KR102618313B1 - Art learning evaluation method and apparatus - Google Patents

Abstract

The art learning evaluation method provided by the present invention includes the steps of a data acquisition unit acquiring text data generated during an art learner's online learning process as raw data; A data preprocessing module preprocesses the raw data so that it can be analyzed and selects a vocabulary to be evaluated; Analyzing the analysis module using a machine learning method based on a predefined art education achievement evaluation corpus based on the selected evaluation target vocabulary; It is characterized in that the output unit includes a step of outputting the analysis results.
The present invention has the effect of using machine learning to multidimensionally analyze and quantitatively evaluate text data generated as a result of online learning interactions between learners and professors or learners.

Description

Art learning evaluation method and device {ART LEARNING EVALUATION METHOD AND APPARATUS}

The present invention relates to an art learning evaluation method and device, and particularly to a method and device for evaluating the learning characteristics and achievement of art learners based on a machine learning method.

In art education, it has generally been done in a way that instructors directly check the works produced by learners through educational activities in order to analyze the learner's learning or evaluate the student's achievement.

However, since this type of evaluation relies on the professor's individual qualitative evaluation, the evaluation standards are different, and there may be time constraints when quantitatively evaluating multiple learners, and there may be a lack of consistency in evaluation. There is a limitation in that the activities and results performed do not reflect all of the characteristics of art education.

In addition, art education services provided online use surveys or simple art tendency diagnosis methods to analyze learners' characteristics. The questionnaire used in this conventional online art education diagnosis method consists of a limited number of questions about learners' interests or preferences in the field of art, making it difficult to secure reliability and objectivity in the analysis results. In particular, measurement tools that require responses within a set time at a certain point in time rather than throughout the entire art learning experience have limitations in identifying complex artistic tendencies and sensibilities.

Therefore, methods and devices for objectively and multidimensionally analyzing the learning characteristics and achievements of online art learners are required.

The present invention seeks to provide a method and device that can multidimensionally analyze and quantitatively evaluate text data generated as a result of online learning interactions between learners and professors or learners using machine learning.

The problem to be solved by the present invention is not limited to the problem(s) mentioned above, and other problem(s) not mentioned will be clearly understood by those skilled in the art from the description below.

In order to solve the above problem, the art learning evaluation method provided by the present invention includes the steps of a data acquisition unit acquiring text data generated during the art learner's online learning process as raw data; A data preprocessing module preprocesses the raw data so that it can be analyzed and selects a vocabulary to be evaluated; Analyzing the analysis module using a machine learning method based on a predefined art education achievement evaluation corpus based on the selected evaluation target vocabulary; It is characterized in that the output unit includes a step of outputting the analysis results.

In one embodiment, the step of selecting the evaluation target vocabulary is characterized in that the target vocabulary is selected based on sentence structure analysis and morphological analysis of the raw data.

In one embodiment, the art learning evaluation method is characterized in that the step of analyzing the art education achievement evaluation corpus using a machine learning method adopts the naive Bayes classifier or the sub-vector machine.

In one embodiment, the machine learning method employing the Naive Bayes classifier includes: constructing a text data set for learning for multidimensional achievement evaluation; Classifying the learning text data set based on the previously defined art education achievement evaluation corpus; calculating a classification decision rule based on the classified text data set; and machine learning the classified text data set based on the classification decision rule.

In one embodiment, the corpus for evaluating art education achievement is characterized by being divided into major categories of observation, ideation, visualization, design, experimentation, and appreciation.

In one embodiment, the major category items of the art education achievement evaluation corpus are each divided into a plurality of subcategory items, and the observations are divided into subcategory items including intuition, perceptual ability, visual memory, synesthetic observation, and task obsession, , the ideas are divided into subcategories including creative problem definition, personal topic expression, social topic expression, visual storytelling, imagination, analogy, gentleness, transformation, and flexible thinking, and the visualization includes color sense, conceptual ability, abstraction, It is divided into subcategories including sense of form, sense of space, texture, screen composition, use of formative principles, completeness, and self-direction, and the design includes use of materials and tools, design thinking, modeling, circular application, recording and sharing, It is divided into subcategories including reflective thinking, and the experiment is divided into subcategories including media utilization, media expansion, new media, convergence thinking, collaborative performance, and challenging spirit, and the above appreciation is visual literacy, critical It is characterized by being divided into subcategories including perspective, art historical understanding, empathy, critical language, and critical thinking.

An art learning evaluation device according to an embodiment of the present invention includes a data acquisition unit that acquires text data generated during an art learner's online learning process as raw data; a data preprocessing module that preprocesses the raw data to enable analysis and selects vocabulary to be evaluated; An analysis module that analyzes a predefined art education achievement evaluation corpus based on the selected evaluation target vocabulary using machine learning; and an output unit that outputs the analysis results.

The present invention has the effect of objectively analyzing the learning characteristics and achievement of art learners from a multidimensional perspective.

Figure 1 is a network configuration diagram of an art learning evaluation system according to an embodiment of the present invention.
Figure 2 is a diagram showing the schematic configuration of an art learning evaluation device according to an embodiment of the present invention.
Figure 3 is a flowchart schematically showing an art learning evaluation method according to an embodiment of the present invention.
Figure 4 is a flow chart schematically showing a machine learning method for evaluating art learning according to an embodiment of the present invention.
Figure 5 is a diagram for explaining art learning achievement evaluation items according to an embodiment of the present invention.

Since the present invention can make various changes and have various embodiments, specific embodiments will be illustrated in the drawings and described in detail in the detailed description. However, this is not intended to limit the present invention to specific embodiments, and should be understood to include all changes, equivalents, and substitutes included in the spirit and technical scope of the present invention. While describing each drawing, similar reference numerals are used for similar components.

Terms such as first, second, A, and B may be used to describe various components, but the components should not be limited by the terms. The above terms are used only for the purpose of distinguishing one component from another. For example, a first component may be named a second component, and similarly, the second component may also be named a first component without departing from the scope of the present invention. The term and/or includes any of a plurality of related stated items or a combination of a plurality of related stated items.

When a component is said to be "connected" or "connected" to another component, it is understood that it may be directly connected to or connected to the other component, but that other components may exist in between. It should be. On the other hand, when it is mentioned that a component is “directly connected” or “directly connected” to another component, it should be understood that there are no other components in between.

The terms used in this application are only used to describe specific embodiments and are not intended to limit the invention. Singular expressions include plural expressions unless the context clearly dictates otherwise. In this application, terms such as “comprise” or “have” are intended to designate the presence of features, numbers, steps, operations, components, parts, or combinations thereof described in the specification, but are not intended to indicate the presence of one or more other features. It should be understood that this does not exclude in advance the possibility of the existence or addition of elements, numbers, steps, operations, components, parts, or combinations thereof.

Unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by a person of ordinary skill in the technical field to which the present invention pertains. Terms defined in commonly used dictionaries should be interpreted as having a meaning consistent with the meaning in the context of the related technology, and should not be interpreted in an ideal or excessively formal sense unless explicitly defined in the present application. No.

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

Figure 1 is a network configuration diagram of an art learning evaluation system according to an embodiment of the present invention.

Referring to FIG. 1, the art learning evaluation system according to an embodiment of the present specification may include a terminal 200 and an art learning evaluation device 100.

The terminal 200 is a user terminal that connects to the art learning evaluation device 100 and receives an art learning evaluation service. The user receiving the service may be a student, professor, or parent. Here, the art learning evaluation service includes providing evaluation results by multidimensionally and quantitatively evaluating the student's art learning achievement based on feedback data from the professor generated while taking art classes through online programs.

The terminal 200 may be implemented as, for example, a smartphone, PDA, tablet PC, notebook computer, laptop computer, personal computer, or other electronic device or similar device that can perform communication, receive user input, and output a screen. You can.

The art learning evaluation device 100 is a device that provides an art learning evaluation service to the connected terminal 200. To this end, it can preferentially perform membership registration and authentication for users connected through the terminal 200. . Since these registration and authentication procedures are general procedures, their description is omitted.

The art learning evaluation device 100 may be implemented as, for example, a workstation, server, general-purpose computer, other electronic device capable of performing communication, or a similar device.

The terminal 200 and the art learning evaluation device 100 are connected through a communication network and communicate with each other through the communication network.

Communication networks include, for example, LTE (Long Term Evolution), LTE-A (LTE-Advanced), WI-FI, LAN (Local Area Network), WAN (Wide Area Network), CDMA (Code Division Multiple Access), and TDMA (Time Division Multiple Access), WiBro (Wireless Broadband), GSM (Global System for Mobile Communications), etc. It can be implemented using at least some of the communication methods developed in the past, present, or that will be available in the future. Hereinafter, for convenience, the communication network 100 will not be mentioned and the description will be made as if the terminal 200 and the art learning evaluation device 100 communicate directly.

Through the art learning evaluation system according to an embodiment of the present invention, text data generated as a result of interaction for learning between learners and professors or learners online can be multidimensionally analyzed and quantitatively evaluated using machine learning. .

Figure 2 is a diagram showing the schematic configuration of an art learning evaluation device according to an embodiment of the present invention.

Figure 2 shows that the art learning evaluation device 100 according to an embodiment of the present invention may include a data acquisition unit 110, a storage unit 120, a control unit 130, and an output unit 140.

The data acquisition unit 110 collects raw data to evaluate the user's art learning achievement. Here, raw data is text data generated by interactions between students and professors while taking art classes through online programs, etc., such as text-based evaluations of the art learner's work and learning process, questions and answers with the professor, etc. It may contain unstructured data.

The data acquisition unit 110 may receive raw data for evaluating the user's art learning achievement from the connected user's terminal 200.

Additionally, the data acquisition unit 110 may store the collected information in the storage unit 120.

The storage unit 120 stores programs and data for the art learning evaluation device 100 to operate. The storage unit 120 stores data under the control of the control unit 130 and transmits the data requested from the control unit 130 to the control unit 130.

In one embodiment, the storage unit 120 may store a machine learning model for evaluating art learner achievement and store data collected by the data acquisition unit 110.

The control unit 130 controls the overall operation and each component of the art learning evaluation device 100. The control unit 130 evaluates the art learning achievement in a multidimensional and quantitative manner based on the collected raw data for evaluating the user's art learning achievement and outputs the results. The output result can be output through an output device (not shown) or transmitted to the connected terminal 200.

The control unit 130 may be configured to include a preprocessing module 131 and an analysis module 133.

The preprocessing module 131 selects target vocabulary that becomes a keyword through sentence structure analysis, morphological analysis, etc. of raw data to evaluate the user's art learning achievement. The selection targets include nouns, verbs, adjectives, and adverbs, as well as vocabulary corresponding to the art education achievement evaluation corpus (hereinafter referred to as evaluation corpus) defined in advance for art education achievement evaluation. Vocabulary selection can use similarity between words. The evaluation corpus includes major category items and subcategory items for each major category item. The evaluation corpus will be described in detail with reference to FIG. 4, which will be described later.

The analysis module 133 analyzes the target vocabulary selected through the dictionary preparation module 131 using a machine learning method based on the constructed evaluation corpus and outputs a quantified value.

This type of machine learning method can utilize deep learning algorithms such as naive Bayes classifier, support vector machine, and convolutional neural network.

A machine learning model using Naive Bayes calculates the probability that random data belongs to a specific class based on Bayes' theorem. More specifically, Naive Bayes uses multiple algorithms based on general principles rather than training through a single algorithm, and commonly assumes that all feature values are independent of each other. In other words, it is assumed that there is no possible correlation between characteristics.

To explain the case of adopting such a Naive Bayes classifier as an example of a multidimensional achievement evaluation model based on machine learning, first, a text data set for learning is constructed. The learning text data set constructed in this way is classified according to M achievement evaluation dimensions (evaluation corpus) defined in advance. Afterwards, a multidimensional classification decision rule is generated as shown in Equation 1 based on the learning text data classified according to the achievement evaluation dimension.

[Equation 1]

The classification decision rule calculates M posterior probabilities that the text subject to multidimensional achievement evaluation will be classified into a specific dimension, and among these, it is classified into the category with the largest posterior probability.

Word distribution information can be generated by converting the words for each evaluation dimension classified in this way into vectors, and based on this, the similarity between words can be calculated numerically.

The output unit 140 outputs information according to instructions from the control unit 130. The output unit 140 can output information to a pre-connected display device and transmit information to the connected terminal 200. The output unit 140 may be comprised of a communication module or a display device.

Figure 3 is a flowchart schematically showing an art learning evaluation method according to an embodiment of the present invention.

In step S110, the data acquisition unit acquires the learner's text data generated during the art learner's online learning process as raw data.

In step S120, the data preprocessing module preprocesses the raw data so that it can be analyzed and selects a plurality of evaluation target vocabulary. To select vocabulary for evaluation, a predefined corpus for evaluating art education achievement is used as the standard.

In one embodiment, the data pre-processing module recognizes vocabulary based on structural analysis and morphological analysis of sentences from raw data, and selects a vocabulary to be evaluated based on the similarity between the recognized vocabulary and the vocabulary of the corpus for evaluating art education achievement. can be selected.

In step S130, the analysis module analyzes a predefined art education achievement evaluation corpus based on the selected evaluation target vocabulary using a machine learning method. The results analyzed in this way can also serve as training data for machine learning.

In step S140, the output unit outputs the analysis result according to instructions from the control unit.

The analysis results indicate the learner's art learning characteristics and achievement level.

Figure 4 is a flowchart schematically showing a machine learning method for evaluating art learning according to an embodiment of the present invention.

First, in step S210, a learning text data set for multidimensional achievement evaluation is constructed. To build a text data set for learning, learning activity data is collected through online and offline art education programs.

In step S220, the learning text data set is classified based on the previously defined art education achievement evaluation corpus.

In step S230, a classification decision rule is calculated based on the classified text data set.

In step S240, machine learning is performed on the text data set classified based on the classification decision rule.

Figure 5 is a diagram for explaining art learning achievement evaluation items according to an embodiment of the present invention.

Referring to Figure 5, art learning achievement evaluation items are divided into major categories of observation, ideation, visualization, design, experiment, and appreciation.

Each major category item includes a plurality of subcategory items.

In order to define major category items and multiple subcategory items, we first conducted a literature analysis of art education-related, prior research, national art curriculum and textbooks, and art education evaluation research reports, etc. to provide a representative for analysis of art learning at a conceptual level. Derive variables. Next, the actual learning activity data collected from the online and offline art education programs conducted for three years from 2018 to 2020 are cross-analyzed with the representative variables derived previously to confirm the art learning achievement evaluation items. In addition, based on actual online art education program operation experience, a list of data sources that can measure the results of representative variables is created.

First, the major category item ‘Observation’ includes the subcategory items intuition, perceptual ability, visual memory, synesthetic observation, and task obsession.

Intuition is an item to evaluate whether you can pay deep attention to objects or phenomena in your life and capture their aesthetic characteristics from a unique perspective.

Perceptual ability is an item used to evaluate whether one can use various senses, information, and experiences to form cognitive and emotional responses to objects or phenomena and express them in one's own way.

Visual memory is an item used to evaluate whether an object or phenomenon can be observed in detail to identify detailed formative characteristics and represent them realistically.

Synesthetic observation is an item to evaluate whether complex meaning and feelings can be derived from an object or phenomenon by connecting various senses.

Task obsession is an item to evaluate a high degree of concentration that can be expressed by observing an object or phenomenon through self-identification with the object or phenomenon.

The large category item ‘Idea’ includes small items such as creative problem definition, personal topic expression, social topic expression, visual storytelling, imagination, analogy, gentleness, transformation, and flexible thinking.

Creative problem definition is an item that evaluates the ability to set original questions for artistic problem solving and to specify them using various materials and information.

Personal topic expression is an item to evaluate the ability to discover personal meaning and develop an original topic by paying in-depth attention to an object or phenomenon in one's own experience.

Expression of social themes is an item to evaluate the ability to be interested in the community to which one belongs, to discover the socio-cultural meaning of objects or phenomena, and to participate in solving social problems through art.

Visual storytelling is an item to evaluate the ability to visualize one's experience into a story that others can relate to through personification of the object, connection of time and space, and development of content.

Imagination is an item to evaluate the ability to attempt approaches that go beyond existing methods in terms of the content and form of a work with a rich imagination.

Analogy is an item to evaluate the ability to create new relationships and derive creative meanings and stories based on the properties of objects.

Metaphor is an item to evaluate the ability to interpret a topic from a new perspective using metaphors and symbols and to express it creatively using visual metaphors.

Transformation is an item to evaluate the ability to convey purpose and intention by exploring various ways to express the topic and creatively transforming the content and form.

Flexible thinking is an item to evaluate the ability to explore objects with curiosity and enjoy the process of finding new possibilities for expression outside the box.

The large category item ‘Visualization’ includes small items such as color sense, conceptual ability, abstraction, sense of form, sense of space, texture, screen composition, use of formative principles, completeness, and self-direction.

Color sense allows you to express the theme of a work by knowing the properties of color and the principles of color combination and using them harmoniously, and shows original color sensitivity.

Configuration ability allows you to visualize the thoughts and feelings you want to convey in various ways and find new forms and formats to creatively express topics.

Abstraction can express the symbolic meaning of the subject by identifying the essential properties of the object and phenomenon to be expressed.

Emotional expression can be expressed by emotionally reacting to and internalizing the object or phenomenon to be expressed, and conveying the emotion by creatively utilizing formative elements and principles.

Sense of form allows you to express topics in various shapes and forms by finding creative patterns in the objects and phenomena you want to express.

The sense of space allows you to create a unique screen by mixing two-dimensional and three-dimensional space, and express the subject creatively by utilizing the sense of space.

Texture captures the feeling of the object and phenomenon you want to express, and can creatively express the subject with a new tactile feeling by using materials and media in an original way.

Screen composition allows you to create an original screen by creatively utilizing various composition methods such as screen division and arrangement, and positive/negative space.

Using formative principles, you can creatively express a theme by applying formative principles such as balance, symmetry, rhythm, emphasis, and change in your own way.

Completeness can be achieved by synthesizing various formative elements to visually convey the theme and finishing them in a detailed and precise manner to produce a completed work.

Self-directedness allows one to take the initiative in planning, analyzing, and executing the process of visualizing a topic with a clear writerly awareness of the topic.

The large category item ‘Design’ includes small items such as use of materials and tools, design thinking, modeling, circular application, recording and sharing, and reflective thinking.

When using materials and tools, you can understand the characteristics of the materials and tools, explore new ways to use them, and establish a plan to use them in your own way.

Design thinking utilizes the design process to design the production process and creatively solve problems in an analytical and comprehensive manner.

Modeling clarifies and expands the topic, and various methods such as thumbnail sketches, mock-ups, prototypes, and models can be used to design works and use them in the production process.

Circular application allows repeated attempts to solve problems that arise during the production process, find improvements, and reflect them in the next step or the next work.

For recording and sharing, actively participate in creating a portfolio that faithfully reflects the expression process and results and receiving feedback by sharing the work through exhibitions and SNS.

Reflective thinking allows you to check, adjust or develop your own expression method during the production process, and self-evaluate the performance process after production.

The large category item ‘Experiment’ includes small items such as media utilization, media expansion, new media, convergent thinking, collaborative performance, and challenging spirit.

Media utilization involves understanding and mastering the characteristics of expression materials, tools, and media, and the ability to creatively express topics by taking advantage of the characteristics of the medium.

Media expansion involves experimenting with various expressive media such as painting, sculpture, design, crafts, and video in connection with the subject and discovering and expressing new characteristics of the media.

New media allows you to actively explore new methods of artistic expression using multimedia in response to technological changes and use them in creative ways in your own work.

Convergent thinking can creatively solve artistic problems by understanding and fusing the interconnections between knowledge and functions in various fields.

Collaborative performance can encourage the participation of others in various art activities, actively participate in the creative problem-solving process, and demonstrate leadership.

A challenging spirit does not avoid complexity and ambiguity, but overcomes the fear of failure and actively participates in exploring and utilizing new methods.

The major category ‘appreciation’ includes the smaller categories visual literacy, critical perspective, art historical understanding, empathy, critical language, and critical thinking.

Visual literacy allows you to critically analyze and understand the semiotic and symbolic meanings conveyed by visual images and use them creatively to convey your thoughts.

A critical perspective explores multiple (expressive, formal, and contextual) perspectives and information to infer the meaning of (one's) work and present one's own interpretation and judgment.

Art historical understanding allows you to understand the basic concepts necessary for art historical research, such as formative style, iconography, trend, and area, and to criticize (one's) artwork using art historical research methods.

Empathy is the ability to emotionally communicate with a work by reacting to the content and emotions conveyed by the work and connecting it with one's own experience.

Critical language allows you to logically explain and express your own thoughts and feelings about a work of art based on the work's formative characteristics and art historical knowledge.

Critical thinking allows you to understand your own perspective, beliefs, and social values while analyzing and interpreting works of art within a social and cultural context.

As discussed above, the present invention can multidimensionally analyze and quantitatively evaluate text data generated as a result of online learning interactions between learners and professors or learners using machine learning.

So far, the present invention has been examined focusing on its preferred embodiments. A person skilled in the art to which the present invention pertains will understand that the present invention may be implemented in a modified form without departing from the essential characteristics of the present invention. Therefore, the disclosed embodiments should be considered from an illustrative rather than a restrictive perspective. The scope of the present invention is indicated in the claims rather than the foregoing description, and all differences within the equivalent scope should be construed as being included in the present invention.

110: Data acquisition unit
120: storage unit
130: control unit
131: Preprocessing module
133: Analysis module
140: output unit

Claims (12)

A data acquisition unit acquiring text data generated during an art learner's online learning process as raw data;
A data preprocessing module preprocesses the raw data so that it can be analyzed and selects a vocabulary to be evaluated;
Analyzing the analysis module using a machine learning method based on a predefined art education achievement evaluation corpus based on the selected evaluation target vocabulary; and
An output unit outputting the analysis results;
Including,
The corpus for evaluating art education achievement is divided into major categories of observation, ideation, visualization, design, experimentation, and appreciation,
Each major category item in the art education achievement evaluation corpus is divided into a plurality of subcategory items,
The above observations are divided into subcategories including intuition, perceptual ability, visual memory, synesthetic observation, and task obsession,
The above ideas are divided into subcategories including creative problem definition, personal topic expression, social topic expression, visual storytelling, imagination, analogy, gentleness, transformation, and flexible thinking.
The visualization is divided into subcategories including color sense, conceptual ability, abstraction, sense of form, sense of space, texture, screen composition, use of formative principles, completeness, and self-direction,
The design is divided into subcategories including use of materials and tools, design thinking, modeling, circular application, recording and sharing, and reflective thinking.
The above experiments are divided into subcategories including media utilization, media expansion, new media, convergence thinking, collaborative performance, and challenging spirit.
An art learning evaluation method characterized in that the appreciation is divided into subcategories including visual literacy, critical perspective, art historical understanding, empathy, critical language, and critical thinking.
According to paragraph 1,
The step of selecting the vocabulary to be evaluated is,
An art learning evaluation method characterized in that target vocabulary is selected based on sentence structure analysis and morphological analysis of the raw data.
According to paragraph 1,
The step of analyzing using machine learning based on the corpus for evaluating art education achievement is,
An art learning evaluation method characterized by adopting a naive Bayes classifier or a sub-vector machine.
According to paragraph 3,
The machine learning method adopting the Naive Bayes classifier is,
Building a training text data set for multidimensional achievement assessment;
Classifying the learning text data set based on a predefined art education achievement evaluation corpus;
calculating a classification decision rule based on the classified text data set; and
Machine learning the classified text data set based on the classification decision rule.
An art learning evaluation method comprising:
delete delete a data acquisition unit that acquires text data generated during the art learner's online learning process as raw data;
a data preprocessing module that preprocesses the raw data to enable analysis and selects vocabulary to be evaluated;
An analysis module that analyzes a predefined art education achievement evaluation corpus based on the selected evaluation target vocabulary using machine learning; and
Output unit that outputs the analysis results
Including,
The corpus for evaluating art education achievement is divided into major categories of observation, ideation, visualization, design, experimentation, and appreciation,
Each major category item in the art education achievement evaluation corpus is divided into a plurality of subcategory items,
The above observations are divided into subcategories including intuition, perceptual ability, visual memory, synesthetic observation, and task obsession,
The above ideas are divided into subcategories including creative problem definition, personal topic expression, social topic expression, visual storytelling, imagination, analogy, gentleness, transformation, and flexible thinking.
The visualization is divided into subcategories including color sense, conceptual ability, abstraction, sense of form, sense of space, texture, screen composition, use of formative principles, completeness, and self-direction,
The design is divided into subcategories including use of materials and tools, design thinking, modeling, circular application, recording and sharing, and reflective thinking.
The above experiments are divided into subcategories including media utilization, media expansion, new media, convergence thinking, collaborative performance, and challenging spirit.
An art learning evaluation device characterized in that the appreciation is divided into subcategories including visual literacy, critical perspective, art historical understanding, empathy, critical language, and critical thinking.
In clause 7,
The data pre-processing module is an art learning evaluation device characterized in that the target vocabulary is selected based on sentence structure analysis and morphological analysis of the raw data.
In clause 7,
The analysis module is an art learning evaluation device characterized in that it adopts a naive Bayes classifier or a sub-vector machine.
According to clause 9,
The machine learning method adopting the Naive Bayes classifier is,
Construct a learning text data set for multidimensional achievement evaluation, classify the learning text data set based on a predefined art education achievement evaluation corpus, calculate a classification decision rule based on the classified text data set, and An art learning evaluation device characterized by machine learning on a classified text data set based on a classification decision rule.
delete delete