the time-series arranged values into a sequence of the values in ascending order as completely as possible. Specifically, it is preferable that the psychological state of the target comment is determined as an average of the psychological states of n comments adjacent in front and rear. Alternatively, the mental state of the target comment may be a moving average of previous comments within a predetermined range. The following is an example in the case of averaging two comments adjacent before and after.
A，A，I，A，I，I，D，I，D，D，M，M，M
0，0，1，0，1，1，2，1，2，2，3，3，3
0.3, 0.3, 0.4, 0.6, 1.1, 1.4, 1.6, 2, 2.2, 2.4, 2.6, 2.75, 3 are rounded to the integer- >)
0，0，0，1，1，1，1，2，2，2，2，3，3，3
A，A，A，I，I，I，I，D，D，D，D，M，M，M
< correction of psychological shift based on time difference of shift > comment text generally includes transmission time. Then, the psychological state determiner 12 is adapted to output a transmission time of the comment text including the psychological keyword together with a psychological state of the comment text. Score updater 13 may use two adjacent transmission times to record the elapsed time interval between mental states arranged in a time series.
The score updater 13 then weights each of the time-series arranged values in such a way that:
the longer the previous elapsed time interval, the smaller the weighting factor used to weight the value; and is
The shorter the preceding elapsed time interval, the larger the weighting factor used to weight the value.
Alternatively, each of the integers 0-4 corresponding to a mental state may be weighted by the estimated likelihood of the corresponding mental state. In the case where a is 10%, I is 70%, D is 20%, and M is 0%, the integers 0-3 are weighted as follows:
0*10％+1*70％+2*20％+3*0％＝1.1
(score update step) the score updater 13 is further adapted to perform one or both of the following two update steps, and then to give instructions to the score memory 102.
< standard update step > the standard update step is a step of: wherein, in the set of comment texts, when a psychological state between the standard comment text and one or more previous comment texts defined as comment texts generated before the standard comment text is different, a psychological state score of the standard comment text including a site address is increased.
< subsequent update step > the subsequent update step is a step of: wherein when the psychological state between the standard comment text and the subsequent comment text is different, the psychological state score of one or more subsequent comment texts defined as comment texts generated after the standard comment text is increased.
Specifically, in these steps, the AIDMA transition in the previous/subsequent comment text before/after the standard comment text is expressed as follows:
previous comment text- > Standard comment text:
db(a，i，d，m，a’)
standard comment text- > comment text later:
da(a，i，d，m，a’)
here, the value of each component having (a, i, d, m, a') is 0 or 1.
Fig. 4 is a schematic diagram for explaining a first score updating process in the present invention.
(step S41) the psychological state of the user AAA changes as follows:
"i happen to see many Commercials (CMs) of alpha corporation's smart phone. "(previous review text) - - > attention A
(browsing site: http:// hp. html)
"I see the smartphone of the alpha company placed on the HP. http:// hp. html "(standard comment text) - - > interest I
In this manner, by the viewing site: http:// hp. html, the mental state of user AAA changes from focus a to interest I. Therefore, the site http:// hp. html is judged to contribute to the transition of the mental state to interest I. When this determination is made, the score P (I) for interest I for site http:// hp. html is incremented by 1 in score store 102.
Previous comment text- > Standard comment text:
db(0，1，0，0，0)
(step S42) then, the psychological state of the user AAA changes as follows:
"I see the smartphone of the alpha company placed on the HP. http:// hp. html "(standard comment text) - - > interest I
"I want a company's smart phone. RT @ XXX "(review text later) - - > desired D
In this manner, by the viewing site: http:// hp. html, the mental state of user AAA changes from interest I to expectation D. Therefore, site http:// hp. html is judged to contribute to the transition of the mental state to the desired D. When this determination is made, the score P (D) for the expected D for site http:// hp. html is incremented by 1 in the score store 102.
Standard comment text- > comment text later:
da(0，0，1，0，0)
by accumulating db (a, i, d, m, a ') and da (a, i, d, m, a') as explained above, the score for each promotional site can be estimated ultimately. In the scoring memory 102 as shown in fig. 2, the following estimates are made:
html. the news site page a (http:// news. html) makes a large contribution to the mental state "focus (a)".
Product introduction site page B (http:// hp. html) has the largest contribution to the mental state action (A') "and the second largest contribution to the mental state expectation (D)".
Subject site page C (http:// aaa. html) has the largest contribution to the mental state "attention (A)" and the second largest contribution to the mental state "interest (I)" and mental state "expectation (D)".
Fig. 5 is a schematic diagram for explaining a second score updating process in the present invention.
(step S51) the psychological state of the user AAA changes as follows:
"new project release for smartphone by α corporation. http:// news. html "- - - > attention A
"commercial advertising for alpha's smart phones is interesting. "- - > interest I
In this manner, by the viewing site: http:// news. html, the mental state of user AAA changes from focus a to interest I. Therefore, the site http:// news. html is judged to contribute to the transition of the mental state to interest I. When this determination is made, the score P (I) for interest I for the site http:// news. html is incremented by 1 in the score store 102.
(step S52) then, the psychological state of the user AAA transitions as follows:
"commercial advertising for alpha's smart phones is interesting. "- - > interest I
"I see the smartphone of the alpha company placed on the HP. http:// hp. html "- - > interest I
At this time, even though through the viewing site: http:// hp. html, the user AAA mental state also does not change and maintains the state of interest I. Therefore, the scores are not updated in the score memory 102.
(step S53) then, the mental state of the user AAA changes as follows:
"I see the smartphone of the alpha company placed on the HP. http:// hp. html "- - > interest I
"my friend has smartphone of company alpha" - - > interest I
Again, even though through the viewing site: http:// hp. html, the user AAA mental state also does not change and maintains the state of interest I. Therefore, the scores are not updated in the score memory 102.
Fig. 6 is a schematic diagram for explaining a first score updating process using weights in the present invention.
As shown in fig. 6, a score update process similar to the process shown in fig. 4 is performed. As shown below, the difference in the score update process shown in fig. 6 is that the score for each mental state is increased by using a different weight in each mental state.
(S61) a weight wb (previous weight) of the psychological state for the standard comment text:
wb(A)，wb(I)，wb(D)，wb(M)，wb(A')
(S62) a weight wa (later weight) for the psychological state of the subsequently commented text, the weight wa not being equal to wb:
wa(A)，wa(I)，wa(D)，wa(M)，wa(A')
in the above case, the score value P is expressed as follows:
P＝Σi＝A-A'(wb(i)*db(i)+wa(i)*da(i))
the weight wb of each of the mental states A, I, D and M (attention- > interest- > desire- > memory) is set to a value greater than the weight wb of the mental state a' (action). In the process of increasing the score of the psychological state in the standard comment text, the above setting means that the contribution of the promotion site described in the standard comment text whose psychological state is changed to A, I, D or M to the psychological state transition is higher than the contribution of the promotion site described in the standard comment text whose psychological state is changed to a' to the psychological state transition.
Further, the weight wa of each of the psychological states A, I, D and M (attention- > interest- > desire- > memory) is set to a value smaller than the weight wa of the psychological state a' (action). In the process of increasing the score of the psychological state in the subsequent comment text, the above setting means that the contribution of the promotion site described in the standard comment text whose psychological state is changed to A, I, D or M to the psychological state transition is lower than the contribution of the promotion site described in the standard comment text whose psychological state is changed to a' to the psychological state transition.
Fig. 7 is a schematic diagram for explaining a second score updating process using weights in the present invention.
As shown in fig. 7, when the psychological states between the standard comment text and one or more subsequent comment texts generated after the standard comment text are different, the score updater 13 sets the weight wa to a smaller value as the posting time interval between the standard comment text and the subsequent comment text becomes longer. At this time, not only one comment text immediately before/after the standard comment text but also a plurality of comment texts located in the vicinity of the standard comment text are considered. Then, the weights are set as follows:
a greater weight is set for a psychological state generated by comment text temporally or positionally closer to the standard comment text.
A smaller weight is set for a psychological state generated by comment text that is temporally or positionally farther away from the standard comment text.
(promotional effects notifier 14) the promotional effects notifier 14 is configured to send the score for each mental state stored in the score memory 102 for each site address.
As explained in detail above, the program, apparatus and method according to the present invention allow the comment text transmitted by the user to be used in order to analyze the effect of the promotion site on the transition based on the user's psychological state. At this point, the more effective the promotional site is at the user's purchasing behavior, the more valuable the promotional site is. The present invention not only refers to the psychological state included in the comment text, but also enables the effect of a promotion site to be estimated based on the change in the user's psychological state with respect to a purchase. Specifically, online promotion effects of news articles or SNS reviews (for which it is generally not possible to estimate promotion effects) may be estimated.
Many widely different alterations and modifications of the above-described various embodiments of the present invention may be made without departing from the spirit and scope of the invention. All of the foregoing embodiments are merely examples of the present invention and are not intended to be limiting. Accordingly, the invention is limited only as defined in the following claims and equivalents thereto
List of reference numerals
1 a psychological transition analysis device; 101 a psychological keyword dictionary; 102 a score memory; 11 comment text obtainer; 12 a mental state determiner; 13 a score updater; 14 a promotional effect notifier; 2, an SNS site server; 3, a terminal; and 4 a web server.
Claims (11)
1. A computer-readable storage medium in which a program is stored which is executed by a computer installed on an apparatus that analyzes an effect of a promotion site for a product or service on a target keyword, the effect being caused by a psychological state transition of a user, based on a set of comment texts transmitted by each contributor,
the device has:
a psychological keyword dictionary through which one or more psychological keywords are registered for each psychological state in advance;
a score memory that stores, for each promotional site address, a score set for each mental state,
when the program is executed by a computer, the following steps are realized:
a step of obtaining, as a comment text obtainer, for each contributor, comment texts each including the target keyword and arranged in time series;
a step of outputting, as a psychological state determiner, a psychological state for which the included psychological keyword is registered, in a case where the obtained comment text of the contributor includes the psychological keyword registered to the psychological keyword dictionary;
as a score updater, the score memory is instructed to increase the score of the mental state of the standard comment text in a case where the mental state between the standard comment text including the site address and one or more previous comment texts generated before the standard comment text is different, and/or the score memory is instructed to increase the score of the mental state of the one or more subsequent comment texts in a case where the mental state between the standard comment text including the site address and one or more subsequent comment texts generated after the standard comment text is different, and the mental state transition caused by the promotion site address is enabled to be identified.
2. The computer-readable storage medium of claim 1, wherein the psychographic keyword dictionary sets the psychological states according to an AIDMAA (attention, interest, desire, memory, action) model, and registers one or more psychological keywords corresponding to the target keyword for each psychological state.
3. The computer-readable storage medium of claim 2,
wherein each mental state is assigned a value that increases in the order of mental state attention, mental state interest, mental state expectation, mental state memory, mental state action,
wherein the transition of time-series mental states is set to the mental state values arranged in time series, and
wherein the program acts as the score updater to set each of the time-sequenced values to a moving average derived through a predetermined range.
4. The computer-readable storage medium of claim 2, wherein the program sets the weight of the psychological state of the standard comment text and the weight of the psychological state of the subsequent comment text to values different from each other as the score updater, and increases the score by using the weights.
5. The computer-readable storage medium of claim 2, wherein the program sets a weight of the psychological state of the standard comment text and a weight of the psychological state of the subsequent comment text as the score updater, sets the weights to different values for each psychological state, and increases the score by using the weights.
6. The computer-readable storage medium of claim 4,
wherein the program sets in advance, as the score updater, a weight of each of mental state attention, mental state interest, mental state expectation, and mental state memory for the standard comment text to a value larger than a weight of mental state action for the standard comment text, and
wherein the weight of each of the psychological state attention, the psychological state interest, the psychological state expectation, and the psychological state memory for the subsequent comment text is set in advance to a value smaller than the weight of the psychological state action for the subsequent comment text.
7. The computer-readable storage medium of claim 4, wherein in a case where a mental state between the standard comment text and one or more subsequent comment texts generated after the standard comment text is different, the program sets a smaller weight as the score updater for the mental state of the subsequent comment text as a posting time interval between the standard comment text and the subsequent comment text becomes longer.
8. The computer-readable storage medium of claim 1,
wherein the target keyword is a keyword based on the product or the service, and
wherein the site address is a URL (Uniform resource locator) of the promotional site for the product or the service.
9. The computer-readable storage medium of claim 1, the program, when executed by a computer, further implementing the step of sending a score for each mental state stored in the score memory for each site address as a promotion effect notifier.
10. An apparatus for analyzing an effect of a promotion site for a product or service on a target keyword, the effect being caused by a psychological state transition of a user, based on a set of comment texts transmitted by each contributor, and the apparatus comprising:
a psychological keyword dictionary through which one or more psychological keywords are registered for each psychological state in advance;
a comment text obtainer that obtains, for each contributor, comment texts each including the target keyword and arranged in time series;
a psychological state determiner that outputs a psychological state for which the included psychological keyword is registered, in a case where the obtained comment text of the contributor includes the psychological keyword registered to the psychological keyword dictionary;
a score memory that stores, for each promotion site address, a score set for each psychological state; and
a score updater that instructs the score memory to increase the score of the psychological state of the standard comment text in a case where the psychological state between the standard comment text including the site address and one or more previous comment texts generated before the standard comment text is different, and/or that instructs the score memory to increase the score of the psychological state of one or more subsequent comment texts generated after the standard comment text in a case where the psychological state between the standard comment text including the site address and the one or more subsequent comment texts is different, and
the apparatus enables identification of the mental state transition caused by the promotional site address.
11. A method for analyzing, by using a device, an effect of a promotion site for a product or service on a target keyword, the effect being caused by a transition in a user's mental state, based on a set of comment texts transmitted by each contributor,
the device includes:
a psychological keyword dictionary through which one or more psychological keywords are registered for each psychological state in advance; and
a score memory that stores, for each promotion site address, a score set for each psychological state, and
the method comprises the following steps:
obtaining comment texts for each contributor, each of the comment texts including the target keyword and being arranged in a time series;
in a case where the obtained comment text of the contributor includes a psychological keyword registered to the psychological keyword dictionary, outputting a psychological state for which the included psychological keyword is registered; and
instructing the scoring memory to increase the score of the mental state of a standard comment text including the site address in the case where the mental state is different between the standard comment text and one or more previous comment texts generated before the standard comment text, and/or instructing the scoring memory to increase the score of the mental state of one or more subsequent comment texts generated after the standard comment text in the case where the mental state is different between the standard comment text including the site address and the subsequent comment text, and
the method enables identification of the mental state transition caused by the promotional site address.
Applications Claiming Priority (3)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP2014145050A JP6257086B2 (en) | 2014-07-15 | 2014-07-15 | Program, apparatus and method for analyzing effect of user's psychological transition on promotion site |
| JP2014-145050 | 2014-07-15 | ||
| PCT/JP2015/070016 WO2016009985A1 (en) | 2014-07-15 | 2015-07-13 | Program, device, and method for analyzing effect of promotion site on transition of psychological state of user |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106471494A CN106471494A (en) | 2017-03-01 |
| CN106471494B true CN106471494B (en) | 2019-12-20 |
Family
ID=55078478
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201580034569.2A Expired - Fee Related CN106471494B (en) | 2014-07-15 | 2015-07-13 | Program, apparatus and method for analyzing effect of promotion site on user's psychological state transition |
Country Status (3)
| Country | Link |
|---|---|
| JP (1) | JP6257086B2 (en) |
| CN (1) | CN106471494B (en) |
| WO (1) | WO2016009985A1 (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP6719727B2 (en) * | 2016-03-23 | 2020-07-08 | 富士ゼロックス株式会社 | Purchase behavior analysis device and program |
| JP6815235B2 (en) * | 2017-03-16 | 2021-01-20 | ヤフー株式会社 | Information processing equipment, information processing methods, and programs |
| KR102091661B1 (en) * | 2017-12-20 | 2020-03-20 | (주)아크릴 | Method for providing cost-heartfelt satisfaction evaluation-based service based on user's situational emotion change |
| JP6943810B2 (en) * | 2018-05-18 | 2021-10-06 | ヤフー株式会社 | Providing equipment, providing method and providing program |
| US10789429B2 (en) | 2018-11-21 | 2020-09-29 | Intuit, Inc. | Visualizing comment sentiment |
| JP6647543B1 (en) * | 2019-03-06 | 2020-02-14 | 株式会社Ｃｒｅａｔｏｒ’ｓ ＮＥＸＴ | Information processing apparatus, information processing method and program |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2001222596A (en) * | 2000-02-08 | 2001-08-17 | Mega Chips Corp | Mail-order sale system |
| JP2008146293A (en) * | 2006-12-08 | 2008-06-26 | Fujitsu Ltd | Evaluation system, method and program for browsing target information |
| JP2011108053A (en) * | 2009-11-18 | 2011-06-02 | Nomura Research Institute Ltd | System for evaluating news article |
| CN103235818A (en) * | 2013-04-27 | 2013-08-07 | 北京百度网讯科技有限公司 | Information push method and device based on webpage emotion tendentiousness |
| CN103268560A (en) * | 2013-04-19 | 2013-08-28 | 杭州电子科技大学 | Before-release advertising effect evaluation method based on electroencephalogram indexes |
| US8799150B2 (en) * | 2009-09-30 | 2014-08-05 | Scorelogix Llc | System and method for predicting consumer credit risk using income risk based credit score |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP5518027B2 (en) * | 2011-10-25 | 2014-06-11 | クエリーアイ株式会社 | Information analysis system |
-
2014
- 2014-07-15 JP JP2014145050A patent/JP6257086B2/en active Active
-
2015
- 2015-07-13 CN CN201580034569.2A patent/CN106471494B/en not_active Expired - Fee Related
- 2015-07-13 WO PCT/JP2015/070016 patent/WO2016009985A1/en active Application Filing
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2001222596A (en) * | 2000-02-08 | 2001-08-17 | Mega Chips Corp | Mail-order sale system |
| JP2008146293A (en) * | 2006-12-08 | 2008-06-26 | Fujitsu Ltd | Evaluation system, method and program for browsing target information |
| US8799150B2 (en) * | 2009-09-30 | 2014-08-05 | Scorelogix Llc | System and method for predicting consumer credit risk using income risk based credit score |
| JP2011108053A (en) * | 2009-11-18 | 2011-06-02 | Nomura Research Institute Ltd | System for evaluating news article |
| CN103268560A (en) * | 2013-04-19 | 2013-08-28 | 杭州电子科技大学 | Before-release advertising effect evaluation method based on electroencephalogram indexes |
| CN103235818A (en) * | 2013-04-27 | 2013-08-07 | 北京百度网讯科技有限公司 | Information push method and device based on webpage emotion tendentiousness |
Also Published As
| Publication number | Publication date |
|---|---|
| JP2016021174A (en) | 2016-02-04 |
| JP6257086B2 (en) | 2018-01-10 |
| WO2016009985A1 (en) | 2016-01-21 |
| CN106471494A (en) | 2017-03-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106471494B (en) | Program, apparatus and method for analyzing effect of promotion site on user's psychological state transition | |
| US9183259B1 (en) | Selecting content based on social significance | |
| US20140172545A1 (en) | Learned negative targeting features for ads based on negative feedback from users | |
| US20140172544A1 (en) | Using negative feedback about advertisements to serve advertisements | |
| US20110218859A1 (en) | Method, Apparatus and System for Increasing Website Data Transfer Speed | |
| EP2743874A1 (en) | Targeting objects to users based on search results in an online system | |
| KR20210006505A (en) | Methods and apparatus to estimate demographics of users employing social media | |
| JPWO2012002351A1 (en) | Information processing apparatus, information processing method, and information processing program | |
| JP2015515676A (en) | How to target stories based on influencer scores | |
| US10897638B2 (en) | Generation apparatus, generation method, and non-transitory computer readable storage medium | |
| US20160012485A1 (en) | Browsing context based advertisement selection | |
| US20120232956A1 (en) | Customer insight systems and methods | |
| KR20170084171A (en) | Using Audience Metrics with Targeting Criteria for an Advertisement | |
| JP5229504B2 (en) | Advertisement presenting method, advertisement presenting system and program | |
| US20130006760A1 (en) | Systems and methods for presenting comparative advertising | |
| US10922722B2 (en) | System and method for contextual video advertisement serving in guaranteed display advertising | |
| JP6169511B2 (en) | Apparatus, program, and method for analyzing poster's psychological transition based on comment text | |
| US20150019568A1 (en) | Identifying word-of-mouth influencers using topic modeling and interaction and engagement analysis | |
| WO2016125166A1 (en) | Systems and methods for analyzing video and making recommendations | |
| JP5762456B2 (en) | Advertisement providing device | |
| JP5869931B2 (en) | Recommendation item detection program, apparatus and method for detecting items to be criticized by critics | |
| JP6549675B2 (en) | Learning apparatus, learning method and learning program | |
| JP2016048526A (en) | Extraction device, extraction method, and extraction program | |
| JP6353396B2 (en) | Advertisement providing apparatus and advertisement providing method | |
| JP6025155B2 (en) | Information processing apparatus, method, and program |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20191220 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |