JP2016122360A - Program, device and method for detecting place influencing human psychological state from comment sentence - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a program, device and method capable of detecting a place that influences a psychological state of a person from a comment sentence.SOLUTION: The device includes: comment sentence acquisition means for acquiring comment sentences including an object keyword in a time series in each contributor; place psychology determination means for associating a psychological state of a psychological keyword with each comment sentence when the psychological keyword is written, and associating place information with each comment sentence when the place information is written in each contributor; score update means for updating score storage means so as to increment scores of the psychological state in the place information determined by the place psychology determination means; and place value detection means for using the score storage means to output the prescribed number of pieces of place information in order of upper scores with a value to the psychological state as a high place about each psychological state.SELECTED DRAWING: Figure 2

Description

  The present invention relates to a technique for analyzing comment text posted to a communication site server such as SNS (Social Networking Service).

  In recent years, an unspecified number of third parties can actively transmit their own comment sentences (text information) via the SNS site server. The SNS site server publishes comment text posted by one user to a large number of users in a group. For example, there are facebook (registered trademark), twitter (registered trademark), google + (registered trademark), and mixi (registered trademark), which are also generally referred to as miniblog sites. By analyzing the comment texts of a large number of users, for example, it is possible to know a tendency according to the user's profile (age, gender, hobby, etc.). Even for the same product service, the content of the comment text may be different depending on the user's profile.

  A company attempts to advertise its product service using an advertising medium (for example, a poster, a signboard, or a digital signage) at a place in a real space (for example, a store, a station, or an event). In order to determine an effective advertisement place, for example, the traffic volume of people and cars is often used as the advertisement value of the place. However, a large amount of traffic does not necessarily affect the purchasing psychology of those who pass.

  Conventionally, for each advertiser, there is a technique for selecting whether or not an installation location on an advertising billboard is effective (see, for example, Patent Document 1). According to this technique, a person passing in front of an advertising billboard is photographed with a camera, and the person attribute and traffic volume are analyzed. It is possible to select an effective installation location of the advertising billboard according to the traffic amount of the person attribute that the advertiser wants to appeal to.

  There is also a technique for calculating a user's evaluation score for a place (see, for example, Patent Document 2). According to this technique, in order to present a place to be visited to a specific user, an evaluation score for each place is calculated using the visit history (when and which place was visited) of the user and other users.

  As another conventional technique, there is a technique for analyzing an advertisement effect using an AIDMA model that is an economics model relating to purchasing behavior (see, for example, Patent Document 3). According to the general knowledge of economics, the psychological state regarding the purchase behavior of the user is A (Attention)-> I (Interest)-> D (Desire)-> M (Memory) -> Change like A (Action). Each AIDMA phase is assigned to each type of advertisement or action (TV advertisement, magazine advertisement, email, Web page, banner click, bookmark, coupon acquisition, etc.), and the number of those (number of TV advertisements, banners) If it is a click, the number of clicks) is measured. This quantifies the impact of advertising on each phase of AIDMA.

JP 2007-293544 A JP 2013-257671 A JP 2003-044738 A

  The comment text posted by the user often includes the user's own psychological state consciously or unconsciously. In particular, according to the marketing application, it is desired to analyze the user's psychological remarks regarding the product service.

  In contrast, the inventors of the present application estimated the user's purchasing psychological state from comment text posted to the SNS for a specific product service, and contributed to the psychological state “location (for example, a place name (station name or station or Is it possible to detect “shops, etc.) and latitude / longitude”? I thought. For example, for each piece of location information, can a score value that contributes to the user's psychological state with respect to the product service be accumulated? I thought. This makes it possible to detect which place has an influence on the psychological state in marketing and promotion for the user.

  In particular, the inventors of the present application wanted to efficiently extract influencers based on “location”. Specifically, when a user's psychological state transitions at a certain place, there is a possibility that the advertising medium installed at that place has contributed to the transition of the psychological state. Here, “influencer” means a place where the purchase psychological state is likely to change when the user stays at the place. This means that the place where the influencer's influence is higher, the greater the effect as marketing or promotion in order to introduce the product service.

Here, according to the technique described in Patent Document 1, the amount of traffic of a person at a place is analyzed, but the influence on the purchasing psychology of the person is not estimated. In other words, it cannot be assumed whether or not it is effective as a place for installing an advertising medium that promotes the purchase of merchandise services. For example, there is a possibility that an advertising medium in a local shopping center may lead to purchase rather than an advertising medium in front of Shibuya Station where there are many people.
Further, according to the technique described in Patent Document 2, the value of whether or not the place is useful for the user to visit is merely estimated, and the purchase psychology of the user is not estimated.
In addition, according to the technique described in Patent Document 3, the comment sentence posted to the SNS is not assumed for the estimation of the psychological state in the AIDMA model.

  Then, an object of this invention is to provide the program, apparatus, and method which can detect the place which influenced the human psychological state from the comment text.

According to the present invention, from a group of comment sentences transmitted for each contributor, a program for causing a computer mounted on the apparatus to function so as to analyze the effect of the user's psychological transition on the target keyword,
Psychological keyword dictionary means for registering psychological keywords in advance for each psychological state;
Score storage means for storing a score of each psychological state in each place information;
For each contributor, comment sentence acquisition means for acquiring comment sentences including the target keyword in time series,
For each contributor, when a psychological keyword is described in each comment sentence, the psychological state of the psychological keyword is associated, and when location information is described, a place psychological determination unit that associates the location information,
Score update means for updating the score storage means so as to increment the score of the psychological state to the place information determined by the place psychological determination means;
The score storage means is used to cause the computer to function as place value detection means for outputting a predetermined number of place information from the top of the score as places with high value for the psychological state for each psychological state.

According to another embodiment of the program of the present invention,
The score update means
In the group of comment sentences, for a standard comment sentence including location information, if the psychological state changes between the standard comment sentence and one or more forward comment sentences in the past, the psychological state of the reference comment sentence And / or if the psychological state changes between the reference comment sentence and one or more backward comment sentences in the future, the psychological state score of the backward comment sentence is incremented. It is also preferred to have the computer function to update the score storage means.

According to another embodiment of the program of the present invention,
Comment text is based on SNS,
It is also preferable to further cause the computer to function so that the target keyword is a keyword based on the product service.

According to another embodiment of the program of the present invention,
It further has a place name storage means associated with the place name,
It is also preferable that the place psychological judgment means further causes the computer to function so as to search for a place name stored in the place name storage means.

According to another embodiment of the program of the present invention,
The place name storage means associates representative place names with a plurality of place names,
It is preferable that the place psychological determination means further causes the computer to function so as to convert the place name into a representative place name stored in the place name storage means.

According to another embodiment of the program of the present invention,
The location information further includes latitude and longitude,
The place name storage means associates a predetermined range of latitude and longitude with the place name,
It is preferable that the place psychological determination means further causes the computer to function so as to convert the latitude and longitude as the place information into a representative place name stored in the place name storage means.

According to another embodiment of the program of the present invention,
The psychological keyword dictionary means that the psychological state is associated with the AtIDMAC (Attention: interest-> Interest: interest-> Desire: desire-> Memory: memory-> Action: behavior) model. It is also preferable to make the computer function so as to register the psychological keywords for.

According to another embodiment of the program of the present invention,
The psychological states are assigned numerical values that increase in the order of At->I->D->M-> Ac,
A time series of psychological transitions is a time series of psychological values.
The score updating means preferably causes the computer to function so that the numerical values arranged in time series are set to a moving average value within a predetermined range.

According to another embodiment of the program of the present invention,
It is also preferable that the score updating means sets the weight wb for the psychological state of the reference comment sentence and the weight wa for the psychological state of the backward comment sentence as different values, and causes the computer to function so that the score is weighted and incremented. .

According to another embodiment of the program of the present invention,
The score updating means preferably causes the computer to function such that the weight wb for the psychological state of the reference comment sentence and the weight wa for the psychological state of the backward comment sentence are incremented with different weights for each psychological state.

According to another embodiment of the program of the present invention,
The weight wb of the psychological state AtIDM (Attention: attention-> Interest: interest-> Desire: desire-> Memory: memory) is larger than the weight wb of the psychological state Ac (Action),
The weight wa of the psychological state AtIDM (Attention: attention-> Interest: interest-> Desire: desire-> Memory: memory) is set in advance so that the weight wa is smaller than the weight wa of the psychological state Ac (Action). It is also preferable to make the computer function.

According to another embodiment of the program of the present invention,
The score update means
When the psychological state changes between the reference comment sentence and one or more backward comment sentences in the future, the weight wa becomes smaller as the posting time interval between the reference comment sentence and the backward comment sentence becomes longer. It is also preferred to have the computer function to set.

According to the present invention, from a group of comment sentences transmitted for each contributor, an apparatus for analyzing the effect of a user's psychological transition on a target keyword,
Psychological keyword dictionary means for registering psychological keywords in advance for each psychological state;
Score storage means for storing a score of each psychological state in each place information;
For each contributor, comment sentence acquisition means for acquiring comment sentences including the target keyword in time series,
For each contributor, when a psychological keyword is described in each comment sentence, the psychological state of the psychological keyword is associated, and when location information is described, a place psychological determination unit that associates the location information,
Score update means for updating the score storage means so as to increment the score of the psychological state to the place information determined by the place psychological determination means;
It is characterized by having a place value detecting means for outputting, for each psychological state, a predetermined number of place information from the top of the score as a place having a high value for the psychological state using the score storage means.

According to the present invention, using a device, a method of analyzing the effect of a user's psychological transition related to a target keyword from a group of comment sentences transmitted for each contributor,
The device
For each psychological state, a psychological keyword dictionary part in which psychological keywords are registered in advance,
A score storage unit that stores a score of each psychological state in each place information,
The device
For each contributor, a first step of acquiring comment sentences including the target keyword in time series;
For each contributor, if a psychological keyword is described in each comment sentence, the psychological state of the psychological keyword is associated, and if location information is described, a second step of associating the location information;
A third step of updating the score storage means so as to increment the score of the psychological state to the location information determined by the second step;
And a fourth step of outputting, for each psychological state, a predetermined number of pieces of place information from the top of the score as places having a high value for the psychological state using the score storage unit.

  According to the program, apparatus, and method of the present invention, it is possible to detect a place that affects a person's psychological state from comment text. Specifically, it is possible to estimate the purchase psychological state of the user from the comment text posted to the SNS for a specific product service, and to detect the location information that has influenced the purchase psychological state.

It is a system configuration diagram in the present invention. It is a functional block diagram of the psychological transition analyzer in this invention. It is explanatory drawing showing the comment text posted in time series. It is explanatory drawing which divided the comment text containing a target keyword for every user address. It is explanatory drawing which provided the psychological state to the comment text containing a target keyword. It is explanatory drawing showing the 1st score update in this invention. It is explanatory drawing showing the 2nd score update in this invention. It is explanatory drawing showing the score update which attached the 1st weight in this invention. It is explanatory drawing showing the score update which attached the 2nd weight in this invention.

  Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings.

  FIG. 1 is a system configuration diagram according to the present invention.

  According to FIG. 1, the psychological transition analysis apparatus 1 of the present invention is connected to the Internet. The psychological transition analysis device 1 communicates with the SNS site server 2 via the Internet. The psychological transition analysis apparatus 1 can obtain comment text for each contributor via the API (Application Programming Interface) from the SNS site server 2. The API is a rule interface for using the function of the application service, and is prepared as different for each of various servers.

  In addition, the psychological transition analysis apparatus 1 may accumulate comment texts in a database in advance. That is, the psychological transition analysis device 1 does not necessarily communicate with the SNS site server 2.

  An unspecified number of third parties can send comment text to the SNS site server 2 via the Internet using their own terminals 3. Moreover, the psychological transition analysis apparatus 1 analyzes the user psychological transition regarding a target keyword from the group of comment sentences transmitted for each contributor. The “target keyword” is a keyword based on the product service. In addition, a large number of comment sentences include those that include location information and those that do not.

  The location information is, for example, “location name” and / or “latitude / longitude”. The “place name” may be a specific place name such as “Tokyo Station”, “Kawagoe SC”, or “Shibuya Station”. Further, for example, URL (Uniform Resource Locator) (check-in information) of Foursquare (registered trademark) may be used. Regarding the granularity of the place, in the case of latitude / longitude and foursquare check-in information, it is possible to specify a specific store name such as a restaurant.

  FIG. 2 is a functional configuration diagram of the psychological transition analysis apparatus according to the present invention.

  The psychological transition analysis apparatus 1 of the present invention can analyze user psychological transitions related to the target keyword from a group of comment sentences transmitted for each contributor. The psychological transition analysis device 1 includes a psychological keyword dictionary unit 101, a score storage unit 102, a place name storage unit 103, a comment sentence acquisition unit 11, a place psychological determination unit 12, and a score update unit 13 together with a communication interface unit. And a place value detection unit 14. These functional components excluding the communication interface unit are realized by executing a program that causes a computer installed in the apparatus to function. Moreover, the flow of processing of these functional components can be understood as a psychological transition analysis method of the apparatus.

[Psychological keyword dictionary unit 101]
The psychological keyword dictionary unit 101 registers psychological keywords in advance for each psychological state. The psychological state transitions in time series as follows, corresponding to the AIDMA model.
Cognitive stage: Attention: Attention->
Emotional stage: Interest->
Desire: Desire->
Memory: Memory->
Action stage: Action: Action The psychological keyword dictionary unit 101 preferably has different psychological keywords registered in each psychological state for each target keyword.

  The AIDMA model is an abbreviation that represents a consumer psychological process for advertising. By tracking utterances of the same user in a time series with respect to the target keyword (target product service), it can be estimated by applying to a transition model of purchasing psychological state in economics.

The psychological keyword dictionary unit 101 registers a psychological keyword for the target keyword (for example, “a company smartphone”) for each psychological state (A, ID, M, A).
Attention state: sale, CM, new work, new product, ...
Interest state: lineup, pamphlet, HP, cute, ...
Desired state: Wanted, price, specs, design, ...
Memory state: shop, exhibition, real thing, preview, ...
Action state: buy, get, give up, model change This is a dictionary in which words characteristically appearing in each psychological state are registered for the target keyword.

The psychological keyword dictionary unit 101 is basically created manually in advance. However, pre-psychological keywords registered manually as a seed (teacher data), the characteristically appearing word to each psychological state, using statistical indicators (e.g. chi ² value and Akaike Information Criterion (AIC)) It may be calculated.

[Score storage unit 102]
The score memory | storage part 102 memorize | stores the score of each psychological state in each place information. According to FIG. 2, the score memory | storage part 102 is represented by the table which consists of each place name (row) and the score (column) of each psychological state. The score is updated by the score update unit 13.

[Location name storage unit 103]
The place name storage unit 103 stores at least a place name (for example, a station name, a facility name, a store name, etc.). Further, one representative place name may be associated with a plurality of place names based on the same place. According to FIG. 2, for example, the place name “Hachiko-mae” is grouped into “Shibuya Station”.
Each location name may be associated with a predetermined range of latitude and longitude. Predetermined ranges having the same latitude and longitude can be combined into one representative place name. That is, even if the latitude / longitude information is described in the comment text of the user, it can be associated with the place name.

[Comment text acquisition unit 11]
The comment text acquisition unit 11 acquires, from the SNS site server 2, comment text including the target keyword in time series for each user address (contributor). The “target keyword” may be, for example, the name of a product service for which an advertisement place is to be analyzed. This target keyword is set for a system user, for example, a promotion person in charge of a company.

  FIG. 3 is an explanatory diagram showing comment sentences posted in time series.

It is assumed that the psychological transition analysis apparatus 1 analyzes the psychological state included in the comment text for the target keyword “Company A”. According to FIG. 3, various comment texts for a large number of users are represented for the target keyword “a company smartphone”. Some of these comment texts include location information (location name and latitude / longitude) cited in their own comments. For example, it is assumed that comment sentences are transmitted in the following time series.
User @CCC “When is the company a smartphone released?”
User @ABC "New a company smartphone. Http: //news.html"
User @AAA “Today is a day out!”
User @ AAA “A new smartphone ad discovery at Tokyo Station”
User @BBB "I wonder if I will change to a company smartphone"
User @ AAA “Drama Now”
User @DEF "New a company smartphone, easy to use and recommended"
User @AAA "A company smartphone, the color has changed. Cute!"
User @ AAA “I'm at Kawagoe SC https://www.shopping.com”
・ ・ ・ 「・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・」

  FIG. 4 is an explanatory diagram in which the comment text including the target keyword is divided for each user address.

According to FIG. 4, only the comment text posted by the user “@AAA” is shown.
User @AAA “Today is a day out!”
User @ AAA “A new smartphone ad discovery at Tokyo Station”
User @ AAA “Drama Now”
User @AAA "A company smartphone, the color has changed. Cute!"
User @ AAA “I'm at Kawagoe SC https://www.shopping.com”
User @AAA “Let's meet up.
User @ AAA "Company a smartphone, I'm doing a campaign. I want!"
User @ AAA ".................."
User @ AAA "A company smartphone at the shop, let's have a preview"

[Place psychology determination unit 12]
The place psychology determination unit 12 associates the following two elements for each comment sentence.
(Decision 1) When the psychological keyword of the psychological keyword dictionary unit 101 is described in the comment text for each contributor, the place psychological determination unit 12 outputs the psychological state of the psychological keyword.
(Decision 2) When the location information of the location name storage unit 103 is described in the comment text for each poster, the location psychology determination unit 12 associates the location information with the location information. The location information is a location name and / or latitude / longitude. Here, the place psychology determination unit 12 may convert the place name into a representative place name stored in the place name storage unit 103. Further, the place psychological determination unit 12 may convert the latitude and longitude as the place information into a representative place name stored in the place name storage unit 103.

  FIG. 5 is an explanatory diagram in which a psychological state is given to the comment text including the target keyword.

From the comment text including the psychological keyword “new work” and the location information “Tokyo Station”, it is estimated that the user is in an attention state at the location “Tokyo Station”.
From the comment text including the psychological keyword “cute”, it is estimated that the user is in an interest state.
From the comment text that includes the location information “I'm at Kawagoe SC https://www.shopping.com”, the user stays at the location “Kawagoe SC” (which may be the latitude and longitude based on the URL). Authenticate that
From the comment text including the place information “Hachiko-mae”, the user determines that he / she is staying at the place “Hachiko-mae”.
From the comment text including the psychological keyword “I want”, it is estimated that the user is in the Desire state.
...
From the comment text including the psychological keywords “shop” and “preview”, it is estimated that the user is in a memory state.

As another embodiment, when a plurality of psychological keywords are included in one comment sentence, the psychological state of the entire comment sentence may be determined based on the number of appearances. Alternatively, the psychological state may be determined using a discriminator such as a support vector machine from the appearance tendency of words in the teacher data. Further, the likelihood may be given in addition to the AIDMA model.
"Let's have a look at a company's smartphone at the shop this time"
Shop = M, Preview = M
A = 0, I = 0, D = 0, M = 2, A = 0
Likelihood of M = 100%

[Score Updater 13]
The score update unit 13 increments the score of the psychological state in the place information when the place psychological determination unit 12 determines. The score means the degree of influence of the place on the purchasing psychology of the user staying at the place. Here, the score update unit 13 has the following two steps.
<Psychological transition determination step>
<Score update step>

<Psychological transition determination step>
The score update unit 13 estimates a psychological transition in which psychological states are arranged in time series for each poster. For example, the following psychological transition is estimated.
A, A, I, A, I, I, D, I, D, D, M, M, M

Here, it is also preferable to assign a numerical value that increases in order of A->I->D->M-> A to the psychological transition. As a result, the psychological transition is obtained by arranging the numerical values of the psychological state in time series. It can be understood that the state has shifted to the next psychological state depending on the magnitude of the numerical value.
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
However, in this case, a psychological state may naturally occur.

(Correction by moving average of psychological transition)
On the other hand, the score update unit 13 corrects the numerical values arranged in time series so as to be in ascending order as much as possible. Specifically, the average value of the psychological states of adjacent n comments before and after is set as the psychological state of the comment. That is, it is also preferable to set the moving average value within a predetermined range in the previous stage.
Take the average of two adjacent terms.
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
((((((((((((((Rounding rounded down ↓))))))))))))))))))
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 based on time difference between psychological state transitions)
The comment text includes the posting time. The place psychology determination unit 12 also outputs the posting time of the comment text including the psychological keyword together with the psychological state. Thus, the score updater 13 can know the elapsed time interval between the psychological states arranged in time series.

Then, the score update unit 13 weights the numerical values arranged in time series in the time series psychological transition as follows.
The longer the elapsed time interval in the previous stage, the smaller the weight for the value. The shorter the elapsed time interval in the previous stage, the greater the weight for the value.

As another embodiment, the product of the likelihood of the estimated psychological state may be used for numerical values of 0 to 4. When A = 10%, I = 70%, D = 20%, and M = 0%, multiplication is performed as follows.
0 × 10% + 1 × 70% + 2 × 20% + 3 × 0% = 1.1

<Score update step>
The score update unit 13 executes one or both of the following two update steps for the reference comment text including the location information in the comment text group, and instructs the score storage section 102.
(Reference update step) When the psychological state changes between the reference comment sentence and one or more forward comment sentences in the past, the psychological state score of the reference comment sentence is incremented.
(Backward update step) When the psychological state changes between the reference comment sentence and one or more backward comment sentences in the future, the score of the psychological state of the backward comment sentence is incremented.

Specifically, for each user, the AIDMA transition of the forward / backward comment text is expressed as follows, as seen from the standard comment text.
Forward comment text-> standard comment text: db (At, I, D, M, Ac)
Standard comment text-> backward comment text: da (At, I, D, M, Ac)
Each element of (At, I, D, M, Ac) is represented by 0/1.
It can be considered that the degree of influence of the location information increases as the psychological state of the user approaches the purchase behavior between the comments before and after the reference comment text including the location information.

  FIG. 6 is an explanatory diagram showing the first score update in the present invention.

(S61) For user @ AAA, the psychological state is changing as follows.
"A company smartphone, new ad discovery Tokyo Station"-> Attention At
Here, the user @AAA has found an advertisement at the place “Tokyo Station”, and thus the psychological state has shifted to attention A. For this purpose, the score value P (At) of the attention At of the location information “Tokyo Station” is incremented by 1 for the score storage unit 102.
Forward comment text-> standard comment text: db (0,1,0,0,0)

(S62) Next, the psychological state of user @AAA is changing as follows.
"Company a's smartphone is changing color. Cute!"-> Interest I
Here, for user @AAA, the psychological state has transitioned to attention A. At this time, a predetermined number of comment sentences (or a predetermined time range before and after the reference comment sentence) are examined. It should be noted that nb comment sentences are considered forward and / or na comment sentences backward from the reference comment. Moreover, the comment text of time tb ahead and / or time ta behind may be considered.
In the comment sentence one piece behind, it is described as follows.
"I'm at Kawagoe SC https://www.shopping.com"
Here, user @ AAA can be recognized as staying at “Kawagoe SC”. Therefore, the score value P (I) of the interest I of the location information “Kawagoe SC” is incremented by 1 for the score storage unit 102.
Forward comment text-> standard comment text: db (0,1,0,0,0)

(S63) Next, the psychological state of user @AAA is changing as follows.
"Company a smartphone, I'm doing a campaign. I want!"-> Desire D
Here, the user @AAA has the psychological state transitioned to desire D. At this time, a predetermined number of comment sentences (or a predetermined time range before and after the reference comment sentence) are examined.
In the comment text one piece ahead, it is written as follows.
“Let's meet. There are many people in front of Hachiko.”
Here, the user @AAA can be recognized as staying in “Hachiko-mae”. Further, according to the place name storage unit 102, “Hachiko-mae” is typically associated with “Shibuya Station”. Therefore, the score value P (D) of the desire D of the location information “Shibuya Station” is incremented by 1 for the score storage unit 102.
Forward comment text-> standard comment text: db (0,0,1,0,0)

  Finally, the score is estimated by accumulating db (at, i, d, m, ac) and da (at, i, d, m, ac) for each user address.

  FIG. 7 is an explanatory diagram showing the second score update in the present invention.

  According to FIG. 7, it may be determined that the location has contributed to the transition of the psychological state only when the user's psychological state transitions at the location. Therefore, the score is not updated when the user's psychological state has not changed at that location.

(S71) For user @ AAA, the psychological state is changing as follows.
"A company's smartphone lineup is good"-> Interest I
"Company a's smartphone is changing color. Cute!"-> Interest I
Here, even though the user @AAA is in the place “Kawagoe SC”, the psychological state remains as interest I and does not change. Therefore, no score value is updated for the score storage unit 102.

(S72) Next, the psychological state of user @AAA is changing as follows.
“The design of company a's smartphone is GOOD!”-> Desire D
"Let's meet. There are many people in front of Hachiko"-> Desire D
Here, even if the user @AAA is in the place “Shibuya Station”, the psychological state remains the desire D and does not change. Therefore, no score value is updated for the score storage unit 102.

  FIG. 8 is an explanatory diagram showing the score update with the first weight in the present invention.

According to FIG. 8, the score is incremented with a different weight for each psychological state.
(S81) Weight wb (Weight before) for the psychological state of the standard comment sentence
wb (At), wb (I), wb (D), wb (M), wb (Ac)
(S82) Weight after the psychological state of the backward comment sentence wa (Weight after) (≠ wb)
wa (At), wa (I), wa (D), wa (M), wa (Ac)
In this case, the influence degree P is expressed by the following equation using the state changes db (i) and da (i).
P = Σ _{i = At to Ac} (wb (i) × db (i) + wa (i) × da (i))

According to FIG. 8, the weights wb (i) and wa (i) can be set in a 5 × 5 matrix. For example, b _ati means the weight for the transition from Attention to Interest. By adjusting the value of each element of this matrix, it is possible to calculate the degree of influence that emphasizes a specific state transition.

  The weight wb of the psychological state AtIDM (Attention: attention-> Interest: interest-> Desire: desire-> Memory: memory) is set larger than the weight wb of the action state Ac (Action). When the score of the psychological state of the standard comment sentence is incremented, the user address described in the standard comment sentence transitioned to the psychological state AtIDM is compared with the user address described in the standard comment sentence transitioned to the action state Ac. Means that the contribution to the psychological state is high.

  The weight wa of the psychological state AtIDM (Attention: attention-> Interest: interest-> Desire: desire-> Memory: memory) is set smaller than the weight wa of the action state Ac (Action). When the score of the psychological state of the backward comment sentence is incremented, the user address described in the reference comment sentence transitioned to the psychological state AtIDM is compared with the user address described in the reference comment sentence transitioned to the action state Ac. Means that the contribution to the psychological state is low.

  FIG. 9 is an explanatory diagram showing the score update with the second weight in the present invention.

According to FIG. 9, when the psychological state changes between the reference comment sentence and one or more backward comment sentences in the future, the score update unit 13 posts the time between the reference comment sentence and the backward comment sentence. The weight wa is set to be smaller as the interval becomes longer. That is, a plurality of comments are used in addition to one comment sentence adjacent to the reference comment sentence in front / back. In that case, the weight is set as follows.
A larger weight is set for a psychological state that has been transitioned by a comment sentence that is closer in time or number to the reference comment sentence.
A smaller weight is set for a psychological state that is shifted by a comment sentence that is distant from the reference comment sentence in terms of time or number of cases.

  According to the present invention, it is preferable to calculate a score for each psychological state for each place name from a group of comment sentences collected over a relatively long period of time. On the other hand, it is also preferable to give a greater weight to the score calculated based on the comment text having a shorter posting time. That is, after the user stays at the place, the higher the psychological state changes in a short period, the greater the weight is given to the score.

[Location value detector 14]
The place value detection unit 14 uses the score storage unit 13 to output, for each psychological state, a predetermined number of pieces of place information from the top of the score as places with high value for the psychological state. For example, a place where the score is equal to or greater than a predetermined threshold (for example, 20 or more) for the psychological state is detected as an influencer for the transition to the psychological state.

For example, according to the score storage unit 102 of FIG.
The place “Tokyo Station” is recognized as an influencer with a high contribution to the psychological state “attention (A)”.
The place “Kawagoe SC” is recognized as an influencer with a high contribution to the psychological states “interest (I)” and “desire (D)”.
The place “Shibuya Station” is recognized as an influencer with a high contribution to the psychological state “memory (M)”.

  As another embodiment, it is also preferable to calculate scores for one place name before and after installing the advertising medium at the place. The installation effect of the advertising medium can be detected from the difference in the scores.

  As described above in detail, according to the program, apparatus, and method of the present invention, it is possible to detect a place that affects a person's psychological state from a comment sentence. Specifically, it is possible to estimate the purchase psychological state of the user from the comment text posted to the SNS for a specific product service, and to detect the location information that has influenced the purchase psychological state.

  ADVANTAGE OF THE INVENTION According to this invention, the influence (value of the place for installing an advertisement etc.) with respect to a user's purchasing psychology in a real place is detectable. This makes it possible to clarify the effective installation location of the advertising medium or to detect a change in the value of the location after the advertising medium is installed.

  In addition, according to this invention, it is going to detect the value about one place used as the factor of the purchase psychology transition. It is also possible to detect a connection between a plurality of places (location movement and psychological state transition).

  Various changes, modifications, and omissions of the above-described various embodiments of the present invention can be easily made by those skilled in the art. The above description is merely an example, and is not intended to be restrictive. The invention is limited only as defined in the following claims and the equivalents thereto.

DESCRIPTION OF SYMBOLS 1 Psychological transition analyzer 101 Psychological keyword dictionary part 102 Score memory | storage part 103 Location name memory | storage part 11 Comment sentence acquisition part 12 Place psychological judgment part 13 Score update part 14 Location value detection part 2 SNS site server 3 Terminal

Claims (14)

A program that causes a computer installed in the device to function so as to analyze the effect of the user's psychological transition related to the target keyword from the group of comment sentences transmitted for each contributor,
Psychological keyword dictionary means for registering psychological keywords in advance for each psychological state;
Score storage means for storing a score of each psychological state in each place information;
For each contributor, comment sentence acquisition means for acquiring comment sentences including the target keyword in time series,
For each contributor, if the psychological keyword is described in each comment sentence, the psychological state of the psychological keyword is associated, and if the location information is described, a place psychological determination unit that associates the location information;
Score update means for updating the score storage means to increment the score of the psychological state to the place information determined by the place psychological determination means;
A program for causing a computer to function as place value detection means for outputting a predetermined number of place information from the top of the score as a place having high value for the psychological state for each psychological state using the score storage means . The score update means includes
In the group of comment sentences, for a standard comment sentence including location information, if the psychological state changes between the standard comment sentence and one or more forward comment sentences in the past, the psychological state of the reference comment sentence And / or if the psychological state changes between the reference comment sentence and one or more backward comment sentences in the future, the psychological state score of the backward comment sentence is incremented. The program according to claim 1, wherein the computer is caused to function so as to update the score storage unit. The comment text is based on SNS (Social Networking Service),
The program according to claim 1 or 2, further causing the computer to function so that the target keyword is a keyword based on a merchandise service. It further has a place name storage means associated with the place name,
The program according to any one of claims 1 to 3, wherein the place psychological determination unit causes the computer to further function to search for a place name stored in the place name storage unit. The location name storage means associates representative location names with a plurality of location names,
The program according to claim 4, wherein the place psychological determination unit further causes the computer to function to convert a place name into a representative place name stored in the place name storage unit. The location information further includes latitude and longitude,
The location name storage means associates a predetermined range of latitude and longitude with the location name,
The said place psychology determination means makes a computer further function so that the latitude longitude as place information may be converted into the representative place name memorize | stored in the said place name memory | storage means. program. The psychological keyword dictionary means that the psychological state is associated with the AtIDMAC (Attention: interest-> Interest: interest-> Desire: desire-> Memory: memory-> Action: behavior) model. The program according to any one of claims 1 to 6, wherein the computer is caused to function so as to register a psychological keyword for. The psychological states are assigned numerical values that increase in the order of At->I->D->M-> Ac,
A time series of psychological transitions is a time series of psychological values.
The program according to claim 7, wherein the score updating unit causes the computer to function so that numerical values arranged in time series are set to a moving average value within a predetermined range. The score updating means sets the weight wb for the psychological state of the reference comment sentence and the weight wa for the psychological state of the backward comment sentence as different values, and causes the computer to function so as to weight and increment the score. The program according to claim 7 or 8, characterized in that the program. The score updating means causes the computer to function such that the weight wb for the psychological state of the reference comment sentence and the weight wa for the psychological state of the backward comment sentence are incremented with different weights for each psychological state. The program according to claim 9. The weight wb of the psychological state AtIDM (Attention: attention-> Interest: interest-> Desire: desire-> Memory: memory) is larger than the weight wb of the psychological state Ac (Action),
The weight wa of the psychological state AtIDM (Attention: attention-> Interest: interest-> Desire: desire-> Memory: memory) is set in advance so that the weight wa is smaller than the weight wa of the psychological state Ac (Action). The program according to claim 9, which causes a computer to function. The score update means includes
When the psychological state changes between the reference comment sentence and one or more backward comment sentences in the future, the weight wa becomes smaller as the posting time interval between the reference comment sentence and the backward comment sentence becomes longer. The program according to any one of claims 7 to 11, wherein the computer is caused to function so as to be set. A device that analyzes the effect of a user's psychological transition on a target keyword from a group of comment sentences sent to each contributor,
Psychological keyword dictionary means for registering psychological keywords in advance for each psychological state;
Score storage means for storing a score of each psychological state in each place information;
For each contributor, comment sentence acquisition means for acquiring comment sentences including the target keyword in time series,
For each contributor, if the psychological keyword is described in each comment sentence, the psychological state of the psychological keyword is associated, and if the location information is described, a place psychological determination unit that associates the location information;
Score update means for updating the score storage means to increment the score of the psychological state to the place information determined by the place psychological determination means;
An apparatus comprising: a place value detecting means for outputting, for each psychological state, a predetermined number of pieces of place information as a place having a high value for the psychological state using the score storage means. A method of analyzing the effect of a user's psychological transition on a target keyword from a group of comment sentences sent to each contributor using an apparatus,
The device is
For each psychological state, a psychological keyword dictionary part in which psychological keywords are registered in advance,
A score storage unit that stores a score of each psychological state in each place information,
The device is
For each contributor, a first step of acquiring comment sentences including the target keyword in time series;
For each contributor, if the psychological keyword is described in each comment sentence, the psychological state of the psychological keyword is associated, and if the location information is described, the second step of associating the location information;
A third step of updating the score storage means to increment the score of the psychological state to the location information determined by the second step;
And a fourth step of outputting, for each psychological state, a predetermined number of pieces of place information from the top of the score as places having a high value for the psychological state using the score storage unit.

Images