CN111813919A - MOOC course evaluation method based on syntactic analysis and keyword detection - Google Patents
MOOC course evaluation method based on syntactic analysis and keyword detection Download PDFInfo
- Publication number
- CN111813919A CN111813919A CN202010592147.XA CN202010592147A CN111813919A CN 111813919 A CN111813919 A CN 111813919A CN 202010592147 A CN202010592147 A CN 202010592147A CN 111813919 A CN111813919 A CN 111813919A
- Authority
- CN
- China
- Prior art keywords
- course
- score
- keywords
- keyword
- mooc
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000011156 evaluation Methods 0.000 title claims abstract description 29
- 238000001514 detection method Methods 0.000 title claims abstract description 17
- 238000000034 method Methods 0.000 claims abstract description 54
- 230000008569 process Effects 0.000 claims description 27
- 239000011159 matrix material Substances 0.000 claims description 15
- 230000008451 emotion Effects 0.000 claims description 13
- 241001347978 Major minor Species 0.000 claims description 10
- 238000012545 processing Methods 0.000 claims description 7
- 208000025174 PANDAS Diseases 0.000 claims description 3
- 208000021155 Paediatric autoimmune neuropsychiatric disorders associated with streptococcal infection Diseases 0.000 claims description 3
- 235000016496 Panda oleosa Nutrition 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims description 3
- 230000007935 neutral effect Effects 0.000 claims description 3
- 230000011218 segmentation Effects 0.000 claims description 3
- 230000009471 action Effects 0.000 claims description 2
- 240000000220 Panda oleosa Species 0.000 claims 1
- 238000013441 quality evaluation Methods 0.000 abstract description 2
- 230000000694 effects Effects 0.000 description 6
- 240000004718 Panda Species 0.000 description 2
- 230000008520 organization Effects 0.000 description 2
- 239000013598 vector Substances 0.000 description 2
- 230000008901 benefit Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000002996 emotional effect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/335—Filtering based on additional data, e.g. user or group profiles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9536—Search customisation based on social or collaborative filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
- G06F40/12—Use of codes for handling textual entities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
- G06F40/211—Syntactic parsing, e.g. based on context-free grammar [CFG] or unification grammars
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06395—Quality analysis or management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/01—Social networking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/20—Education
- G06Q50/205—Education administration or guidance
Abstract
The invention belongs to the field of education informatization, and provides an MOOC course evaluation method based on syntactic analysis and keyword detection. The method can provide reliable and reference basis for the quality evaluation of the MOOC course, and help to improve the quality of the MOOC course, thereby helping students select proper courses and helping teachers improve the courses set by the students.
Description
Technical Field
The invention belongs to the field of education informatization, and particularly relates to an MOOC course evaluation method based on syntactic analysis and keyword detection.
Background
MOOC (massive Open Online courses), a large Open network course, is an emerging educational model. Different from the traditional classroom teaching mode, the MOOC course can integrate various digital teaching resources to provide diversified course contents, and the combination with the social tool can make the communication between teachers and students more convenient and the interactivity of the course higher. The biggest advantage of the MOOC course is that the online teaching mode can break through the limitations of the traditional classroom on time, space and number of people, so that learners around the world can learn the course at any time.
However, there are some problems with the MOOC mode: the teaching effect of the MOOC course depends on the self-learning ability of the learner, and the dropping rate of the MOOC course is at a high level for a long time; the quality of the MOOC course is difficult to guarantee due to the control force of the MOOC platform and the input degree of the MOOC teacher to the course.
If an effective grading frame can be given to the quality of the course, the MOOC system can provide feedback for the course openers according to the scores of the course on different indexes, so that the course openers can improve the course in a targeted manner; and the courses with higher professional scores can be preferentially pushed to the corresponding users, so that the overall teaching quality and the learning effect are improved.
Disclosure of Invention
The invention aims to overcome the defects in the prior art, and provides an MOOC course evaluation method based on syntactic analysis and keyword detection, which is used for obtaining reliable evaluation of the MOOC course from the discussion content of the MOOC course.
The object of the invention is achieved by the following technical measures.
An MOOC course evaluation method based on syntactic analysis and keyword detection comprises the following steps:
(1) retrieving postings of courses to be evaluated from forum data of the MOOC course forum;
(2) performing syntactic analysis on the posting content retrieved in the step (1), extracting a relation triple contained in the content, and extracting a main and subordinate relation, an action and guest relation and a sentence containing a course name contained in the posting content;
(3) detecting the relation extracted in the step (2) according to the keywords, extracting a part containing the keywords, and performing emotion analysis to obtain an emotion score;
(4) and (4) summarizing scores of all evaluation indexes in the step (3) according to certain weight to obtain the overall score of the course.
In the above technical solution, the specific process of syntax analysis in step (2) is as follows:
(2-1) extracting the posting content of the forum
The discussion area data of the MOOC course forum is a CSV file recording the course id, the course name, the author id, the post type, the main post id, the title and the content data of each post, the CSV file is read by using a read _ CSV method of a pandas module of Python, and the course id, the course name, the title and the content data of a course to be evaluated are extracted from the CSV file; specifically, a search method is defined: reading in a CSV file in a matrix data table mode, setting a corresponding search condition according to search requirements, setting a course name as the search condition if all postings of a course need to be searched, setting a keyword as the search condition if a title or content needs to be searched and postings containing a specific keyword, setting a main post id as the search condition if all main posts and postings of a certain post need to be searched, retrieving corresponding parts of data in the matrix data table one by one, if the search conditions are met, storing the whole data into a new matrix data table, outputting the new matrix data table after the whole search process is finished, and using the matrix data table for the next step;
(2-2) dependency parsing of posting Contents
Segmenting the data extracted in the step (2-1) by using a segment method of a segment object of a Python pyltp module, performing part-of-speech tagging on a segmentation result by using a Postager pop method, and finally performing dependency syntax analysis by using a Parser parse method;
(2-3) processing the dependency parsing result
Extracting a part containing a specific dependency relationship pair from a dependency syntax analysis result, specifically, firstly extracting a part containing a major-minor relationship, wherein the major-minor relationship is formed by combining the major-minor relationship and a moving-minor relationship in the dependency syntax analysis in a pyltp module, if the major-minor relationship and the moving-minor relationship exist between a verb and other words in a sentence, the sentence can be considered to contain the major-minor relationship, then extracting the part only containing the moving-minor relationship, and meanwhile, if the sentence contains the name of a course to be evaluated, extracting the sentence;
(2-4) completion of the treatment results
And (4) completing the result obtained by the treatment in the step (2-3): if the obtained words have a fixed relation, adding the corresponding fixed language into the result; if the obtained words are verbs and the relationship of the subject and the subject guest exists, adding the subject and the object corresponding to each verb into the result; this operation is repeated until no new words can be added; the completed result is the output result of the syntactic analysis process.
In the above technical solution, the specific process of keyword detection in step (3) is as follows:
(3-1) selection and expansion of keywords
Making course evaluation indexes and corresponding grading weights thereof, and further selecting a plurality of keywords for the corresponding evaluation indexes to form an evaluation system; expanding the selected keywords, wherein the expanded keywords need to be related to the basic keywords, obtaining a series of words related to the basic keywords by using a nearby method of a syntony module of Python, selecting the words related to course evaluation as the expanded keywords, and finally obtaining a keyword list;
(3-2) scoring search by keyword
And (3) for an output result of the syntactic analysis process, searching each keyword according to the keyword list obtained in the step (3-1), performing emotion analysis on the searched result by using a Paddlehub module of Python, and obtaining an emotion tendency score, wherein the obtained emotion score is in a range of-1 to 1, a score smaller than 0 represents a negative tendency, a score larger than 0 represents a positive tendency, and 0 represents neutral emotion.
In the above technical solution, the specific process of obtaining the overall score in step (4) is as follows:
let the weight of the ith index score in the overall score be ωiEach index comprises k keywords, and the Score of the jth keyword is ScorejThen, the calculation method of the ith index score is as follows:
and if the total number of the indexes is n, the overall score S of the course is calculated by the following method:
the technical scheme provided by the invention is that the dependency syntax analysis is carried out on the posted content of the discussion area of the MOOC course forum to extract the part containing the specific content, and then the specified keywords are detected and scored, so that the scores and the overall scores of all aspects of the quality of the course are obtained. The method can provide reliable and reference basis for the quality evaluation of the MOOC course, help to improve the MOOC course quality, and help students select proper courses and teachers to improve the courses set by the students.
Drawings
FIG. 1 is a flow chart of the parsing process in the present embodiment;
fig. 2 is a flowchart of a keyword detection process in this embodiment.
Detailed Description
The technical solution of the present invention will be described in detail below by taking as an example the evaluation of MOOC courses in Pytone development environment in Python language on a developer.
The MOOC course evaluation method based on syntactic analysis and keyword detection mainly comprises a syntactic analysis process and a keyword detection process.
The syntactic analysis process is to perform dependency syntactic analysis on the contents posted in the forum of the MOOC course forum and extract the contents containing specific relationships.
And in the keyword detection process, corresponding keywords are summarized according to all evaluation indexes, and the result obtained in the sentence analysis process is detected and scored.
Syntax analysis process, as shown in fig. 1.
(1) Extracting forum posting content
The MOOC forum discussion area data adopted in the embodiment is a CSV file recording data such as course id, course name, author id, post type, main post id, title, content and the like of each post. To realize the grading of the course, only the course id, the course name, the title and the content data need to be used.
Reading the CSV file by using a read _ CSV method of a Python pandas module, defining a search method according to actual needs, and extracting the course id, the course name, the title and the content data of the course to be evaluated from the CSV file.
Specifically, a search method is defined: reading in the CSV file in the form of a matrix data table, searching corresponding parts of data in the matrix data table one by one according to set search conditions (course names, main post ids or keywords), if the search conditions are met, storing the whole data in a new matrix data table, and outputting the new matrix data table after the whole search process is finished, wherein the new matrix data table is used in the following steps.
(2) Dependency parsing of posted content
Because the contents of the forum data are mixed and contain a large amount of data irrelevant to the course quality, in order to realize the grading of the course quality, the data relevant to the course quality needs to be extracted from the forum data, and the dependency syntax analysis needs to be firstly carried out on the data:
and (2) segmenting the data extracted in the step (1) by using a segment method of a segment object of a Python pyltp module, performing part-of-speech tagging on a segmentation result by using a Postager pop method, and finally performing dependency syntax analysis by using a Parser parse method.
(3) Processing dependency parsing results
For the result of the dependency syntax analysis, a portion containing a specific dependency relationship pair is extracted. Specifically, a portion including a relationship of a principal and a predicate is extracted first. In the pyltp module, the predicate relationship is formed by combining two dependency relationships, namely a predicate relationship and a predicate relationship in dependency syntax analysis, and if the predicate relationship (marked as SBV) and the predicate relationship (marked as VOB) exist between a verb and other words in a sentence at the same time, the sentence can be considered to contain the predicate relationship, and the code is as follows:
and then extracting a part only containing the dynamic guest relationship. Meanwhile, if the sentence contains the name of the course to be evaluated, the sentence is extracted.
(4) Complementing the processing result
Because the result obtained by processing in step (3) only contains three words, in order to avoid missing semantic information, the processing result needs to be completed: if the obtained words have a fixed relation (marked as ATT), adding a corresponding fixed language into the result; and if the obtained word is a verb and the subject-guest relationship exists, adding the subject and the object corresponding to the verb into the result. The code is as follows:
and (4) repeating the steps (2-4) until no new words can be added, wherein the completed result is the output of the syntactic analysis process.
(II) keyword detection process, as shown in FIG. 2.
(1) Keyword selection and expansion
In order to comprehensively evaluate the MOOC course, a series of indexes are required to be formulated, and specific keywords are selected for each index so as to score the indexes. In the embodiment, 4 primary indexes of course planning, course contents, a teaching process and a learning effect, 9 secondary indexes of a teaching target, system openness, content organization and the like and corresponding scoring weights are formulated, and a plurality of keywords are selected for the corresponding indexes to form a basic evaluation system.
In order to collect as much information about the evaluation index as possible, the selected keyword needs to be further expanded. The expanded keywords need to be related to the basic keywords, and the word vector method can be used for conveniently calculating the correlation between words. In the embodiment, a syntony module of Python is used, word vectors of 12 ten thousand Chinese words are trained by the module through a word2vec model issued by Google, a series of words related to basic keywords can be quickly obtained through a nearby method of the syntony module, the words related to course evaluation are selected as expansion keywords, and finally a keyword list comprising 97 words is obtained.
(2) Search scoring by keyword
And (3) searching each keyword according to the keyword list obtained in the step (1) as to the result of the syntactic analysis process. And (4) carrying out emotion analysis on the searched result by using a paddlehub module of Python, and obtaining an emotional tendency score. The sentiment analysis function of the paddlehub module uses a Senta-BilSTM model, the obtained sentiment score is in a range from-1 to 1, the score smaller than 0 represents a negative tendency, the score larger than 0 represents a positive tendency, and 0 represents neutral sentiment. The code is as follows:
(3) processing the scores
After all the keywords are scored in the step (2), the scores of the keywords are collected to obtain the scores corresponding to the keywordsScores for individual indices and overall scores for MOOC courses. The scoring criteria of this embodiment includes 4 first-level index scores (FIS) and 9 second-level index scores (SIS), and the weight of the ith second-level index score in the total score is ωiEach secondary index comprises k keywords, and the Score of the jth keyword is ScorejThen, the calculation method of the ith secondary index score is as follows:
the score of each primary index is a weighted sum of the scores of the secondary indexes contained in the primary index. The overall score S of the course is calculated as follows:
after the method is executed, the corresponding scores of all the evaluation indexes of the MOOC course and the overall scores of the courses can be obtained.
The index system cited in this embodiment is derived from a peer published paper, and relates to the whole teaching process of the MOOC course, and the 4 first-level indexes are: course planning, course content, teaching process and learning effect. The 9 secondary indexes are respectively: teaching goals, system openness, content organization, learning support services, teaching video quality, teaching mode, teaching activities, knowledge and skill acquisition, and learning method acquisition. After the corresponding scores of all the evaluation indexes are obtained, the system feeds back the scoring results to the course seter, and can feed back the scores of the second-level indexes corresponding to all the first-level indexes to the course seter according to the query request of the course seter, and the course seter can improve courses according to specific scoring conditions.
After the overall scores of all MOOC courses are obtained, when a user retrieves the courses, the system puts the courses with higher overall scores in advance, so that the user resources of high-quality courses can be expanded, and the overall teaching quality and the teaching effect of the platform are improved.
By using the method in different teaching stages, real-time feedback of MOOC course quality and real-time allocation of user resources can be realized.
Details not described in the present specification belong to the prior art known to those skilled in the art.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (4)
1. An MOOC course evaluation method based on syntactic analysis and keyword detection is characterized by comprising the following steps:
(1) retrieving postings of courses to be evaluated from forum data of the MOOC course forum;
(2) performing syntactic analysis on the posting content retrieved in the step (1), extracting a relation triple contained in the content, and extracting a main and subordinate relation, an action and guest relation and a sentence containing a course name contained in the posting content;
(3) detecting the relation extracted in the step (2) according to the keywords, extracting a part containing the keywords, and performing emotion analysis to obtain an emotion score;
(4) and (4) summarizing scores of all evaluation indexes in the step (3) according to certain weight to obtain the overall score of the course.
2. The MOOC course evaluation method based on syntactic analysis and keyword detection according to claim 1, wherein the specific process of syntactic analysis in step (2) is as follows:
(2-1) extracting the posting content of the forum
The discussion area data of the MOOC course forum is a CSV file recording the course id, the course name, the author id, the post type, the main post id, the title and the content data of each post, the CSV file is read by using a read _ CSV method of a pandas module of Python, and the course id, the course name, the title and the content data of a course to be evaluated are extracted from the CSV file; specifically, a search method is defined: reading in a CSV file in a matrix data table mode, setting a corresponding search condition according to search requirements, setting a course name as the search condition if all postings of a course need to be searched, setting a keyword as the search condition if a title or content needs to be searched and postings containing a specific keyword, setting a main post id as the search condition if all main posts and postings of a certain post need to be searched, retrieving corresponding parts of data in the matrix data table one by one, if the search conditions are met, storing the whole data into a new matrix data table, outputting the new matrix data table after the whole search process is finished, and using the matrix data table for the next step;
(2-2) dependency parsing of posting Contents
Segmenting the data extracted in the step (2-1) by using a segment method of a segment object of a Python pyltp module, performing part-of-speech tagging on a segmentation result by using a Postager pop method, and finally performing dependency syntax analysis by using a Parser parse method;
(2-3) processing the dependency parsing result
Extracting a part containing a specific dependency relationship pair from a dependency syntax analysis result, specifically, firstly extracting a part containing a major-minor relationship, wherein the major-minor relationship is formed by combining the major-minor relationship and a moving-minor relationship in the dependency syntax analysis in a pyltp module, if the major-minor relationship and the moving-minor relationship exist between a verb and other words in a sentence, the sentence can be considered to contain the major-minor relationship, then extracting the part only containing the moving-minor relationship, and meanwhile, if the sentence contains the name of a course to be evaluated, extracting the sentence;
(2-4) completion of the treatment results
And (4) completing the result obtained by the treatment in the step (2-3): if the obtained words have a fixed relation, adding the corresponding fixed language into the result; if the obtained words are verbs and the relationship of the subject and the subject guest exists, adding the subject and the object corresponding to each verb into the result; this operation is repeated until no new words can be added; the completed result is the output result of the syntactic analysis process.
3. The MOOC course evaluation method based on syntactic analysis and keyword detection according to claim 1, wherein: the specific process of keyword detection in step (3) is as follows:
(3-1) selection and expansion of keywords
Making course evaluation indexes and corresponding grading weights thereof, and further selecting a plurality of keywords for the corresponding evaluation indexes to form an evaluation system; expanding the selected keywords, wherein the expanded keywords need to be related to the basic keywords, obtaining a series of words related to the basic keywords by using a nearby method of a syntony module of Python, selecting the words related to course evaluation as the expanded keywords, and finally obtaining a keyword list;
(3-2) scoring search by keyword
And (3) for an output result of the syntactic analysis process, searching each keyword according to the keyword list obtained in the step (3-1), performing emotion analysis on the searched result by using a Paddlehub module of Python, and obtaining an emotion tendency score, wherein the obtained emotion score is in a range of-1 to 1, a score smaller than 0 represents a negative tendency, a score larger than 0 represents a positive tendency, and 0 represents neutral emotion.
4. The MOOC course evaluation method based on syntactic analysis and keyword detection as claimed in claim 1, wherein the specific process of obtaining the overall score in step (4) is as follows:
let the weight of the ith index score in the overall score be ωiEach index comprises k keywords, and the Score of the jth keyword is ScorejThen, the calculation method of the ith index score is as follows:
and if the total number of the indexes is n, the overall score S of the course is calculated by the following method:
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010592147.XA CN111813919A (en) | 2020-06-24 | 2020-06-24 | MOOC course evaluation method based on syntactic analysis and keyword detection |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010592147.XA CN111813919A (en) | 2020-06-24 | 2020-06-24 | MOOC course evaluation method based on syntactic analysis and keyword detection |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111813919A true CN111813919A (en) | 2020-10-23 |
Family
ID=72856511
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010592147.XA Pending CN111813919A (en) | 2020-06-24 | 2020-06-24 | MOOC course evaluation method based on syntactic analysis and keyword detection |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111813919A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114490526A (en) * | 2022-04-02 | 2022-05-13 | 北京新唐思创教育科技有限公司 | Course selection index file updating method, course searching method and device |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104881402A (en) * | 2015-06-02 | 2015-09-02 | 北京京东尚科信息技术有限公司 | Method and device for analyzing semantic orientation of Chinese network topic comment text |
| CN109255028A (en) * | 2018-08-28 | 2019-01-22 | 西安交通大学 | Quality of instruction integrated evaluating method based on teaching evaluation data reliability |
| CN110147552A (en) * | 2019-05-22 | 2019-08-20 | 南京邮电大学 | Educational resource quality evaluation method for digging and system based on natural language processing |
| WO2020101477A1 (en) * | 2018-11-14 | 2020-05-22 | Mimos Berhad | System and method for dynamic entity sentiment analysis |
-
2020
- 2020-06-24 CN CN202010592147.XA patent/CN111813919A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104881402A (en) * | 2015-06-02 | 2015-09-02 | 北京京东尚科信息技术有限公司 | Method and device for analyzing semantic orientation of Chinese network topic comment text |
| CN109255028A (en) * | 2018-08-28 | 2019-01-22 | 西安交通大学 | Quality of instruction integrated evaluating method based on teaching evaluation data reliability |
| WO2020101477A1 (en) * | 2018-11-14 | 2020-05-22 | Mimos Berhad | System and method for dynamic entity sentiment analysis |
| CN110147552A (en) * | 2019-05-22 | 2019-08-20 | 南京邮电大学 | Educational resource quality evaluation method for digging and system based on natural language processing |
Non-Patent Citations (1)
| Title |
|---|
| 刘亚男;肖明;刘江荣;徐烨;: "基于"中国大学MOOC"平台的MOOC质量评价研究", 软件导刊, no. 12 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114490526A (en) * | 2022-04-02 | 2022-05-13 | 北京新唐思创教育科技有限公司 | Course selection index file updating method, course searching method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Ahmed et al. | Tweeting India’s Nirbhaya protest: A study of emotional dynamics in an online social movement | |
| WO2021000909A1 (en) | Curriculum optimisation method, apparatus, and system | |
| CN102262634B (en) | Automatic questioning and answering method and system | |
| US20110270883A1 (en) | Automated Short Free-Text Scoring Method and System | |
| KR20180105693A (en) | Digital media content extraction and natural language processing system | |
| CN109255028A (en) | Quality of instruction integrated evaluating method based on teaching evaluation data reliability | |
| CN111242816B (en) | Multimedia teaching plan manufacturing method and system based on artificial intelligence | |
| CN109815491A (en) | Answer methods of marking, device, computer equipment and storage medium | |
| Agrawal et al. | Identifying enrichment candidates in textbooks | |
| US20150026184A1 (en) | Methods and systems for content management | |
| CN113610680A (en) | AI-based interactive reading material personalized recommendation method and system | |
| CN113360598A (en) | Matching method and device based on artificial intelligence, electronic equipment and storage medium | |
| CN110888989B (en) | Intelligent learning platform and construction method thereof | |
| US10275487B2 (en) | Demographic-based learning in a question answering system | |
| CN111813919A (en) | MOOC course evaluation method based on syntactic analysis and keyword detection | |
| Riza et al. | Natural language processing and levenshtein distance for generating error identification typed questions on TOEFL | |
| Zhu et al. | YUN111@ Dravidian-CodeMix-FIRE2020: Sentiment Analysis of Dravidian Code Mixed Text. | |
| CN116595188A (en) | Educational knowledge graph system based on artificial intelligence and big data | |
| Ye et al. | Answer quality evaluation of social Q&A platforms based on feature filtering | |
| CN113342953A (en) | Government affair question and answer method based on multi-model integration | |
| Elalfy et al. | Predicting best answer in community questions based on content and sentiment analysis | |
| Richter et al. | Tracking the evolution of written language competence: an NLP–based approach | |
| Tian et al. | Semantic similarity measure of natural language text through machine learning and a keyword‐aware cross‐encoder‐ranking summarizer—A case study using UCGIS GIS &T body of knowledge | |
| Anggrayni et al. | Question answering system using semantic reasoning on ontology for the history of the sumedang larang kingdom | |
| Ran et al. | Recommendation algorithm based business english writing training strategy |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |