CN107301200A - A kind of article appraisal procedure and system analyzed based on Sentiment orientation - Google Patents
A kind of article appraisal procedure and system analyzed based on Sentiment orientation Download PDFInfo
- Publication number
- CN107301200A CN107301200A CN201710367254.0A CN201710367254A CN107301200A CN 107301200 A CN107301200 A CN 107301200A CN 201710367254 A CN201710367254 A CN 201710367254A CN 107301200 A CN107301200 A CN 107301200A
- Authority
- CN
- China
- Prior art keywords
- target article
- article
- sentiment orientation
- word
- evaluating
- 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
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
- G06F16/34—Browsing; Visualisation therefor
-
- 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
- G06F16/35—Clustering; Classification
-
- 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
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/374—Thesaurus
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a kind of article appraisal procedure and system analyzed based on Sentiment orientation, methods described includes:Target article evaluating data is obtained using crawler capturing, barrage identification and speech recognition;The Sentiment orientation feature in target article evaluating data is extracted, the evaluation entry collection of target article is obtained;According to the evaluation entry collection average weighted score of the weight computing target article of default evaluation entry, target article recommended hour is obtained;The evaluation entry collection and target article recommended hour of visual presentation target article, so, by extracting the user based on natural language to the Sentiment orientation feature in article review, obtain the evaluation entry collection to target article, the quality of target article is objectively embodied, the reference value in terms of reading and instruction is provided to other users.
Description
Technical field
The present invention relates to information resources technical field, more particularly to a kind of article appraisal procedure analyzed based on Sentiment orientation
And system.
Background technology
With continuing to develop for scientific and technical and Internet technology, current internet information is in a kind of irregular
Among growing trend, internet has turned into the maximum information resource database in the whole world, and it brings revolution in the live and work to the mankind
Property change while, the problems such as also triggering " information overflow " " information puzzle ", with being increased using the personnel of internet, everybody
The producer that information is also become while as information user, then, how to arrange, excavate, organizing out high-quality
And the information that user needs is the problem of internet development is currently needed for solution.
Because internet has high interaction, anonymity, convenience, ageing and open feature, more and more
Information user can be delivered after use information by online rating system oneself to article, data message, webpage evaluation,
Express and oneself read service condition and each side emotion cognition, and these read service conditions and emotion cognition often embodies
The quality of these data messages, these valencys and gains in depth of comprehension when using, largely have impact on other users whether read and
Use these data messages.
The content of the invention
The technical problem existed based on background technology, the present invention proposes a kind of article assessment analyzed based on Sentiment orientation
Method and system;
A kind of article appraisal procedure analyzed based on Sentiment orientation proposed by the present invention, including:
S1, utilize crawler capturing, barrage identification and speech recognition obtain target article evaluating data;
S2, the Sentiment orientation feature extracted in target article evaluating data, obtain the evaluation entry collection of target article;
S3, the evaluation entry collection average weighted score according to the default weight computing target article for evaluating entry, obtain target text
Chapter recommended hour;
S4, the evaluation entry collection of visual presentation target article and target article recommended hour.
Preferably, in step s 2, the Sentiment orientation Feature Words, including:Emotion word, evaluating word and degree word;
Preferably, the emotion word includes positive emotion word and negative emotion word;The evaluating word includes positive evaluating word
With unfavorable ratings word.
Preferably, in step s 2, before the Sentiment orientation Feature Words in extraction target article evaluating data, in addition to:
Set up emotion word dictionary, evaluating word dictionary, degree word dictionary.
Preferably, step S2, is specifically included:
By feature extraction or keyword abstraction, the Sentiment orientation feature in target article evaluating data is extracted;
By vector space model by Sentiment orientation characteristic vector;
The similarity between Sentiment orientation feature is calculated, and selects appropriate algorithm to be clustered, commenting for target article is obtained
Valency entry collection.
Preferably, step S4, is specifically included:Mesh is shown by one or more forms in block diagram, radar map, curve map
Mark the evaluation entry collection and target article recommended hour of article.
A kind of article assessment system analyzed based on Sentiment orientation, including:
Data acquisition module, for obtaining target article evaluating data using crawler capturing, barrage identification and speech recognition;
Characteristic extracting module, for extracting the Sentiment orientation feature in target article evaluating data, obtains target article
Evaluate entry collection;
Recommended hour generation module, for the evaluation entry collection weighting according to the default weight computing target article for evaluating entry
Total score, obtains target article recommended hour;
Display module, evaluation entry collection and target article recommended hour for visual presentation target article.
Preferably, the data acquisition module, specifically for:The Sentiment orientation Feature Words include:Emotion word, evaluating word
With degree word;
Preferably, the emotion word includes positive emotion word and negative emotion word;The evaluating word includes positive evaluating word
With unfavorable ratings word.
Preferably, in addition to dictionary sets up module, it is connected with characteristic extracting module, for evaluating number extracting target article
Before Sentiment orientation feature in, emotion word dictionary, evaluating word dictionary, degree word dictionary are set up.
Preferably, the characteristic extracting module, specifically for:
By feature extraction or keyword abstraction, the Sentiment orientation feature in target article evaluating data is extracted;
By vector space model by Sentiment orientation characteristic vector;
The similarity between Sentiment orientation feature is calculated, and selects appropriate algorithm to be clustered, commenting for target article is obtained
Valency entry collection.
Preferably, the display module, specifically for:Pass through one or more forms in block diagram, radar map, curve map
Show the evaluation entry collection and target article recommended hour of target article.
The present invention extracts the Sentiment orientation feature in target article evaluating data by obtaining target article evaluating data,
The evaluation entry collection of target article is obtained, is weighted according to the evaluation entry collection of the weight computing target article of default evaluation entry total
Point, target article recommended hour is obtained, to the evaluation entry collection and target article recommended hour of user's visual presentation target article, such as
This, by extracting the user based on natural language to the Sentiment orientation feature in article review, obtains the evaluation to target article
Entry collection, objectively embodies the quality of target article, and the reference value in terms of reading and instruction is provided to other users,
The evaluation entry collection and target article recommended hour of target article are shown by the form of block diagram, radar map, curve map, it is convenient to use
The article for meeting oneself condition and article evaluation are quickly found in family from the article of magnanimity and article evaluation, save user when
Between, recall precision is improved, facilitates user quickly to make reading and uses decision-making, lift the Consumer's Experience of user.
Brief description of the drawings
Fig. 1 is a kind of schematic flow sheet for the article appraisal procedure analyzed based on Sentiment orientation proposed by the present invention;
Fig. 2 is a kind of module diagram for the article assessment system analyzed based on Sentiment orientation proposed by the present invention.
Embodiment
Reference picture 1, a kind of article appraisal procedure analyzed based on Sentiment orientation proposed by the present invention, including:
S1, utilize crawler capturing, barrage identification and speech recognition obtain target article evaluating data;
In concrete scheme, because user is in all kinds of articles in reading internet, the mode commented on article is not
It is identical to the greatest extent, so needing, by a variety of acquisition modes, target article evaluating data to be obtained in all directions, improve comment data and obtain effect
Rate.
S2, the Sentiment orientation feature extracted in target article evaluating data, obtain the evaluation entry collection of target article;Its
In, the Sentiment orientation Feature Words, including:Emotion word, evaluating word and degree word;Further, the emotion word includes front
Emotion word and negative emotion word;The evaluating word includes positive evaluating word and unfavorable ratings word;Commented specifically, extracting target article
Before Sentiment orientation Feature Words of the valence mumber in, in addition to:Set up emotion word dictionary, evaluating word dictionary, degree word dictionary.
This step, is specifically included:By feature extraction or keyword abstraction, the emotion in target article evaluating data is extracted
It is inclined to feature;By vector space model by Sentiment orientation characteristic vector;The similarity between Sentiment orientation feature is calculated, and
Selection appropriate algorithm is clustered, and obtains the evaluation entry collection of target article.
In concrete scheme, by feature extraction or keyword abstraction, the emotion extracted in target article evaluating data is inclined
To feature, obtain the evaluation entry collection of target article, these entry collection can clearly show user read the emotion after article and
Evaluate, in feature extraction or keyword abstraction, before extracting the Sentiment orientation feature in target article evaluating data, using a large amount of
Test document as training set, constantly fed back by machine learning algorithm, learn to improve the performance of Sentiment orientation feature extraction,
Until making it.
S3, the evaluation entry collection average weighted score according to the default weight computing target article for evaluating entry, obtain target text
Chapter recommended hour;
In concrete scheme, according to the weights of default evaluation entry, the evaluation entry collection average weighted score of article is calculated, with table
Show the importance that entry concentrates the evaluation entry of each article of evaluating of article.
S4, the evaluation entry collection of visual presentation target article and target article recommended hour.
This step, is specifically included:Target article is shown by one or more forms in block diagram, radar map, curve map
Evaluation entry collection and target article recommended hour.
In concrete scheme, by the form of block diagram, radar map, curve map show target article evaluation entry collection and
Target article recommended hour, facilitate user quickly found from the article of magnanimity and article evaluation the article that meets oneself condition and
Article is evaluated.
Reference picture 2, a kind of article assessment system analyzed based on Sentiment orientation proposed by the present invention, including:
Data acquisition module, for obtaining target article evaluating data using crawler capturing, barrage identification and speech recognition;
In concrete scheme, because user is in all kinds of articles in reading internet, the mode commented on article is not
It is identical to the greatest extent, so needing, by a variety of acquisition modes, target article evaluating data to be obtained in all directions, improve comment data and obtain effect
Rate.
Characteristic extracting module, is connected with data acquisition module, for extracting the Sentiment orientation in target article evaluating data
Feature, obtains the evaluation entry collection of target article;Wherein, the Sentiment orientation Feature Words include:Emotion word, evaluating word and degree
Word, specifically, the emotion word includes positive emotion word and negative emotion word;The evaluating word includes positive evaluating word and negative
Evaluating word, characteristic extracting module, specifically for:By feature extraction or keyword abstraction, extract in target article evaluating data
Sentiment orientation feature;By vector space model by Sentiment orientation characteristic vector;Calculate the phase between Sentiment orientation feature
Like degree, and select appropriate algorithm to be clustered, obtain the evaluation entry collection of target article.
Dictionary sets up module, is connected with characteristic extracting module, inclines for the emotion in target article evaluating data is extracted
To before feature, emotion word dictionary, evaluating word dictionary, degree word dictionary are set up.
In concrete scheme, by feature extraction or keyword abstraction, the emotion extracted in target article evaluating data is inclined
To feature, obtain the evaluation entry collection of target article, these entry collection can clearly show user read the emotion after article and
Evaluate, in feature extraction or keyword abstraction, before extracting the Sentiment orientation feature in target article evaluating data, using a large amount of
Test document as training set, constantly fed back by machine learning algorithm, learn to improve the performance of Sentiment orientation feature extraction,
Until making it.
Recommended hour generation module, is connected with characteristic extracting module, for according to the default weight computing target for evaluating entry
The evaluation entry collection average weighted score of article, obtains target article recommended hour;
In concrete scheme, according to the weights of default evaluation entry, the evaluation entry collection average weighted score of article is calculated, with table
Show the importance that entry concentrates the evaluation entry of each article of evaluating of article.
Display module, is connected with recommended hour generation module, evaluation entry collection and mesh for visual presentation target article
Article recommended hour is marked, specifically for:Target article is shown by one or more forms in block diagram, radar map, curve map
Evaluate entry collection and target article recommended hour.
In concrete scheme, by the form of block diagram, radar map, curve map show target article evaluation entry collection and
Target article recommended hour, facilitate user quickly found from the article of magnanimity and article evaluation the article that meets oneself condition and
Article is evaluated.
Present embodiment is by obtaining target article evaluating data, and the Sentiment orientation extracted in target article evaluating data is special
Levy, obtain the evaluation entry collection of target article, added according to the evaluation entry collection of the weight computing target article of default evaluation entry
Total score is weighed, target article recommended hour is obtained, recommended to the evaluation entry collection and target article of user's visual presentation target article
Point, in this way, by extracting the user based on natural language to the Sentiment orientation feature in article review, obtaining to target article
Entry collection is evaluated, the quality of target article is objectively embodied, the reference in terms of reading and instruction is provided to other users
Value, the evaluation entry collection and target article recommended hour of target article are shown by the form of block diagram, radar map, curve map,
Facilitate user quickly to find the article for meeting oneself condition and article evaluation from the article of magnanimity and article evaluation, save and use
The time at family, recall precision is improved, facilitate user quickly to make reading and use decision-making, lift the Consumer's Experience of user.
The foregoing is only a preferred embodiment of the present invention, but protection scope of the present invention be not limited thereto,
Any one skilled in the art the invention discloses technical scope in, technique according to the invention scheme and its
Inventive concept is subject to equivalent substitution or change, should all be included within the scope of the present invention.
Claims (10)
1. a kind of article appraisal procedure analyzed based on Sentiment orientation, it is characterised in that including:
S1, utilize crawler capturing, barrage identification and speech recognition obtain target article evaluating data;
S2, the Sentiment orientation feature extracted in target article evaluating data, obtain the evaluation entry collection of target article;
S3, the evaluation entry collection average weighted score according to the default weight computing target article for evaluating entry, obtain target article and push away
Recommend point;
S4, the evaluation entry collection of visual presentation target article and target article recommended hour.
2. the article appraisal procedure according to claim 1 analyzed based on Sentiment orientation, it is characterised in that in step S2
In, the Sentiment orientation Feature Words, including:Emotion word, evaluating word and degree word;
Preferably, the emotion word includes positive emotion word and negative emotion word;The evaluating word includes positive evaluating word and negative
Face evaluating word.
3. the article appraisal procedure according to claim 1 analyzed based on Sentiment orientation, it is characterised in that in step S2
In, before the Sentiment orientation Feature Words in extraction target article evaluating data, in addition to:Set up emotion word dictionary, evaluating word word
Allusion quotation, degree word dictionary.
4. the article appraisal procedure according to claim 1 analyzed based on Sentiment orientation, it is characterised in that step S2, tool
Body includes:
By feature extraction or keyword abstraction, the Sentiment orientation feature in target article evaluating data is extracted;
By vector space model by Sentiment orientation characteristic vector;
The similarity between Sentiment orientation feature is calculated, and selects appropriate algorithm to be clustered, the evaluating word of target article is obtained
Bar collection.
5. the article appraisal procedure according to claim 1 analyzed based on Sentiment orientation, it is characterised in that step S4, tool
Body includes:The evaluation entry collection and target of target article are shown by one or more forms in block diagram, radar map, curve map
Article recommended hour.
6. a kind of article assessment system analyzed based on Sentiment orientation, it is characterised in that including:
Data acquisition module, for obtaining target article evaluating data using crawler capturing, barrage identification and speech recognition;
Characteristic extracting module, for extracting the Sentiment orientation feature in target article evaluating data, obtains the evaluation of target article
Entry collection;
Recommended hour generation module, it is total for the evaluation entry collection weighting according to the default weight computing target article for evaluating entry
Point, obtain target article recommended hour;
Display module, evaluation entry collection and target article recommended hour for visual presentation target article.
7. the article assessment system according to claim 6 analyzed based on Sentiment orientation, it is characterised in that the data are obtained
Modulus block, specifically for:The Sentiment orientation Feature Words include:Emotion word, evaluating word and degree word;
Preferably, the emotion word includes positive emotion word and negative emotion word;The evaluating word includes positive evaluating word and negative
Face evaluating word.
8. the article assessment system according to claim 6 analyzed based on Sentiment orientation, it is characterised in that also including dictionary
Module is set up, is connected with characteristic extracting module, for before the Sentiment orientation feature in extracting target article evaluating data, building
Vertical emotion word dictionary, evaluating word dictionary, degree word dictionary.
9. the article assessment system according to claim 6 analyzed based on Sentiment orientation, it is characterised in that the feature is carried
Modulus block, specifically for:
By feature extraction or keyword abstraction, the Sentiment orientation feature in target article evaluating data is extracted;
By vector space model by Sentiment orientation characteristic vector;
The similarity between Sentiment orientation feature is calculated, and selects appropriate algorithm to be clustered, the evaluating word of target article is obtained
Bar collection.
10. the article assessment system according to claim 6 analyzed based on Sentiment orientation, it is characterised in that the displaying
Module, specifically for:The evaluation entry of target article is shown by one or more forms in block diagram, radar map, curve map
Collection and target article recommended hour.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710367254.0A CN107301200A (en) | 2017-05-23 | 2017-05-23 | A kind of article appraisal procedure and system analyzed based on Sentiment orientation |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710367254.0A CN107301200A (en) | 2017-05-23 | 2017-05-23 | A kind of article appraisal procedure and system analyzed based on Sentiment orientation |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107301200A true CN107301200A (en) | 2017-10-27 |
Family
ID=60137303
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710367254.0A Pending CN107301200A (en) | 2017-05-23 | 2017-05-23 | A kind of article appraisal procedure and system analyzed based on Sentiment orientation |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107301200A (en) |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107992548A (en) * | 2017-11-27 | 2018-05-04 | 网易传媒科技(北京)有限公司 | Information processing method, system, medium and computing device |
CN108121698A (en) * | 2017-11-29 | 2018-06-05 | 张宁 | Chinese text Emotion identification method and system |
CN108733652A (en) * | 2018-05-18 | 2018-11-02 | 大连民族大学 | The test method of film review emotional orientation analysis based on machine learning |
CN108804416A (en) * | 2018-05-18 | 2018-11-13 | 大连民族大学 | The training method of film review emotional orientation analysis based on machine learning |
CN109308487A (en) * | 2018-08-06 | 2019-02-05 | 同济大学 | A kind of advertising mechanism based on the analysis of barrage data |
CN109408808A (en) * | 2018-09-12 | 2019-03-01 | 中国传媒大学 | A kind of appraisal procedure and assessment system of artistic works |
CN109783800A (en) * | 2018-12-13 | 2019-05-21 | 北京百度网讯科技有限公司 | Acquisition methods, device, equipment and the storage medium of emotion keyword |
CN110196950A (en) * | 2019-02-28 | 2019-09-03 | 腾讯科技(深圳)有限公司 | Propagate the treating method and apparatus of account number |
CN112883146A (en) * | 2021-01-15 | 2021-06-01 | 上海柏观数据科技有限公司 | Talent evaluation result control method and device based on social information |
CN114626356A (en) * | 2020-12-08 | 2022-06-14 | 腾讯科技(深圳)有限公司 | Article feature generation method, device, equipment and storage medium |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101937462A (en) * | 2010-09-03 | 2011-01-05 | 中国科学院声学研究所 | Method and system for automatically evaluating literature |
CN102682120A (en) * | 2012-05-15 | 2012-09-19 | 合一网络技术(北京)有限公司 | Method,device and system for acquiring essential article commented on network |
CN102708140A (en) * | 2012-03-15 | 2012-10-03 | 冯志刚 | Microblog passage sorting method and system |
CN103049435A (en) * | 2013-01-04 | 2013-04-17 | 浙江工商大学 | Text fine granularity sentiment analysis method and text fine granularity sentiment analysis device |
CN105469282A (en) * | 2015-12-01 | 2016-04-06 | 成都知数科技有限公司 | Online brand assessment method based on text comments |
US20160371261A1 (en) * | 2015-06-19 | 2016-12-22 | Gordon V. Cormack | Systems and methods for conducting a highly autonomous technology-assisted review classification |
CN106296282A (en) * | 2016-08-08 | 2017-01-04 | 南京大学 | A kind of net purchase Product evaluation method marked based on user comment and history |
-
2017
- 2017-05-23 CN CN201710367254.0A patent/CN107301200A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101937462A (en) * | 2010-09-03 | 2011-01-05 | 中国科学院声学研究所 | Method and system for automatically evaluating literature |
CN102708140A (en) * | 2012-03-15 | 2012-10-03 | 冯志刚 | Microblog passage sorting method and system |
CN102682120A (en) * | 2012-05-15 | 2012-09-19 | 合一网络技术(北京)有限公司 | Method,device and system for acquiring essential article commented on network |
CN103049435A (en) * | 2013-01-04 | 2013-04-17 | 浙江工商大学 | Text fine granularity sentiment analysis method and text fine granularity sentiment analysis device |
US20160371261A1 (en) * | 2015-06-19 | 2016-12-22 | Gordon V. Cormack | Systems and methods for conducting a highly autonomous technology-assisted review classification |
CN105469282A (en) * | 2015-12-01 | 2016-04-06 | 成都知数科技有限公司 | Online brand assessment method based on text comments |
CN106296282A (en) * | 2016-08-08 | 2017-01-04 | 南京大学 | A kind of net purchase Product evaluation method marked based on user comment and history |
Cited By (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107992548A (en) * | 2017-11-27 | 2018-05-04 | 网易传媒科技(北京)有限公司 | Information processing method, system, medium and computing device |
CN108121698A (en) * | 2017-11-29 | 2018-06-05 | 张宁 | Chinese text Emotion identification method and system |
CN108804416B (en) * | 2018-05-18 | 2022-08-09 | 大连民族大学 | Training method for film evaluation emotion tendency analysis based on machine learning |
CN108733652A (en) * | 2018-05-18 | 2018-11-02 | 大连民族大学 | The test method of film review emotional orientation analysis based on machine learning |
CN108804416A (en) * | 2018-05-18 | 2018-11-13 | 大连民族大学 | The training method of film review emotional orientation analysis based on machine learning |
CN109308487A (en) * | 2018-08-06 | 2019-02-05 | 同济大学 | A kind of advertising mechanism based on the analysis of barrage data |
CN109308487B (en) * | 2018-08-06 | 2021-03-30 | 同济大学 | Advertisement putting method based on bullet screen data analysis |
CN109408808A (en) * | 2018-09-12 | 2019-03-01 | 中国传媒大学 | A kind of appraisal procedure and assessment system of artistic works |
CN109408808B (en) * | 2018-09-12 | 2023-08-22 | 中国传媒大学 | Evaluation method and evaluation system for literature works |
CN109783800A (en) * | 2018-12-13 | 2019-05-21 | 北京百度网讯科技有限公司 | Acquisition methods, device, equipment and the storage medium of emotion keyword |
CN109783800B (en) * | 2018-12-13 | 2024-04-12 | 北京百度网讯科技有限公司 | Emotion keyword acquisition method, device, equipment and storage medium |
CN110196950A (en) * | 2019-02-28 | 2019-09-03 | 腾讯科技(深圳)有限公司 | Propagate the treating method and apparatus of account number |
CN110196950B (en) * | 2019-02-28 | 2023-10-24 | 腾讯科技(深圳)有限公司 | Processing method and device for propagating account |
CN114626356A (en) * | 2020-12-08 | 2022-06-14 | 腾讯科技(深圳)有限公司 | Article feature generation method, device, equipment and storage medium |
CN112883146A (en) * | 2021-01-15 | 2021-06-01 | 上海柏观数据科技有限公司 | Talent evaluation result control method and device based on social information |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107301200A (en) | A kind of article appraisal procedure and system analyzed based on Sentiment orientation | |
CN108536681B (en) | Intelligent question-answering method, device, equipment and storage medium based on emotion analysis | |
CN110209897B (en) | Intelligent dialogue method, device, storage medium and equipment | |
CN110489755A (en) | Document creation method and device | |
CN108984530A (en) | A kind of detection method and detection system of network sensitive content | |
CN108804512A (en) | Generating means, method and the computer readable storage medium of textual classification model | |
CN102682120B (en) | Method and device for acquiring essential article commented on network | |
CN105045857A (en) | Social network rumor recognition method and system | |
CN107766371A (en) | A kind of text message sorting technique and its device | |
CN108074016B (en) | User relationship strength prediction method, device and equipment based on location social network | |
CN104899335A (en) | Method for performing sentiment classification on network public sentiment of information | |
CN102841940B (en) | Document summary extracting method based on data reconstruction | |
CN108776940A (en) | A kind of intelligent food and drink proposed algorithm excavated based on text comments | |
CN102708164A (en) | Method and system for calculating movie expectation | |
CN108090098B (en) | Text processing method and device | |
CN104915399A (en) | Recommended data processing method based on news headline and recommended data processing method system based on news headline | |
CN106296288A (en) | A kind of commodity method of evaluating performance under assessing network text guiding | |
CN110287405A (en) | The method, apparatus and storage medium of sentiment analysis | |
CN105279148A (en) | User review consistency judgment method of APP (Application) software | |
CN106294676B (en) | A kind of data retrieval method of ecommerce government system | |
CN109902157A (en) | A kind of training sample validation checking method and device | |
CN104598648A (en) | Interactive gender identification method and device for microblog user | |
CN108733652A (en) | The test method of film review emotional orientation analysis based on machine learning | |
CN105447026A (en) | Web information extraction method based on minimum weight communication determining set in multi-view image | |
CN106055657A (en) | Evaluation system for film viewing index of specific population |
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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20171027 |