JP2014010820A - Document evaluation arrangement system and method, computer program, and recording medium - Google Patents

Abstract

PROBLEM TO BE SOLVED: To objectively evaluate each of a plurality of documents, and properly arrange the documents with respect to an arbitrary evaluation axis.SOLUTION: A document evaluation arrangement system 1 includes: input means 11 for receiving a plurality of contents each including a document; analysis means 12 for extracting a first related word group that is a related word group related to feature words that characterize an evaluation axis for evaluating the plurality of contents and a second related word group that is a related word group related to the document included in each of the plurality of contents, and determines the degree of relation between each of the plurality of contents and the evaluation axis on the basis of multiplicity between the extracted first related word group and the extracted second related word group; and relative position adjustment means 14 for determining coordinate candidates on the evaluation axis of each of the plurality of contents according to the determined degree of relation.

Description

  The present invention relates to a technical field of a document evaluation organization system and method, a computer program, and a recording medium that enable evaluation and organization suitable for the contents of a plurality of texts according to the contents of a plurality of input texts.

  As a technique related to this type of system, for example, a technique that supports extraction of other terms related to a specified term has been proposed. In particular, it describes that the use of a business-dependent n-term relation dictionary supports the extraction of related words in consideration of the relationship between terms (see Patent Document 1).

  Alternatively, when a keyword is visualized on a two-dimensional map, a keyword as a feature is extracted from one document, and the degree of relevance between the extracted keyword and a keyword extracted from another document is increased. Accordingly, a technique for calculating the distance between documents and determining the coordinates has been proposed (see Patent Document 2).

JP 2008-305078 A JP 2010-224625 A

  However, the above-described background art has a technical problem that there is room for improvement in that each of a plurality of documents is arranged and visualized with respect to an arbitrary evaluation axis.

  The present invention has been made in view of the above problems, for example, and can evaluate each of a plurality of documents objectively and appropriately arrange them with respect to an arbitrary evaluation axis. It is an object to provide a computer program and a recording medium.

  In order to solve the above problems, the document evaluation and organization system according to the present invention is characterized by an acquisition unit that acquires a plurality of contents each including a document and a characteristic word that characterizes an evaluation axis for evaluating the plurality of contents. A first related word group that is a related related word group, and a second related word group that is a related word group related to a document included in each of the plurality of contents, and the extracted first related word group and Based on the degree of overlap with the extracted second related word group, relevance determining means for determining relevance between each of the plurality of contents and the evaluation axis, and according to the determined relevance, Coordinate determining means for determining coordinate candidates on the evaluation axis of each of a plurality of contents.

  In order to solve the above problems, the document evaluation and organization method of the present invention is characterized by an acquisition step of acquiring a plurality of contents each including a document and a characteristic word that characterizes an evaluation axis for evaluating the plurality of contents. A first related word group that is a related related word group, and a second related word group that is a related word group related to a document included in each of the plurality of contents, and the extracted first related word group and Based on the degree of overlap with the extracted second related word group, a relevance determining step for determining relevance between each of the plurality of contents and the evaluation axis, and according to the determined relevance, A coordinate determining step of determining coordinate candidates on the evaluation axis of each of a plurality of contents.

  In order to solve the above problems, the computer program of the present invention is a feature word that characterizes an acquisition means for acquiring a plurality of contents each including a document and an evaluation axis for evaluating the plurality of contents. A first related word group that is a related word group related to, and a second related word group that is a related word group related to a document included in each of the plurality of contents, and the extracted first related word group And a degree-of-relationship between the plurality of contents and the evaluation axis based on the degree of overlap between the extracted second related word group and the degree of relevance; It is made to function as coordinate determination means for determining coordinate candidates on the evaluation axis of each of the plurality of contents.

  In order to solve the above problems, the recording medium of the present invention stores the computer program of the present invention.

  The effect | action and other gain of this invention are clarified from the form for implementing demonstrated below.

It is a block diagram which shows the structure of the evaluation organization system which concerns on an Example. It is an example of the image displayed on the display means which concerns on an Example. It is a flowchart which shows the label object display process which concerns on an Example. It is another example of the image displayed on the display means which concerns on an Example. It is a flowchart which shows the related degree calculation process which concerns on an Example. It is a conceptual diagram which shows the concept of the related word and associative word about an evaluation axis. It is a flowchart which shows the position adjustment process which concerns on an Example. It is another example of the image displayed on the display means which concerns on an Example. It is another example of the image displayed on the display means which concerns on an Example. It is another example of the image displayed on the display means which concerns on an Example.

  An embodiment relating to a document evaluation and organizing system of the present invention will be described.

(Embodiment of document evaluation organization system)
The document evaluation and organization system according to the embodiment is a related word group related to a feature word that is a word that characterizes an acquisition axis for acquiring a plurality of contents each including a document and an evaluation axis for evaluating the plurality of contents. A first related word group and a second related word group that is a related word group related to a document included in each of the plurality of contents are extracted, and the extracted first related word group and the extracted second relation Relevance determining means for determining the relevance between each of the plurality of contents and the evaluation axis based on the degree of overlap with the word group, and the evaluation of each of the plurality of contents according to the determined relevance Coordinate determining means for determining coordinate candidates on the axis.

  The acquisition unit acquires a plurality of contents each including a document. Here, the “document” is not limited to a sentence including a subject and a predicate, and may include only a clause, a phrase, a word, and the like. The “content” may include, for example, an image in addition to the document.

  The acquisition unit may acquire the content based on, for example, information input by the user via a keyboard or the like. For example, the acquisition unit may acquire the content by performing a known voice recognition process on the voice data corresponding to the voice uttered by the user. You may get it.

  For example, the relevance determination means including a memory, a processor, etc. includes a first related word group that is a related word group related to a feature word that is a word that characterizes an evaluation axis for evaluating a plurality of contents, and a plurality of contents A second related word group that is a related word group related to a document included in each document is extracted, and a plurality of contents are based on the degree of overlap between the extracted first related word group and the extracted second related word group. The degree of association between each and the evaluation axis is determined.

  The “evaluation axis” is set in advance by the user. The “characteristic word” typically means a word indicating an evaluation item (that is, a viewpoint for determining superiority or inferiority of content) related to the evaluation axis, but a part of the word indicating the evaluation item ( For example, it may be “machine” when the evaluation item is “machine control”). The “related word” includes not only a word related to a document but also a word associated with the document (that is, an associated word).

  The “duplication degree” may be expressed, for example, as the number of related words included in both the first related word group and the second related word group, or the ratio, ratio, percentage of the number of related words to the reference value, It may be expressed as a magnification or the like. “Relevance” typically increases as the degree of overlap increases.

  The relevance determination means may be configured to determine the relevance for each evaluation axis when there are two or more evaluation axes, or to determine the relevance for all evaluation axes at once. It may be configured.

  For example, a coordinate determination unit including a memory, a processor, and the like determines coordinate candidates on the evaluation axis of each of the plurality of contents according to the determined degree of association. “Coordinate candidate” means provisional coordinates. Here, the document evaluation and organization system finally presents a plurality of evaluated and organized contents to the user, for example, by displaying them on a screen. For this reason, it is desirable that a plurality of contents are arranged on the screen so as not to overlap each other. Therefore, the coordinate determination means is configured to determine “coordinate candidates” so that the coordinates relating to the content can be changed as necessary.

  According to the inventor's research, the following matters have been found. That is, when evaluating and organizing a plurality of documents (contents) using an evaluation axis that is not quantitative, it is often based on the user's subjectivity at which coordinates on the evaluation axis each content is positioned. In addition, such work often depends on the user's empirical knowledge and insight, and is relatively difficult for non-experts.

  However, in the present embodiment, as described above, the relevance determination unit extracts and extracts the first related word group related to the feature word related to the evaluation axis and the second related word group related to each of the plurality of contents. Based on the degree of overlap between the first related word group and the extracted second related word group, the degree of association between each of the plurality of contents and the evaluation axis is determined. Further, the coordinate determination unit determines coordinate candidates on the evaluation axis of each of the plurality of contents according to the determined degree of association. For this reason, regardless of the skill level of the user, each of the plurality of contents can be arranged on the evaluation axis objectively and appropriately (that is, evaluated and organized).

  In one aspect of the document evaluation organization system according to the present embodiment, the coordinate determination unit further adjusts a relative position between the plurality of contents on the evaluation axis based on coordinate candidates related to each of the plurality of contents. To do.

  According to this aspect, for example, every time new content is acquired, the image presented to the user can be updated appropriately, which is very advantageous in practice.

(Embodiment of document evaluation organization method)
The document evaluation organization method according to the embodiment is a related word group related to a feature word that is a word that characterizes an acquisition axis for acquiring a plurality of contents each including a document and an evaluation axis for evaluating the plurality of contents. A first related word group and a second related word group that is a related word group related to a document included in each of the plurality of contents are extracted, and the extracted first related word group and the extracted second relation A relevance determination step for determining a relevance between each of the plurality of contents and the evaluation axis based on a degree of overlap with a word group; and the evaluation of each of the plurality of contents according to the determined relevance A coordinate determination step for determining coordinate candidates on the axis.

  According to the document evaluation and organizing method according to the present embodiment, similarly to the document evaluation and organizing system according to the above-described embodiment, each of a plurality of contents can be objectively and appropriately placed on the evaluation axis regardless of the skill level of the user. Can be arranged.

(Embodiment of computer program)
The computer program according to the embodiment is a related word group related to a feature word that is a word that characterizes an acquisition unit that acquires a plurality of contents each including a document and an evaluation axis for evaluating the plurality of contents. A first related word group and a second related word group which is a related word group related to a document included in each of the plurality of contents are extracted, and the extracted first related word group and the extracted second related word group are extracted. Relevance level determining means for determining a relevance level between each of the plurality of contents and the evaluation axis based on a degree of overlap with a related word group, and according to the determined relevance level, It is made to function as coordinate determination means for determining coordinate candidates on the evaluation axis.

  According to the computer program according to the present embodiment, the computer program can be evaluated from a recording medium such as a CD-ROM (Compact Disc Read Only Memory) or a DVD-ROM (DVD Read Only Memory) that stores the computer program. If the computer included in the organizing system is read and executed, or if the computer program is downloaded after being transmitted via communication means, the document evaluation organizing system according to the above-described embodiment can be made relatively easy. Can be realized. Thereby, similarly to the document evaluation organization system according to the above-described embodiment, each of the plurality of contents can be arranged on the evaluation axis objectively and appropriately regardless of the skill level of the user.

  An embodiment according to a document evaluation and organization system of the present invention will be described with reference to the drawings.

  The structure of the evaluation organization system which concerns on an Example is demonstrated with reference to FIG. FIG. 1 is a block diagram illustrating a configuration of an evaluation organization system according to an embodiment.

  In FIG. 1, the evaluation organization system 1 includes an input unit 11, an analysis unit 12, an evaluation axis setting unit 13, a relative position adjustment unit 14, a display device 15, and an operation unit 16. The evaluation organizing system 1 evaluates each content input by the user via the input unit 11 with respect to the evaluation axis set by the evaluation axis setting unit 13 by the analyzing unit 12, and performs evaluation of the evaluation by the analyzing unit 12. In accordance with the result, the display unit 15 displays an image in which each content is arranged on the evaluation axis.

  Hereinafter, the operation of the evaluation organization system 1 will be described in detail with specific examples. Here, the operation of the evaluation organization system 1 in the idea conference on new product development is given as a specific example.

  First, when an evaluation axis (evaluation item) for organizing content is set by the user via the evaluation axis setting means 13, an image as shown in FIG. 2 is displayed on the display device 15, for example. . Here, “health” is set as a positive evaluation item, and “unhealthy” is set as a negative evaluation item. FIG. 2 is an example of an image displayed on the display device according to the embodiment.

(Label object display processing)
Next, when content corresponding to each idea is input via the input unit 11 by the user, label object display processing described below is performed. As a specific example of content, it is assumed that content including the following three documents is input.
(1) A camera that calculates calories when taking a picture of a meal (2) A device that automatically measures the number of steps in conjunction with GPS (3) A laser lighter that automatically ignites when a cigarette is added The label object display process will be described with reference to the flowchart of FIG.

  In FIG. 3, first, content is input via the input means 11 (step S101). Subsequently, the analysis unit 12 extracts text data or metadata from the input content (step S102). The extracted text data or metadata is used for relevance calculation processing described later.

  Next, the analysis unit 12 generates a label object that is a label-like object corresponding to the input content (step S103). Subsequently, the analysis unit 12 transmits the generated label object to the display device 15 (step S104).

  As a result, an image as shown in FIG. 4 is displayed on the display device 15, for example. FIG. 4 is another example of an image displayed on the display device according to the embodiment. Note that the display position on the display device 15 relating to each label object displayed on the display device 15 can be freely changed by the user via the operation means 16 such as a touch panel or a mouse at this time. it can.

(Relevance calculation processing)
Next, the relevance calculation process performed on the input content will be described with reference to the flowchart of FIG.

  In FIG. 5, the analysis unit 12 first extracts keywords from the text (document) related to the label object (step S201). Here, the keyword extraction may be performed by, for example, a known morphological analysis. Note that the keyword is typically a noun included in a sentence corresponding to the text.

  Specifically, for example, when keywords are extracted for “camera that calculates calories when taking a picture of a meal”, “meal”, “photo”, “calories”, “calculation”, and “camera” Is extracted as a keyword. Similarly, in “device that automatically measures the number of steps in conjunction with GPS”, the terms “GPS”, “link”, “automatic”, “steps”, “measurement” and “device” are extracted as keywords. Is done. In the “laser lighter that automatically ignites when a cigarette is added”, the words “cigarette”, “automatic”, “ignition” and “lighter” are extracted as keywords.

  Next, based on the extracted keyword, the analysis unit 12 searches for related words and associative words (corresponding to “second related word group” according to the present invention) related to the keyword (step S202). For the search of related words and associative words, for example, a corpus dictionary, a related word dictionary, an associative word dictionary, etc. (not shown) may be used. Alternatively, when the evaluation organization system 1 is connected to a network, for example, it is used in conjunction with a word having a high co-occurrence frequency or a keyword among words appearing in a sentence acquired as a result of a Web search. A word with a high rate is used as a related word.

The related words and associative words searched for “meal”, “photograph”, “calorie”, “calculation”, and “camera” are as follows, for example.
"Meals": rice, dining, restaurants, main dishes, side dishes, tableware, ...
"Photograph": Lens, camera, development, subject, shooting, film, ...
"Calories": calorie, diet, health, obesity, exercise, burning, ...
"Calculation": function, algorithm, variable, computer, abacus, calculator, ...
"Camera": Lens, shutter, aperture, strobe, ...
The related words and associative words searched for “GPS”, “interlocking”, “automatic”, “step count”, “measurement”, and “device” are as follows, for example.
"GPS": Car navigation, satellite, supplement, positioning, ...
"Interlocking": gear, crank, device, ...
"Automatic": Machine control, manual, ...
“Steps”: Pedometer, walking, calories burned, distance, exercise, health “Measurement”: meter, probe “device”: machine, gadget, tool, technology, electricity “cigarette”, “automatic”, “ignition” and The related words and associative words searched for each “writer” are as follows, for example.
"Tobacco": passive smoking, nicotine, butts, fire, lung cancer, smoking cessation, unhealthy, ...
"Automatic": Machine control, manual, ...
"Ignition": combustion, ignition, sparks, matches, flint, ...
"Lighter": cigarettes, matches, fire, lamps ...
Furthermore, related words and associative words related to words obtained by combining the extracted keywords may be searched. Specifically, when “meal”, “photograph”, “calorie”, “calculation” and “camera” are combined, words such as “health promotion assist service”, “health management”, “mobile phone”, etc. are related terms. Or it is searched as an associative word. In addition, when “GPS”, “interlocking”, “automatic”, “step count”, “measurement”, and “device” are combined, for example, “mobile phone”, “health measuring device”, “GPS logger”, etc. Are searched as related words or associative words. In this way, by combining (synthesizing) the extracted keywords, all the keywords extracted from one text data are compared with the case of searching related words and associative words for each extracted keyword. Related related words can be searched.

  Next, the analysis means 12 sets the related word group about the keyword extracted from the text which concerns on a label object as the related word group A (step S203).

  The analysis unit 12 extracts a keyword (corresponding to the “feature word” according to the present invention) from the text (document) related to the evaluation item in the positive direction of the evaluation axis in parallel with the processing of steps S201 to S203 described above ( Step S204).

  Next, the analysis unit 12 searches for related words and associative words (corresponding to the “first related word group” according to the present invention) related to the keyword based on the extracted keyword (step S205). Next, the analysis unit 12 sets the related word group for the evaluation item in the positive direction of the evaluation axis as the related word group B (step S206).

  Specifically, for example, since the evaluation item in the positive direction of the evaluation axis is “health”, the analysis unit 12 extracts “health” as a keyword. Subsequently, the analysis unit 12 searches for “genki”, “active”, “exercise”, “health insurance”, and the like as related words and associative words about “health”.

  Similarly, the analysis unit 12 extracts a keyword (corresponding to the “feature word” according to the present invention) from the text related to the evaluation item in the negative direction of the evaluation axis in parallel with the processing of steps S201 to S206 described above ( Step S207).

  Next, the analysis unit 12 searches for related words and associative words (corresponding to “first related word group” according to the present invention) related to the keyword based on the extracted keyword (step S208). Next, the analysis means 12 sets the related word group about the evaluation item of the negative direction of an evaluation axis as the related word group C (step S209).

  Specifically, for example, since the evaluation item in the negative direction of the evaluation axis is “unhealthy”, the analysis unit 12 extracts “unhealthy” as a keyword. Subsequently, the analysis unit 12 searches for “disease”, “obesity”, “cigarette”, “insufficient sleep”, and the like as related words and associative words about “unhealthy”.

  FIG. 6 conceptually shows a related word group for the evaluation axis. In FIG. 6, the words shown around “health” correspond to the “related word group B” described above. On the other hand, words shown around “unhealthy” correspond to the “related word group C” described above. The image as shown in FIG. 6 is not actually presented to the user.

  Returning to FIG. 5 again, the analysis unit 12 calculates the degree of duplication between the related word group A and the related word group B (step S210), and based on the calculated degree of duplication, the related word group A and the related word group. The degree of association between B is calculated. In parallel with the process of step S210, the analysis unit 12 calculates the degree of overlap between the related word group A and the related word group C (step S211), and based on the calculated degree of overlap, the related word group A And the degree of association between the related word groups C is calculated.

  As a result of the processing in steps S210 and S211, for example, for “a camera that calculates calories when taking a picture of a meal”, “health” and “exercise” (ie, “2”) are related to related word group A. Calculated as the degree of overlap with word group B. Further, “obesity” (that is, “1”) is calculated as the degree of overlap between the related word group A and the related word group C.

  Similarly, regarding “an apparatus that automatically measures the number of steps in conjunction with GPS”, “exercise” and “health” (ie, “2”) indicate the degree of overlap between the related word group A and the related word group B. Is calculated as On the other hand, since there is no common word between the related word group A and the related word group C, “0” is calculated as the degree of overlap between the related word group A and the related word group C.

  As for “laser lighter that automatically ignites when a cigarette is added”, there is no common word in related word group A and related word group B, so “0” is related word group A and related word group B. Is calculated as the degree of overlap with. On the other hand, “cigarette” and “unhealthy” (that is, “2”) are calculated as the degree of overlap between the related word group A and the related word group C.

  In order to simplify the explanation, in the specific example, “duplication degree” is treated as “relevance degree”.

(Position adjustment processing)
Next, the position adjustment process performed based on the result of the relevance calculation process described above will be described with reference to the flowchart of FIG.

  In FIG. 7, the relative position adjusting unit 14 determines whether or not the degree of association between the related word group A and the related word group B is larger than the degree of association between the related word group A and the related word group C (step S301). ). When it is determined that the degree of association between the related word group A and the related word group B is greater than the degree of association between the related word group A and the related word group C (step S301: Yes), the relative position adjusting unit 14 Temporary coordinates (corresponding to “coordinate candidates” according to the present invention) related to the label object corresponding to the word group A are set in the positive region of the evaluation axis (step S302).

  On the other hand, when it is determined that the degree of association between the related word group A and the related word group B is smaller than the degree of association between the related word group A and the related word group C (step S301: No), the relative position adjusting unit 14 Then, provisional coordinates related to the label object corresponding to the related word group A (corresponding to “coordinate candidates” according to the present invention) are set in the negative region of the evaluation axis (step S305). When the degree of association between the related word group A and the related word group B and the degree of association between the related word group A and the related word group C are “equal”, they may be included in either case.

  Specifically, for the “camera that calculates calories when taking a picture of a meal”, the degree of association (2) between the related word group A and the related word group B is between the related word group A and the related word group C. Therefore, the provisional coordinates are set in the positive region (“health” side) of the evaluation axis.

  Similarly, regarding the “device that automatically measures the number of steps in conjunction with GPS”, the degree of association (2) between the related word group A and the related word group B is between the related word group A and the related word group C. Since the degree of relevance is greater than (0), the provisional coordinates are set in the positive region (“health” side) of the evaluation axis.

  On the other hand, regarding “a laser writer that automatically ignites when a cigarette is added”, the degree of association (0) between the related word group A and the related word group B is related to the relation between the related word group A and the related word group C. Since the degree is smaller than (2), the provisional coordinates are set to the negative region (“unhealthy” side) of the evaluation axis.

  After the process in step S302, the relative position adjusting unit 14 determines whether there is another label object (content) set in the normal area (step S303). When it is determined that there is no other label object (step S303: No), the relative position adjusting unit 14 arranges the corresponding label object on the evaluation axis and displays it on the display device 15 based on the provisional coordinates. (Step S308) (see FIG. 8).

  On the other hand, when it is determined that there is another label object set in the normal area (step S303: Yes), the relative position adjusting unit 14 determines whether the related word group A and the related word group B are related to each of the other label objects. Are compared with the degree of association between the related word group A and the related word group B related to the label object for which the temporary coordinates are set this time, and the display coordinates are determined (step S304). Thereafter, based on the determined display coordinates, the relative position adjustment unit 14 (re) places (or re-arranges) the label objects existing in the normal region on the evaluation axis and displays them on the display device 15 (step S308). (See FIG. 9).

  After the process of step S305, the relative position adjusting unit 14 determines whether there is another label object (content) set in the negative area (step S306). When it is determined that there is no other label object (step S306: No), the relative position adjusting unit 14 arranges the corresponding label object on the evaluation axis and displays it on the display device 15 based on the provisional coordinates. (Step S308) (see FIG. 8).

  On the other hand, when it is determined that there is another label object set in the negative region (step S306: Yes), the relative position adjustment unit 14 determines whether the related word group A and the related word group C are related to each of the other label objects. Are compared with the degree of association between the related word group A and the related word group C related to the label object for which the temporary coordinates are set this time, and the display coordinates are determined (step S307). Thereafter, based on the determined display coordinates, the relative position adjustment unit 14 (re) arranges (or re-arranges) the label objects existing in the negative region on the evaluation axis and displays them on the display device 15 (step S308). ).

  As a result, according to the evaluation organizing system 1, the related words and associative words related to the evaluation item of the evaluation axis are compared with the related words and associative words related to the content. Compared with the case of comparing a single text) and a document included in the content, and evaluating the content, the content can be evaluated and organized more objectively, closer to a human thought process.

  The “input means 11”, “analysis means 12”, and “relative position adjustment means 14” according to the embodiment are examples of “acquisition means”, “relevance degree determination means”, and “coordinate determination means” according to the present invention, respectively. It is.

  In the above-described embodiment, the case where there is one evaluation axis (two evaluation items) has been described, but the document evaluation organization system of the present invention has two evaluation axes (for example, as shown in FIG. 10). It is also applicable when there are four or more evaluation items. In this case, it is desirable for the document evaluation system to determine the degree of association for each evaluation axis.

  The present invention is not limited to the above-described embodiments, and can be changed as appropriate without departing from the spirit or concept of the invention that can be read from the claims and the entire specification. Systems and methods, computer programs, and recording media are also included in the technical scope of the present invention.

  DESCRIPTION OF SYMBOLS 1 ... Evaluation organization system, 11 ... Input means, 12 ... Analysis means, 13 ... Evaluation axis setting means, 14 ... Relative position adjustment means, 15 ... Display apparatus, 16 ... Operation means

Claims (6)

Acquisition means for acquiring a plurality of contents each including a document;
A first related word group that is a related word group related to a feature word that is a word that characterizes an evaluation axis for evaluating the plurality of contents, and a related word group related to a document included in each of the plurality of contents A second related word group is extracted, and based on the degree of overlap between the extracted first related word group and the extracted second related word group, the degree of association between each of the plurality of contents and the evaluation axis is determined. Relevance determining means to determine;
Coordinate determination means for determining coordinate candidates on the evaluation axis of each of the plurality of contents according to the determined degree of association;
A document evaluation and organization system characterized by comprising:   2. The document evaluation according to claim 1, wherein the coordinate determination unit further adjusts a relative position between the plurality of contents on the evaluation axis based on a coordinate candidate related to each of the plurality of contents. Organizing system.   3. The document evaluation organization system according to claim 1, wherein when there are two or more evaluation axes, the relevance level determination unit determines the relevance level for each evaluation axis. An acquisition step of acquiring a plurality of contents each including a document;
A first related word group that is a related word group related to a feature word that is a word that characterizes an evaluation axis for evaluating the plurality of contents, and a related word group related to a document included in each of the plurality of contents A second related word group is extracted, and based on the degree of overlap between the extracted first related word group and the extracted second related word group, the degree of association between each of the plurality of contents and the evaluation axis is determined. Relevance determination process to be determined;
A coordinate determination step of determining coordinate candidates on the evaluation axis of each of the plurality of contents according to the determined degree of association;
A document evaluation and organization method characterized by comprising: Computer
Acquisition means for acquiring a plurality of contents each including a document;
A first related word group that is a related word group related to a feature word that is a word that characterizes an evaluation axis for evaluating the plurality of contents, and a related word group related to a document included in each of the plurality of contents A second related word group is extracted, and based on the degree of overlap between the extracted first related word group and the extracted second related word group, the degree of association between each of the plurality of contents and the evaluation axis is determined. Relevance determining means to determine;
Coordinate determination means for determining coordinate candidates on the evaluation axis of each of the plurality of contents according to the determined degree of association;
A computer program that functions as a computer program.   A recording medium storing the computer program according to claim 5.

Images