JP5876642B2 - Text file evaluation device, text file evaluation method, and computer program - Google Patents

Description

  The present invention relates to a text file evaluation device, a text file evaluation method, and a computer program.

  In recent years, a “reputation analysis service” that analyzes the “reputation” included in the text file by searching for text files sent and posted by individuals on the Internet site and scoring the content of the text files has been provided. Yes. In the conventional sentence file evaluation technology that can be used for the reputation analysis service, the evaluation level of the sentence file is determined by performing morphological analysis on the sentence file and scoring the meaning of the morpheme (for example, patent document) 1).

Japanese Patent No. 3962382

  However, in the conventional text file evaluation technique described above, the user (text creator) cannot determine the evaluation level based on the intention of using the pictogram for the text file including the character string and the pictogram. In particular, when a posted text is created by a mobile phone, the user may use a pictograph that expresses emotion or a pictograph that emphasizes a word in order to easily understand the intention of the text. Therefore, it is important to reflect the contents intended by the pictograph on the evaluation level for the text file including the character string and the pictograph. In addition, even with the same pictogram, it is conceivable that the strength expressed by the pictogram varies depending on the user. For this reason, it is desirable to reflect the content intended by the pictogram on the evaluation level according to the user.

  The present invention has been made in consideration of such circumstances, and when calculating the evaluation level of a text file including a character string and a pictogram, the contents intended by the pictogram are reflected in the evaluation level according to the user. It is an object of the present invention to provide a text file evaluation device, a text file evaluation method, and a computer program.

  In order to solve the above-mentioned problem, the text file evaluation device according to the present invention is configured so that an evaluation level of a text file including a character string and a pictogram described by a specific user is expressed by an evaluation level for the evaluation pictogram and an adverbial magnification for the adverbial pictogram Is a text file evaluation device that calculates using a product of the user information acquisition unit that acquires the frequency with which a specific user uses pictograms and the frequency with which the specific user creates text files, and the frequency with which the specific user uses pictograms And a pictographic magnification operation unit for manipulating an adverbial magnification applied to the specific user based on the frequency with which the specific user creates a text file.

  In the sentence file evaluation device according to the present invention, the pictogram magnification operation unit reduces the adverbial magnification as the text file creation frequency increases, and decreases the adverbial magnification as the pictogram use frequency increases. .

  In the text file evaluation device according to the present invention, the user information acquisition unit includes an evaluation target text file total count unit that counts the total number of evaluation target text files created by a specific user within a predetermined period, and a specific user within a predetermined period. The total number of pictographs for counting the total number of pictographs included in the evaluation target text file created in the above, and the pictogram for calculating the average number of pictographs used by dividing the total number of pictographs by the total number of evaluation target text files for a specific user A use number average value calculation unit, and an all-user pictogram use number average value calculation unit that calculates an average value for the average number of pictograms used by all users. A comparison unit that compares the number average value with the average number of pictograms used by all users, and a comparison result of the comparison unit and the evaluation target text file for the specific user. Based on yl total, and having a a adverbial magnification operation determining unit that determines an adverbial magnification operation to be applied to the specific user.

  The text file evaluation method according to the present invention is a text that calculates the evaluation level of a text file including a character string and a pictogram described by a specific user by using the product of the evaluation level for the evaluation pictogram and the adverbial magnification for the adverbial pictogram. It is a file evaluation method, the step of acquiring the frequency with which a specific user uses pictograms, the step of acquiring the frequency with which a specific user creates a text file, the frequency with which the specific user uses pictograms, and the specific user with a text file Manipulating the adverbial magnification applied to the specific user based on the frequency of creating

A computer program according to the present invention is a computer for calculating an evaluation level of a text file including a character string and a pictogram described by a specific user using a product of an evaluation level for the evaluation pictogram and an adverbial magnification for an adverbial pictogram. A step of acquiring a frequency at which a specific user uses a pictogram, a step of acquiring a frequency at which the specific user creates a text file, a frequency at which the specific user uses a pictogram, and the specific user creating a text file A computer program for causing a computer to execute an adverbial magnification to be applied to the specific user based on the frequency of performing the operation.
Thereby, the above-mentioned sentence file evaluation apparatus can be realized using a computer.

  According to the present invention, when calculating the evaluation level of a text file including a character string and a pictogram, the content intended by the pictogram can be reflected in the evaluation level according to the user.

It is a block diagram which shows the structure of the text file evaluation apparatus 1 which concerns on one Embodiment of this invention. It is a structural example of the pictogram dictionary part 20 shown in FIG. It is a block diagram of the user information acquisition part 30 shown in FIG. It is a block diagram of the pictogram magnification operation part 50 shown in FIG. It is an example of the rule of adverbial magnification operation which concerns on one Embodiment of this invention. It is an example of an evaluation object text file. It is a flowchart which shows the text file evaluation level calculation procedure which concerns on one Embodiment of this invention.

Hereinafter, embodiments of the present invention will be described with reference to the drawings.
FIG. 1 is a block diagram showing a configuration of a text file evaluation apparatus 1 according to an embodiment of the present invention. In FIG. 1, a text file evaluation apparatus 1 includes a communication interface unit 11, a text file storage unit 12, a morpheme analysis unit 13, a character string extraction unit 14, a character string level search unit 15, a character string dictionary unit 16, and a pictogram dictionary unit 20. , Pictogram extraction unit 21, pictograph level search unit 22, adverbial magnification search unit 23, dependency analysis unit 24, evaluation level determination unit 25, user information acquisition unit 30, user information storage unit 40, and pictogram magnification operation unit 50 Have.

  The communication interface unit 11 is connected to a communication network. The communication network may be any network capable of data communication, and may be connected by a wireless line or a wired line. The communication interface unit 11 acquires a text file to be evaluated via a communication network. For example, the communication interface unit 11 acquires a text file to be evaluated from an Internet site. As Internet sites, for example, blogs (Web Blog), word-of-mouth sites, Q & A communities, SNS (Social Networking Service), and COI (Community Of Interest) sites as websites that store text files sent and posted by individuals. Etc. are available. Alternatively, the communication interface unit 11 acquires a text file to be evaluated from a site for mobile phones. A site similar to the Internet can be used as a site for mobile phones.

  Here, “text file” and “pictogram” in the present embodiment will be described. In the present embodiment, the “sentence file” includes a character string as text and an “pictogram”. “Emoji” refers to a simplified picture used to convey meaning (eg, emotional expression). This is also called a pictogram, for example, and anyone (for example, a foreigner who cannot understand the language) can understand the meaning of the display regardless of the existing language system. Pictographs are used especially for sending and receiving mail between mobile phones. For example, various icons such as “smile”, “crying face”, “heart mark” for expressing emotions are prepared. Pictographs are used as icons for easily expressing emotions when writing mail containing text.

  “Emoji” has a character code different from that of general text. Usually, the text means ASCII code such as half-width alphanumeric characters, JIS code or shift JIS such as Japanese Kanji, Unicode for multilingual, and the like. On the other hand, each mobile phone communication carrier uniquely determines a pictogram and its character code so that the pictogram does not overlap with these character codes. Therefore, when the telecommunications carrier or the mobile phone manufacturer is different, it is not always possible to display the same pictograph. In addition, a specific communication carrier may transmit pictogram contents after an escape code. This escape code means that “the subsequent data is a pictograph”. Therefore, a pictograph cannot be displayed by a text editor as an application of a personal computer. Thus, text and pictograms have different character systems.

  Returning to FIG. The text file storage unit 12 stores the text file to be evaluated acquired by the communication interface unit 11.

  The morpheme analysis unit 13 reads a text file from the text file storage unit 12 and decomposes the read text file into morphemes. The morpheme analysis unit 13 outputs the decomposed morpheme to the character string extraction unit 14 and the pictogram extraction unit 21.

  The character string dictionary unit 16 stores a set of a specific character string as an evaluation character string and an evaluation level. As the evaluation level, either “positive” or “negative” is set. Alternatively, a plurality of evaluation levels may be set in stages for each of “positive” and “negative”.

  The character string extraction unit 14 uses the character string dictionary unit 16 to extract a morpheme corresponding to the evaluation character string from the morphemes input from the morpheme analysis unit 13. The character string extraction unit 14 outputs an evaluation character string composed of the extracted morphemes to the character string level search unit 114.

  The character string level search unit 15 acquires an evaluation level for the evaluation character string input from the character string extraction unit 14 from the character string dictionary unit 112. The character string level search unit 15 outputs the acquired evaluation level to the evaluation level determination unit 25.

  The pictogram dictionary unit 20 stores a set of a specific pictogram as an evaluation pictogram and an evaluation level. Furthermore, the pictogram dictionary unit 20 stores a set of a specific pictogram as an adverbial pictogram and an adverbial magnification. FIG. 2 shows a configuration example of the pictogram dictionary unit 20. In the example of FIG. 2, three evaluation pictograms “Title: Glitter”, “Title: Heart”, and “Title: Tears” are registered. The evaluation level “positive” is set for the evaluation pictograms “title: glitter” and “title: heart”. The evaluation level “negative” is set for the evaluation pictogram “Title: Tears Polo”. In the example of FIG. 2, one adverbic pictogram “title: emphasis” is registered. The adverbial magnification “1.2” is set for the adverbic pictograph “title: emphasis”.

  The pictogram extraction unit 21 uses the pictogram dictionary unit 20 to extract a morpheme corresponding to the evaluation pictogram from the morphemes input from the morpheme analysis unit 13. The pictograph extraction unit 21 outputs an evaluation pictograph composed of the extracted morphemes to the pictograph level search unit 22. Further, the pictogram extraction unit 21 uses the pictogram dictionary unit 20 to extract morphemes corresponding to adverb pictograms from the morphemes input from the morpheme analysis unit 13. The pictogram extraction unit 21 outputs an adverbial pictograph composed of the extracted morphemes to the adverbial magnification search unit 23.

  The pictogram level search unit 22 acquires an evaluation level for the evaluation pictogram input from the pictogram extraction unit 21 from the pictogram dictionary unit 20. The pictogram level search unit 22 outputs the acquired evaluation level to the evaluation level determination unit 25.

  The adverbial magnification search unit 23 acquires the adverbial magnification for the adverbial pictogram input from the pictogram extraction unit 21 from the pictogram dictionary unit 20. The adverbial magnification search unit 23 outputs the acquired adverbial magnification to the dependency analysis unit 24.

  The dependency analysis unit 24 detects an evaluation pictogram or an evaluation character string that is a dependency of an adverbial pictogram. The dependency analysis unit 24 outputs the detection result of the dependency of adverbial pictograms together with the adverbial magnification to the evaluation level determination unit 25.

  In addition, it is possible to determine which character string or pictogram is dependent on an adverb by using an existing syntactic analysis technique. The parsing process is also called a parser and analyzes the grammatical relationship between sentences. In syntax analysis, a tree-structured data structure in a text file and a lexical expression based on lexical analysis are input, and a data structure such as a syntax tree or an abstract syntax tree is generated. Thus, it is possible to determine which evaluation character string or evaluation pictogram the adverbial pictogram is dependent on.

  The evaluation level determination unit 25 determines the evaluation level of the text file based on the sum of the evaluation levels of all the evaluation character strings and all the evaluation pictograms. At this time, the evaluation level of the evaluation pictogram or evaluation character string that is a dependency of the adverbial pictogram is multiplied by the adverbial magnification of the adverbial pictogram. The adverbial magnification is operated by the pictogram magnification operation unit 50. The evaluation level determination unit 25 stores the determined evaluation level in the text file storage unit 12 in association with the text file.

  The user information acquisition unit 30 acquires user information using a text file (evaluation target text file) read from the text file storage section 12 by the morpheme analysis section 13. The user information storage unit 40 stores user information for each user. The pictogram magnification operation unit 50 uses the user information storage unit 40 to operate the adverbial magnification for each user.

  FIG. 3 is a block diagram of the user information acquisition unit 30 shown in FIG. In FIG. 3, the user information acquisition unit 30 includes an evaluation object sentence file total count unit 31, a pictograph total count unit 32, a pictograph use number average value calculation unit 33, and an all user pictogram use number average value calculation unit 34.

  The evaluation object sentence file total counting unit 31 counts the total number of evaluation object sentence files created by the specific user within a certain period. Here, the evaluation target sentence file created by the specific user includes a sentence file newly created by the specific user and a sentence file obtained by updating the already created sentence file. The total number of evaluation target text files of a specific user represents the frequency with which the specific user creates a text file.

  The pictograph total number counting unit 32 counts the total number of pictographs included in the evaluation target sentence file created by the specific user within a certain period. The pictorial character usage number average value calculation unit 33 calculates the average pictorial character usage number for the specific user by dividing the pictorial character total number by the total text file to be evaluated. The all-user pictogram usage average value calculation unit 34 calculates an average value of the pictogram usage average value of all users.

  The user information storage unit 40 stores the total number of evaluation target sentence files and the average number of pictograms used for each user. Furthermore, the user information storage unit 40 stores the average number of all user pictograms used.

  FIG. 4 is a block diagram of the pictogram magnification operation unit 50 shown in FIG. In FIG. 4, the pictogram magnification operation unit 50 includes a comparison unit 51 and an adverbial magnification operation determination unit 52.

  The pictogram magnification operation unit 50 acquires necessary information from the user information storage unit 40. The comparison unit 51 compares the average number of pictograms used by a specific user with the average value of all user pictograms used. The adverbial magnification operation determination unit 52 determines the adverbial magnification operation to be applied to the specific user based on the comparison result by the comparison unit 51 and the total number of evaluation target sentence files for the specific user.

  FIG. 5 is an example of rules for adverbial magnification operations according to the present embodiment. In the rule of adverbial magnification operation shown in FIG. 5, the adverbial magnification applied to the specific user is changed according to the relationship between the pictogram usage frequency and the text file creation frequency for the specific user. More specifically, the adverbial magnification is decreased as the sentence file creation frequency is higher, and the adverbial magnification is decreased as the pictogram usage frequency is higher.

  FIG. 5 shows that the smaller the value of the circled number, the smaller the adverbial magnification. In FIG. 5, when the text file creation frequency is high and the pictogram usage frequency is high (in the case of the circled number “1”), the adverbial magnification is made the smallest. If the text file creation frequency is low and the pictogram usage frequency is high (in the case of the circled number “2”), the adverbial magnification is set to the second smallest. If the text file creation frequency is high and the pictogram usage frequency is low (in the case of the circled number “3”), the adverbial magnification is made the third smallest. When the text file creation frequency is low and the pictogram usage frequency is low (in the case of the circled number “4”), the adverbial magnification is maximized.

  The determination as to whether the specific user's pictograph usage frequency is high or low is based on the comparison result by the comparison unit 51. Specifically, when the average number of pictograms used by a specific user is equal to or greater than the average value of all user pictograms used, it is determined that the frequency of use of pictograms by the specific user is high. On the other hand, when the average number of pictograms used by a specific user is less than the average number of pictographs used by all users, it is determined that the pictograph usage frequency of the specific user is low.

  The determination as to whether the specific user's text file creation frequency is high or low is based on the total number of evaluation target text files of the specific user. Specifically, a reference value for the total number of evaluation target sentence files is defined, and when the total number of evaluation target sentence files of a specific user is equal to or greater than the reference value, it is determined that the frequency of creating the specific user's sentence file is high. On the other hand, when the total number of evaluation target text files of the specific user is less than the reference value, it is determined that the frequency of generating the text file of the specific user is low.

  The reference value for the total number of evaluation target text files can be set arbitrarily. For example, about 60% of users who have blogs update their blogs once a week. A reference value related to the total number of evaluation target sentence files may be determined based on this information.

  Alternatively, a plurality of reference values regarding the total number of evaluation target text files may be set to determine the text file creation frequency. For example, the judgment categories are “sometimes created” and “every day created”, the “sometimes created” judgment criterion is set to a frequency of less than three times a month, for example, and the “daily creation” judgment criterion is set to, for example, a week The frequency is at least twice (8 times a month).

  The pictogram magnification operation unit 50 outputs an instruction for adverbial magnification operation determined by the adverbial magnification operation determination unit 52 to the evaluation level determination unit 25. The evaluation level determination unit 25 changes the adverbial magnification applied to the specific user in accordance with the adverbial magnification operation command input from the pictogram magnification operation unit 50.

  As a specific example, the adverbial magnification “1.2” is set for the adverbic pictogram “title: emphasis” registered in the pictogram dictionary unit 20 of FIG. 2 ”is used after being changed according to the adverbial magnification operation instruction. For example, in FIG. 5, when the text file creation frequency is high and the pictogram usage frequency is high (in the case of the circled number “1”), the adverbial magnification operation is 0.5 times. When the text file creation frequency is low and the pictogram usage frequency is high (in the case of the circled number “2”), the adverbial magnification operation is 0.8 times. When the text file creation frequency is high and the pictogram usage frequency is low (in the case of the circled number “3”), the adverbial magnification operation is set to 1.0. If the text file creation frequency is low and the pictogram usage frequency is low (in the case of the circled number “4”), the adverbial magnification operation is 1.2 times.

  The evaluation level determination unit 25 multiplies the adverbial magnification operation by the original adverbial magnification “1.2” of the adverbic pictogram “title: emphasis”. Thus, when the text file creation frequency is high and the pictogram usage frequency is high (in the case of the circled number “1”), the adverbial magnification of the adverb pictogram “title: emphasis” is “1.2 × 0. 5 = 0.6 ”. When the text file creation frequency is low and the pictogram usage frequency is high (in the case of the circle numeral “2”), the adverbial magnification of the adverb pictogram “title: emphasis” is “1.2 × 0.8 = 0. .96 ". When the text file creation frequency is high and the pictogram usage frequency is low (in the case of the circle numeral “3”), the adverbial magnification of the adverb pictogram “title: emphasis” is “1.2 × 1.0 = 1”. .2 ". When the text file creation frequency is low and the pictogram usage frequency is low (in the case of the circle numeral “4”), the adverbial magnification of the adverb pictogram “title: emphasis” is “1.2 × 1.2 = 1”. .44 ".

  Next, a method for calculating the evaluation level of the text file according to the present embodiment will be specifically described with reference to FIG. FIG. 6 is an example of an evaluation target sentence file. FIG. 6A shows an example of a text file created by a specific user. FIG. 6B shows the result of decomposing the text file of FIG. 6A into morphemes. A morpheme break is indicated by /.

  FIG. 6C shows the dependency analysis result of the adverbial pictogram for the morpheme of FIG. In FIG. 6C, the adverbic pictograph “title: emphasis” 103 depends on the character string “disappointing” 102. The adverbic pictograph “Title: Emphasis” 113 depends on the character string “Bakayaro” 111.

Here, it is assumed that the following “set of evaluation character string and evaluation level” is registered in the character string dictionary unit 16.
Evaluation string “disappointing”: −1 (negative)
Evaluation character string "Bakayaro": -1 (negative)

Also, it is assumed that the following “a set of evaluation pictograms and evaluation levels” and “a set of adverbic pictograms and adverbial magnification” are registered in the pictogram dictionary unit 20.
Evaluation pictogram "Title: Tears Polo": -1 (negative)
Adverb pictogram “Title: Emphasis”: 1.2 times (adverbial magnification)

The evaluation level determination unit 25 calculates the evaluation level for the text file in FIG. 6A by using the evaluation level and the adverbial magnification corresponding to the evaluation character string, the evaluation pictogram, and the adverbial pictogram in FIG. To do. At this time, the adverbial magnification is changed using the adverbial magnification operation for the specific user. In this example, it is assumed that the adverbial magnification operation is 0.5 times. As a result, the evaluation level for the text file in FIG. 6A is calculated by the following equation to be “−3.2”.
(Evaluation Pictogram “Title: Tears Polo” 101 Evaluation Level “−1”) + ((Evaluation Character String “Disappointing” 102 Evaluation Level “−1”) × (Adverbic Pictogram “Title: Emphasis” 103 Adverb Magnification “1.2”) × (Adverbial magnification operation magnification “0.5”)) + (Evaluation level “−1” of evaluation character string “Frustrating” 104) + ((Evaluation character string “Bakayaro” 111 Evaluation level “−1”) × (adverbic pictogram “title: emphasis” 113 adverbial magnification “1.2”) × (adverbial magnification operation magnification “0.5”)) = (− 1) + (− 1 × 1.2 × 0.5) + (− 1) + (− 1 × 1.2 × 0.5) = − 3.2

  Next, a text file evaluation level calculation procedure according to the present embodiment will be described with reference to FIG. FIG. 7 is a flowchart showing a text file evaluation level calculation procedure according to this embodiment.

(S1) A text file including a character string and a pictograph is read.
(S2) User information is acquired using a text file.
(S3) The sentence file is decomposed into morphemes.
(S4) A morpheme corresponding to the evaluation character string is extracted using the character string dictionary.
(S5) The evaluation level for the extracted evaluation character string is searched using the character string dictionary.
(S6) Using the pictogram dictionary, morphemes corresponding to the evaluation pictogram are extracted.
(S7) The evaluation level for the extracted evaluation pictogram is searched using the pictogram dictionary.
(S8) Using the pictogram dictionary, search for adverbial magnification for the extracted adverbial pictogram.
(S9) The adverbial magnification of the specific user is operated using the user information.
(S10) An evaluation pictogram or evaluation character string that is a dependency of an adverbial pictogram is detected.
(S11) The evaluation level of the text file is determined based on the sum of the evaluation levels of all evaluation character strings and the evaluation levels of all evaluation pictograms. At this time, the evaluation level of the evaluation pictogram or the evaluation character string is multiplied by the adverbial magnification of the adverbial pictogram.
(S12) The evaluation level is associated with the sentence file.

  According to the above-described embodiment, the adverbial magnification operation to be applied to the specific user is determined according to the pictogram usage frequency of the specific user. As a result, when calculating the evaluation level of a text file including character strings and pictograms, the contents intended by the pictograms can be reflected in the evaluation level according to the user, and the same pictogram can be expressed by the pictograms by the user. Will be able to cope with different things.

  For example, users who use pictograms frequently are customary to use pictograms when writing text, so the pictograms in the text are not meant to emphasize content. . On the other hand, when a user who does not usually use pictograms uses pictograms, it can be said to emphasize the contents that he / she writes. As described above, the pictograms are used differently depending on the user, but according to the present embodiment, the pictogram can be weighted according to the user.

  Specifically, the weight of pictograms is set relatively low for users who use pictograms relatively. On the other hand, for a user who uses relatively few pictograms, the pictogram weight is set relatively high. Thus, by treating the pictograms as uniform weights, it is possible to prevent the evaluation level of the text file of the user who frequently uses pictograms from being positively or negatively applied. As a result, the accuracy of reputation analysis in the reputation analysis service can be expected to improve.

  Further, according to the present embodiment, the adverbial magnification operation to be applied to the specific user is determined according to the specific user's text file creation frequency. Thereby, when calculating the evaluation level of the text file including the character string and the pictogram, the contents intended by the pictogram can be reflected on the evaluation level according to the user. For example, a user who creates a text file every day tends to write more about his / her private life than to write special contents. On the other hand, a user who only occasionally creates a text file is likely to write only what he / she really wants to write. Therefore, when a user who creates a text file only occasionally uses pictograms, it is desirable to increase the weight of pictograms more than the user who creates text files every day. According to the present embodiment, this problem can also be solved.

  The text file evaluation apparatus 1 according to the present embodiment may be realized by dedicated hardware, or may be configured by a computer system such as a personal computer, and the text file evaluation apparatus 1 shown in FIG. The function may be realized by executing a program for realizing the function of each unit.

In addition, an input device, a display device, and the like (none of which are shown) are connected to the sentence file evaluation device 1 as peripheral devices. Here, the input device refers to an input device such as a keyboard and a mouse. The display device refers to a CRT (Cathode Ray Tube), a liquid crystal display device or the like.
Further, the peripheral device may be connected directly to the text file evaluation apparatus 1 or may be connected via a communication line.

As mentioned above, although embodiment of this invention was explained in full detail with reference to drawings, the specific structure is not restricted to this embodiment, The design change etc. of the range which does not deviate from the summary of this invention are included.
For example, the above-described embodiment can be similarly applied to a sentence file including text written in a language other than Japanese (for example, English) as long as it includes pictograms.

  In addition, the text file evaluation device may have a function of accumulating text files transmitted / posted by a user such as a mobile phone and releasing the same to a third party via a communication network.

Also, a program for realizing each step shown in FIG. 7 is recorded on a computer-readable recording medium, and the program recorded on the recording medium is read into a computer system and executed, thereby executing a sentence file evaluation process. May be performed. Here, the “computer system” may include an OS and hardware such as peripheral devices.
Further, the “computer system” includes a homepage providing environment (or display environment) if a WWW system is used.
“Computer-readable recording medium” refers to a flexible disk, a magneto-optical disk, a ROM, a writable nonvolatile memory such as a flash memory, a portable medium such as a DVD (Digital Versatile Disk), and a built-in computer system. A storage device such as a hard disk.

Further, the “computer-readable recording medium” means a volatile memory (for example, DRAM (Dynamic DRAM) in a computer system that becomes a server or a client when a program is transmitted through a network such as the Internet or a communication line such as a telephone line. Random Access Memory)), etc., which hold programs for a certain period of time.
The program may be transmitted from a computer system storing the program in a storage device or the like to another computer system via a transmission medium or by a transmission wave in the transmission medium. Here, the “transmission medium” for transmitting the program refers to a medium having a function of transmitting information, such as a network (communication network) such as the Internet or a communication line (communication line) such as a telephone line.
The program may be for realizing a part of the functions described above. Furthermore, what can implement | achieve the function mentioned above in combination with the program already recorded on the computer system, and what is called a difference file (difference program) may be sufficient.

DESCRIPTION OF SYMBOLS 1 ... Text file evaluation apparatus, 11 ... Communication interface part, 12 ... Text file storage part, 13 ... Morphological analysis part, 14 ... Character string extraction part, 15 ... Character string level search part, 16 ... Character string dictionary part, 20 ... Pictogram dictionary section, 21 ... Pictogram extraction section, 22 ... Pictogram level search section, 23 ... Adverbial magnification search section, 24 ... Dependency analysis section, 25 ... Evaluation level determination section, 30 ... User information acquisition section, 31 ... Evaluation target Text file total number counting unit, 32 ... Pictogram total number counting unit, 33 ... Pictogram usage average value calculation unit, 34 ... All user pictogram usage average value calculation unit, 40 ... User information storage unit, 50 ... Pictogram magnification operation unit, 51 ... Comparison part, 52 ... Adverbial magnification operation decision part

Claims (5)

A sentence file that calculates an evaluation level of a sentence file including a character string and a pictogram described by a specific user by using a product of an adverbial magnification for the adverbial pictogram and an evaluation level for the evaluation pictogram that is a dependency of the adverbial pictogram Evaluation device,
A text file storage unit for storing the text file;
A user information acquisition unit that acquires the frequency with which a specific user uses pictograms and the frequency with which a specific user creates a text file, using the evaluation target text file read from the text file storage unit ;
For each user, a user information storage unit that stores the frequency with which the user uses pictograms and the frequency with which the user creates sentence files;
The frequency at which a specific user uses pictograms and the frequency at which the specific user creates a text file are acquired from the user information storage unit, and the frequency at which the acquired specific user uses pictograms and the specific user creates a text file. An emoji magnification operation unit for manipulating an adverbial magnification applied to the specific user based on the frequency;
A sentence file evaluation device characterized by comprising:   2. The sentence file evaluation device according to claim 1, wherein the pictogram magnification operation unit reduces the adverbial magnification as the text file creation frequency increases, and decreases the adverbial magnification as the pictogram use frequency increases. . The user information acquisition unit
An evaluation object sentence file total counting unit for counting the total number of evaluation object sentence files created by a specific user within a certain period;
A pictogram total counting unit that counts the total number of pictograms included in the evaluation target sentence file created by the specific user within a certain period;
With respect to a specific user, the pictorial character usage number average value calculating unit that calculates the average pictorial character usage value by dividing the pictorial character total number by the total number of evaluation object text files;
An average value calculation unit for all user pictograms used to calculate an average value for the average number of pictograms used by all users,
The pictogram magnification operation unit is
A comparison unit that compares the average number of pictograms used by a specific user with the average number of pictographs used by all users;
An adverbial magnification operation determining unit that determines an adverbial magnification operation to be applied to the specific user based on a comparison result by the comparison unit and the total number of the evaluation target sentence files with respect to the specific user;
The sentence file evaluation apparatus according to claim 2, wherein: A text file storage unit, a user information acquisition unit, a user information storage unit, and a pictogram magnification operation unit, and the evaluation level of a text file including a character string and a pictograph described by a specific user is expressed as an adverb for an adverbial pictograph Is a sentence file evaluation method of a sentence file evaluation apparatus that calculates using a product of an objective magnification and an evaluation level for an evaluation pictogram that is a dependency of the adverbial pictogram,
The sentence file storage unit storing the sentence file;
The user information acquisition unit uses the evaluation target text file read from the text file storage unit to acquire the frequency with which a specific user uses pictograms and the frequency with which the specific user creates a text file ;
The user information storage unit stores, for each user, a frequency at which the user uses pictograms and a frequency at which the user creates a text file;
The pictogram magnification operation unit acquires the frequency with which a specific user uses pictograms and the frequency with which the specific user creates a text file from the user information storage unit, and the frequency with which the acquired specific user uses pictograms and the specification Manipulating the adverbial magnification applied to the specific user based on the frequency with which the user creates the sentence file;
A method for evaluating a text file, comprising: For calculating an evaluation level of a sentence file including a character string and a pictogram described by a specific user by using a product of an adverbial magnification for the adverbial pictogram and an evaluation level for the evaluation pictogram serving as a dependency of the adverbial pictogram A computer program,
Storing the sentence file in a sentence file storage unit;
Using the evaluation target sentence file read from the sentence file storage unit , obtaining a frequency at which a specific user uses pictograms and a frequency at which the specific user creates a sentence file ;
For each user, storing the frequency in which the user uses pictograms and the frequency in which the user creates a text file in the user information storage unit;
The frequency at which a specific user uses pictograms and the frequency at which the specific user creates a text file are acquired from the user information storage unit, and the frequency at which the acquired specific user uses pictograms and the specific user creates a text file. Manipulating the adverbial magnification applied to the specific user based on the frequency;
A computer program for causing a computer to execute.

Images