JP2016110452A - Program, device, and method for updating dictionary of words for which psychological states should be extracted - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a program, etc. for updating a dictionary of words for which psychological states of a user should be extracted, for a designated product service, from a comment sentence submitted to an SNS.SOLUTION: A computer is operated to function as: psychological keyword dictionary means in which psychological keywords are previously registered for each psychological state; comment sentence acquisition means that time-sequentially acquires, for each contributor, a comment sentence including a target keyword; psychological state determination means that outputs, if any of the psychological keywords is included in the comment sentence, the psychological state of the psychological keyword for each contributor; transition phase detection means that detects, for each contributor, a transition phase in which a previous psychological state differs from a later psychological state; transition word extraction means that extracts, for each contributor, a transition word through a morphological analysis from the comment sentence based on the later psychological state; and psychological keyword update means that registers the transition word the appearance frequency of which is equal to or higher than a predetermined threshold value, in the psychological keyword dictionary means as a psychological keyword based on the later 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.

  In many cases, the comment text transmitted by the user 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. For example, even for the same product service, the content of the comment text differs depending on the user's psychological state. Therefore, a dictionary in which words characteristically appearing in each psychological state are registered, and the psychological state can be estimated from the appearance frequency of the words registered in the dictionary for comment sentences.

  2. Description of the Related Art Conventionally, there is a technique for providing a label corresponding to the content of text included in an electronic document (see, for example, Patent Document 1). According to this technique, a word score indicating relevance to each label is calculated based on a statistical index of words appearing in the text of the electronic document. For each label, a word having a high word score can be registered in the dictionary as a characteristic word.

  There is also a technique for creating a dictionary of words based on the frequency of appearance of n-grams of words appearing in a learning document for use in natural language analysis processing (see, for example, Patent Document 2). According to this technique, the dictionary registers word breaks that are used particularly for speech recognition.

  Furthermore, as another conventional technique, there is a technique for analyzing an advertising effect using an AIDMA model that is an economics model related to purchasing behavior (see, for example, Patent Document 3). According to the general knowledge of economics, the psychological state regarding the purchasing behavior of the user is At (Attention)-> I (Interest)-> D (Desire)-> M (Memory) -> Changes like Ac (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 2010-015395 A JP 2011-154061 A JP 2003-044738 A

Here, can the inventors of the present application optimally update the dictionary in which words characteristically appearing in each psychological state are registered? I thought.
According to Patent Document 1, even if each label is associated with a psychological state, all the words appearing in each label are handled equally. For this reason, the label series that changes in time series is not consistent, and the same labels may be arranged while being scattered. That is, even if the psychological state of the user at each time point can be specified by the label, it is impossible to estimate the change of the psychological state.
According to Patent Document 2, a dictionary that uses the appearance frequency of words in a document can be generated, but the dictionary is not classified for each label (for example, for each psychological state).
According to Patent Document 3, only the transition of the psychological state using the AIDMA model is described, and a comment sentence posted to the SNS is not assumed.

  Therefore, the present invention provides a program, an apparatus, and a method capable of updating a dictionary of words for which a user's psychological state should be extracted from comment text posted to an SNS for a specified product service. And

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 a user's psychological transition related to a target keyword,
Psychological keyword dictionary means for registering psychological keywords in advance for each psychological state;
For each contributor, comment sentence acquisition means for acquiring comment sentences including the target keyword in time series,
For each contributor, when the psychological keyword of the psychological keyword dictionary means is included in the comment text, the psychological state determining means for outputting the psychological state of the psychological keyword,
For each contributor, a transition phase detecting means for detecting a transition phase in which the prior psychological state and the backward psychological state are different,
Transition word extraction means for extracting a transition word by morphological analysis from the comment text based on the backward psychological state detected by the transition phase detection means for each contributor,
The computer is caused to function as a psychological keyword updating means for registering, in the psychological keyword dictionary means, a transition word that appears at a frequency equal to or higher than a predetermined threshold among the transition words as a psychological keyword based on the backward psychological state.

According to another embodiment of the program of the present invention,
The target keyword is the product service keyword,
It is also preferable that the psychological state determination means causes the computer to function so as to determine the contributor's psychological state with respect to the keyword of the product service.

According to another embodiment of the program of the present invention,
The psychological keyword dictionary means the psychological state corresponds to the AIDMA (Attention: attention-> Interest: interest-> Desire: desire-> Memory: memory-> Action: behavior) model, and the target keyword for each psychological state. 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,
Transition phase detection means
For psychological states, assign numerical values that increase in the order of At->I->D->M-> Ac,
As psychological transitions in time series, the psychological values are arranged in time series,
It is also preferable to cause the computer to function so as to detect the transition phase using the numerical values arranged in time series as moving average values within a predetermined range.

According to another embodiment of the program of the present invention,
The transition word extraction means may cause the computer to function so that the comment sentence for extracting the transition word is a predetermined number of comment sentences after the backward psychological state and / or a predetermined number of comment sentences before the front psychological state. preferable.

According to the present invention, from a group of comment sentences transmitted for each contributor, an apparatus for analyzing a user's psychological transition related to a target keyword,
Psychological keyword dictionary means for registering psychological keywords in advance for each psychological state;
For each contributor, comment sentence acquisition means for acquiring comment sentences including the target keyword in time series,
For each contributor, when the psychological keyword of the psychological keyword dictionary means is included in the comment text, the psychological state determining means for outputting the psychological state of the psychological keyword,
For each contributor, a transition phase detecting means for detecting a transition phase in which the prior psychological state and the backward psychological state are different,
Transition word extraction means for extracting a transition word by morphological analysis from the comment text based on the backward psychological state detected by the transition phase detection means for each contributor,
Psychological keyword update means for registering a transition word that appears at a frequency equal to or higher than a predetermined threshold among the transition words as a psychological keyword based on the backward psychological state in the psychological keyword dictionary means.

According to the present invention, there is a psychological transition analysis method for a device that analyzes a user's psychological transition related to a target keyword from a group of comment sentences transmitted for each contributor,
The apparatus has a psychological keyword dictionary part in which psychological keywords are registered in advance for each psychological state,
The device
For each contributor, a first step of acquiring comment sentences including the target keyword in time series;
For each contributor, if the comment text includes a psychological keyword of the psychological keyword dictionary means, a second step of outputting the psychological state of the psychological keyword;
For each contributor, a third step of detecting a transition phase in which the prior psychological state and the backward psychological state are different;
For each contributor, a fourth step of extracting a transition word by morphological analysis from a comment sentence based on the backward psychological state detected by the transition phase detection means;
A fifth step of registering a transition word that appears at a frequency equal to or higher than a predetermined threshold among the transition words as a psychological keyword based on the backward psychological state in the psychological keyword dictionary means is provided.

  According to the program, apparatus, and method of the present invention, it is possible to update a dictionary of words for which a user's psychological state should be extracted from comment text posted to an SNS for a specified product service.

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 transmitted 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 an appearance frequency table | surface for every transition word counted by the psychological keyword update part.

  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.
Of course, the psychological transition analysis apparatus 1 may be one in which comment sentences are stored 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, in many comment sentences, those including or not including quoted addresses (user addresses of other users, such as account names, reply addresses, and comment addresses in SNS) are mixed.

  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 apparatus 1 includes a psychological keyword dictionary unit 10, a comment sentence acquisition unit 11, a psychological state determination unit 12, a transition phase detection unit 13, a transition word extraction unit 14, and a psychological keyword update together with a communication interface unit. Part 15. 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 section 10]
The psychological keyword dictionary unit 10 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: Interest-> Desire: Desire-> Memory: Memory->
Action stage: Action: Action

  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 10 registers a psychological keyword for the target keyword (for example, “a company smartphone”) for each psychological state (At, ID, M, Ac).
Attention: Advertising, CM, release, new product, ...
Interest state: Lineup, HP, friends, pamphlet, ...
Desired state: price, design, want, CM, ...
Memory state: shop, exhibition, real thing, preview, ...
Behavioral state: MNP, model change, compliment, buy ...
This is a dictionary in which words characteristically expressed in each psychological state are registered for the target keyword.

The psychological keyword dictionary unit 10 may be basically manually created in advance at the initial stage.
The psychological keyword dictionary unit 10 is created for each target keyword (for example, a keyword for a product service), but may be created for each category of a product service (car, service, terminal, etc.), for example. Further, it may be created as a common dictionary for all target keywords.

[Comment text acquisition unit 11]
The comment text acquisition unit 11 acquires the comment text from the SNS site server 2 for each user address (contributor) using the target keyword (for example, “a company smartphone”) as a search key in time series. The target keyword may be, for example, a product service name. This target keyword is set for a system user, for example, a promotion person in charge of a company. The acquired comment text is output to the psychological state determination unit 12.

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

  According to FIG. 3, various comment texts of a large number of users are represented for the target keyword (a company smartphone).

According to FIG. 3, it is assumed that the psychological transition analysis apparatus 1 has analyzed the psychological state included in the comment text for the target keyword “a company smartphone”. 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."
User @AAA “Are you going to release a new product from company a?”
User @AAA "Do not watch CM of a company's smartphone well."
User @BBB "I wonder if I will change to a company smartphone"
User @AAA "A company's smartphone seems convenient! I want!"
User @DEF "New a company smartphone, easy to use and recommended"
User @AAA “A company's smartphone CM is doing again”
・ ・ ・ 「・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・」
User @AAA "Let's see a company smartphone at the shop this time"
・ ・ ・ 「・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・ ・」

  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 transmitted from the user @AAA including the target keyword “a company smartphone” is shown.
User @AAA “Are you going to release a new product from company a?”
User @AAA "Do not watch CM of a company's smartphone well."
User @AAA “It seems to be convenient for company a smartphone!
User @ AAA “A company's smartphone CM is doing again”
... "..."
User @AAA "Looking at a company's smartphone next time in the shop."
... "..."
User @AAA "I finally purchased a company smartphone!"
User @AAA "I can use a smartphone of company a"
... "..."

[Psychological state determination unit 12]
When the psychological keyword of the psychological keyword dictionary unit 10 is included in the comment text for each contributor, the psychological state determination unit 12 outputs the psychological state of the psychological keyword. As a result, the psychological state determination unit 12 determines the contributor's psychological state with respect to the target keyword (product service keyword). The determined psychological state is output to the transition phase detection unit 13.

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

From the comment sentence including the target keyword “Company a smartphone” and the psychological keyword “new product”, it can be estimated that the user is in an attention state.
From the comment text including the target keyword “Company a” and the psychological keyword “lineup”, it can be estimated that the user is in an interest state.
From the comment text including the target keyword “Company a smartphone” and the psychological keyword “I want”, it can be estimated that the user is in the Desire state.
From the comment text including the target keyword “a company smartphone” and the psychological keyword “CM”, it can be estimated that the user is in an interest state.
From the comment text including the target keyword “a company smartphone” and the psychological keywords “shop” and “preview”, it can be estimated that the user is in a memory state.
From the comment text including the target keyword “a company smartphone” and the psychological keyword “purchase”, it can be estimated that the user is in an action state.
From the comment sentence including the target keyword “Company a smartphone” and the psychological keyword “usable”, it can be estimated that the user is in an action 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 appearance frequency. 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.
“A company's new smartphone will be released”
New work = A, release = A
A = 2, I = 0, D = 0, M = 0, A = 0
Likelihood of A = 100%

[Transition phase detector 13]
The transition phase detection unit 13 detects a transition phase in which the prior psychological state and the backward psychological state are different for each poster. And the transition word extraction part 14 outputs that to the transition word extraction part 14, when a psychological state changes for every contributor by comparing a prior psychological state and a back psychological state.

The transition phase detection 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 adjust the psychological transition by assigning numerical values that increase in the order of A->I->D->M-> A. 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)
It is also preferable that the transition phase detection 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. Here, the psychological state determination unit 12 also outputs the posting time of the comment text including the psychological keyword together with the psychological state. Thus, the transition phase detection unit 13 can register the elapsed time interval between the psychological states arranged in time series. And when there is a long time difference between the previous psychological state and the backward psychological state, the transition phase detecting unit 13 may adjust the numerical value of the psychological state so that the psychological state is not transitioning or going backward. preferable.

[Transition word extraction unit 14]
The transition word extraction unit 14 extracts a transition word by morphological analysis from the comment text based on the backward psychological state detected by the transition phase detection unit 13 for each contributor. `` Morphological analysis '' means that a natural language sentence in a submitted sentence is divided into columns of morpheme (Morpheme), which is the smallest unit having meaning as a language, using a morpheme word dictionary and dependency dictionary, and each part of speech A technique for discriminating. By this analysis, for example, only morphemes of nouns and adjectives can be extracted as keywords.

There is a high possibility that a comment sentence posted when the psychological state transitions includes a word characterizing the psychological state. In addition, it is considered that many users use similar words in the transition phase between psychological states.
For example, the word “I want” is likely to appear immediately after the transition from the interest state to the desire state. On the other hand, when the time has passed for a while after the transition to the desire state, the possibility that the word “want” appears will be low.
Similarly, for example, the word “Bought” is likely to appear immediately after the transition from the memory state to the action state. On the other hand, when the time has passed for a while after the transition to the action state, the possibility that the word “Bought” appears is low.

  The transition word extracting unit 14 extracts a comment sentence for extracting a transition word from a predetermined number (for example, nb) of comment sentences after the backward psychological state and / or a predetermined number (for example, na) before the forward psychological state. The comment text. That is, by extracting transition words not only from the comment text at the transition point but also from a plurality of preceding and following comment texts, the registration range of the transition word in the dictionary can be expanded.

For example, it is assumed that each comment sentence has a psychological state as follows.
At, At, At, I, D, D, D, M, M, Ac, Ac,.
Here, if only the predetermined number nb = 1 after the backward psychological state, only the following comment sentences are extracted.
At, At, At, I, D, D, D, M, M, Ac, Ac,.
↓ ↓ ↓ ↓ ↓
At, I, D, M, Ac
Further, assuming that the predetermined number na = 1 before the forward psychological state and the predetermined number nb = 1 after the rear psychological state, only the following comment sentences are extracted.
At, At, At, I, D, D, D, M, M, Ac, Ac,.
↓ ↓ ↓ ↓ ↓ ↓ ↓ ↓
At, At, I, D, D, M, M, Ac

[Psychological keyword update unit 15]
The psychological keyword update unit 15 registers, in the psychological keyword dictionary unit 10, a transition word that appears at a frequency (statistical index) equal to or higher than a predetermined threshold among the transition words as a psychological keyword based on the backward psychological state.

  FIG. 6 is an appearance frequency table for each transition word counted by the psychological keyword update unit.

According to FIG. 6, for each psychological state, the transition word having the highest appearance frequency is represented by a broken line ○. These transition words are registered in the psychological keyword dictionary unit 10 as psychological keywords based on the psychological state.
(1) With regard to the attention state At, the appearance frequency of “new product” is the highest. Therefore, in this case, the transition word “new product” is registered in the attention state At.
(2) For the interest state I, the appearance frequency of “I want” is the highest. However, for “desired”, the appearance frequency of the desire state D is higher than the appearance frequency of the interest state I. Therefore, in this case, the transition word “I want” is registered in the desire state D.
(3) Regarding the interest state I, the appearance frequency of “release” is the second highest. However, for “release”, the appearance frequency of the interest state I is higher than the appearance frequency of the attention state At. Therefore, in this case, “release” is deleted from the attention state At, and the transition word “release” is registered in the interest state I.
(4) In the desire state D, the frequency of appearance of “convenient” is high in addition to “desired” (for example, when the threshold is 60). Therefore, in this case, the transition word “convenient” is registered in the desire state D.
(5) For the behavioral state Ac, the frequency of occurrence of “purchase” is the highest. Therefore, in this case, the transition word “purchase” is registered in the action state Ac.
Finally, according to FIG. 6, “new product” for the attention state, “release” for the interest state, “want” for the desire state, and “purchase” for the behavior state are newly registered in the psychological keyword dictionary unit 11. The

  The psychological keyword update unit 15 uses, for example, an Akaike information criterion (AIC (Akaike's Information Criterion)) or a χ-square value as a statistical index of words that appear characteristically for each psychological state. It may be calculated using.

  As described above in detail, according to the program, the apparatus, and the method of the present invention, the word dictionary in which the user's psychological state should be extracted from the comment text posted to the SNS for the specified product service is updated. can do.

  According to the present invention, characteristic words that appear frequently in the comment text in the transition phase are registered in the dictionary as transition words that appear in the psychological state. On the other hand, words that frequently appear in comment sentences other than the transition phase are excluded because they do not contribute to the transition of the psychological state and have a high possibility of noise. According to the present invention, words having a high appearance frequency are not detected equally in all psychological state phases, but are detected only in the psychological state transition phase. Therefore, the dictionary including the words for detecting the psychological state is updated assuming that only the phase transition point of the purchase psychological phase that changes in time series is emphasized.

  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 10 Psychological keyword dictionary part 11 Comment sentence acquisition part 12 Psychological state determination part 13 Transition phase detection part 14 Transition word extraction part 15 Psychological keyword update part 2 SNS site server 3 Terminal

Claims (7)

A program that causes a computer mounted on the device to function so as to analyze a user's psychological transition regarding a target keyword from a group of comment sentences transmitted for each contributor,
Psychological keyword dictionary means for registering psychological keywords in advance for each psychological state;
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 of the psychological keyword dictionary means is included in the comment text, the psychological state determining means for outputting the psychological state of the psychological keyword,
For each contributor, a transition phase detecting means for detecting a transition phase in which the prior psychological state and the backward psychological state are different,
For each contributor, from a comment sentence based on the backward psychological state detected by the transition phase detecting means, a transition word extracting means for extracting a transition word by morphological analysis;
The computer is caused to function as a psychological keyword update unit that registers a transition word that appears at a frequency equal to or higher than a predetermined threshold among the transition words as a psychological keyword based on a backward psychological state in the psychological keyword dictionary unit. program. The target keyword is a keyword for product service,
The program according to claim 1, wherein the psychological state determination unit causes a computer to function so as to determine a contributor's psychological state with respect to the keyword of the product service. The psychological keyword dictionary means that the psychological state corresponds to an AIDMA (Attention: attention-> Interest: interest-> Desire: desire-> Memory: memory-> Action) model, and for each psychological state, The program according to claim 1 or 2, wherein the computer functions so as to register a psychological keyword for the keyword. The transition phase detection means includes
For psychological states, assign numerical values that increase in the order of A->I->D->M-> A,
As psychological transitions in time series, the psychological values are arranged in time series,
4. The program according to claim 3, wherein the computer is caused to function so as to detect a transition phase by using a numerical value arranged in time series as a moving average value in a predetermined range. The transition word extracting means causes the computer to function so that the comment text for extracting the transition word is a predetermined number of comment text after the backward psychological state and / or a predetermined number of comment text before the front psychological state. The program according to any one of claims 1 to 4, wherein: A device that analyzes a user's psychological transition related to 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;
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 of the psychological keyword dictionary means is included in the comment text, the psychological state determining means for outputting the psychological state of the psychological keyword,
For each contributor, a transition phase detecting means for detecting a transition phase in which the prior psychological state and the backward psychological state are different,
For each contributor, from a comment sentence based on the backward psychological state detected by the transition phase detecting means, a transition word extracting means for extracting a transition word by morphological analysis;
An apparatus comprising psychological keyword updating means for registering a transition word appearing at a frequency equal to or higher than a predetermined threshold among the transition words as a psychological keyword based on a backward psychological state in the psychological keyword dictionary means. A psychological transition analysis method of a device that analyzes a user's psychological transition related to a target keyword from a group of comment sentences transmitted for each contributor,
The apparatus has a psychological keyword dictionary part in which psychological keywords are registered in advance for each psychological state,
The device is
For each contributor, a first step of acquiring comment sentences including the target keyword in time series;
For each contributor, when the psychological keyword of the psychological keyword dictionary means is included in the comment sentence, a second step of outputting the psychological state of the psychological keyword;
For each contributor, a third step of detecting a transition phase in which the prior psychological state and the backward psychological state are different;
For each contributor, a fourth step of extracting a transition word by morphological analysis from a comment sentence based on a backward psychological state detected by the transition phase detection means;
And a fifth step of registering a transition word that appears at a frequency equal to or higher than a predetermined threshold among the transition words as a psychological keyword based on a backward psychological state in the psychological keyword dictionary means. Psychological transition analysis method.

Images