CN109190121A - Car review sentiment analysis method based on automobile body and part-of-speech rule - Google Patents
Car review sentiment analysis method based on automobile body and part-of-speech rule Download PDFInfo
- Publication number
- CN109190121A CN109190121A CN201811020000.2A CN201811020000A CN109190121A CN 109190121 A CN109190121 A CN 109190121A CN 201811020000 A CN201811020000 A CN 201811020000A CN 109190121 A CN109190121 A CN 109190121A
- Authority
- CN
- China
- Prior art keywords
- automobile
- comment
- speech rule
- word
- emotion
- 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
- 238000004458 analytical method Methods 0.000 title claims abstract description 31
- 238000012552 review Methods 0.000 title claims abstract description 15
- 230000008451 emotion Effects 0.000 claims abstract description 44
- 230000002996 emotional effect Effects 0.000 claims abstract description 24
- 238000000034 method Methods 0.000 claims description 17
- 238000012549 training Methods 0.000 claims description 9
- 238000011156 evaluation Methods 0.000 claims description 7
- 238000012545 processing Methods 0.000 claims description 7
- 239000000284 extract Substances 0.000 claims description 6
- 238000013507 mapping Methods 0.000 claims description 3
- 230000011218 segmentation Effects 0.000 claims description 3
- 230000015572 biosynthetic process Effects 0.000 claims 1
- 230000000694 effects Effects 0.000 description 3
- 238000010801 machine learning Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 244000097202 Rathbunia alamosensis Species 0.000 description 1
- 235000009776 Rathbunia alamosensis Nutrition 0.000 description 1
- 238000009412 basement excavation Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/237—Lexical tools
- G06F40/242—Dictionaries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/253—Grammatical analysis; Style critique
Abstract
A kind of car review sentiment analysis method based on automobile body and part-of-speech rule provided by the invention, comprising: building automotive field ontology dictionary, sentiment dictionary and emotion adjust dictionary；Obtain comment of the user to automobile；According to emotion word, negative word and the degree adverb in sentiment dictionary and emotion adjustment dictionary identification comment, according to automobile Feature Words in the identification comment of automotive field ontology dictionary and automobile Feature Words are mapped to corresponding automotive performance dimension；Sentiment analysis part-of-speech rule is extracted from user comment, is built into effective sentiment analysis part-of-speech rule set；Corresponding emotion, which is extracted, from comment sentence using part-of-speech rule set comments on viewpoint sentence, according to sentiment dictionary, degree dictionary and adjustment dictionary, the comprehensive emotional value of user for corresponding to automotive performance dimension in car review is calculated separately, fine granularity, digitized user feeling value are obtained.
Description
Technical field
The present invention relates to a kind of analysis method more particularly to a kind of car review feelings based on automobile body and part-of-speech rule
Feel analysis method.
Background technique
Most domestic auto vendor relies primarily on the shop 4S, questionnaire survey, user visiting, telephone interview, dealer at present
Equal traditional channels test obtaining the purchase car body of small part user and suggestion feedback, and that there are timeliness is low, at high cost, the period is long, sample
It is few to wait limitation.It is flourished with the family of automobile, Sina's automobile, Netease's automobile etc. for the professional car website of representative, is numerous nets
The people, which share, to be purchased car body and tests and provide platform with product feedback with exchange.These platforms generate magnanimity automobile online comment information be
Auto vendor obtains high timeliness, large-scale field feedback provides possibility.But at the same time, auto vendor of China is overall
The level of informatization is generally relatively low, and most of auto vendors do not have accurate, the quick excavation effective information from magnanimity comment also
Ability mainly takes the form browsed one by one from forum to collect field feedback at present, extremely low to online comment utilization rate.
As online comment quantity is increasing and product attribute is increasingly various, enterprise is intended not only to acquisition user and sees to product entirety
Method prefers to understand from comment user to the opinion of product particular community, could produce and provide the production for meeting the market demand
Product and service.
Text emotion analysis method is broadly divided into the analysis method based on sentiment dictionary and the feelings based on machine learning at present
Feel analysis method.The existing sentiment analysis method based on sentiment dictionary, has ignored the context semantic relation of word, word
It isolates and comes out from sentence, influence the effect of comment text Sentiment orientation classification；And the sentiment analysis method based on machine learning
Processing entire article or sentence effect it is preferable, but to more fine-grained text carry out sentiment analysis when effect it is not ideal enough.
Therefore, in order to solve the above-mentioned technical problem, need to propose a kind of new method.
Summary of the invention
In view of this, the object of the present invention is to provide a kind of car review emotions based on automobile body and part-of-speech rule point
Analysis method can convert consumers' opinions information to emotional value and carry out emotional semantic classification, improve the accuracy of emotional semantic classification.
A kind of car review sentiment analysis method based on automobile body and part-of-speech rule provided by the invention, comprising:
It constructs automotive field ontology dictionary, sentiment dictionary and emotion and adjusts dictionary；
Obtain comment of the user to automobile；
Emotion word, negative word and degree adverb in comment are identified according to sentiment dictionary and emotion adjustment dictionary, according to
Automotive field ontology dictionary identifies automobile Feature Words in comment and automobile Feature Words is mapped to corresponding automotive performance dimension；
The part-of-speech rule of building comment sentence, and determine effective part-of-speech rule；
Sentiment analysis part-of-speech rule set corresponding with effective part-of-speech rule is extracted from user comment；
User feeling value is calculated according to effective sentiment analysis part-of-speech rule set.
Further, the automotive field ontology includes automobile category ontology, automotive performance ontology and automobile component ontology；
Wherein, automotive field ontology dictionary is established according to the following method:
Obtain evaluation of the user to automobile, and extract evaluation medium-high frequency notional word, high frequency notional word include automobile brand,
Automobile rank, vehicle system, vehicle, performance indicator and automobile component；
The automotive performance that automobile component is embodied is extracted, and establishes the pass of the mapping between automobile component and performance indicator
System；
High frequency notional word is subjected to classification processing, automobile brand, automobile rank, vehicle system and vehicle are referred to automobile product
Class ontology, is referred to automotive performance ontology for performance indicator, and automobile component is referred to automobile component ontology.
Further, part-of-speech rule is determined according to the following method:
It chooses M user comment sentence and forms training set, stop words and word segmentation processing shape are removed to comment sentence
At comment viewpoint sentence；
Part-of-speech tagging is carried out to each word of comment viewpoint sentence: including automobile Feature Words mark, negative word mark, emotion word mark
Note and degree adverb mark；
Part of speech assemblage characteristic in analysis comment viewpoint sentence, extracts and combines to the effective part of speech of sentiment analysis.
Further, effective part-of-speech rule is determined according to the following method:
Calculate the confidence level and support of the part-of-speech rule in the training set of comment viewpoint sentence；
Confidence level and support are compared with the confidence threshold value of setting and support threshold respectively, current part of speech
When the confidence level of rule is greater than support threshold greater than the confidence threshold value and support of setting, current part-of-speech rule is effective
Part-of-speech rule；
Wherein, the support of part-of-speech rule is that the comment to match in all viewpoint sentence Q with part-of-speech rule r in training set is seen
Point sentence quantity q accounts for the ratio of comment viewpoint sentence sum Q；
The confidence level of part-of-speech rule is to account for regular r with the quantity of the matched comment viewpoint sentence q of part-of-speech rule r to cover viewpoint
The ratio of sentence quantity.
Further, the emotional value of user is calculated according to the following method:
The automobile Feature Words in viewpoint sentence and the journey before and after emotion word corresponding with the automobile Feature Words, emotion word will be commented on
It spends adverbial word and negative word forms an emotion member；
Calculate the emotional value Se (t) of the Feature Words t of each comment viewpoint sentence:
Wherein, Se (t) is in comment viewpoint sentence
The emotional value of Feature Words t, S (wk) it is emotion word w in emotion memberkEmotional value, wei (d) be emotion member in degree word weight, l
For the number of negative word in emotion member, n is the number for commenting on the emotion member in viewpoint sentence；
Calculate automobile feature class AsiEmotional value Se (Asi):
Wherein, i indicates feature class AsiIn automobile Feature Words different comprising i, N is characterized As in classiInclude Feature Words t
Viewpoint sentence sum；
Calculate the emotional value Se (car of Automobile systemj):
Wherein, q is different feature class AsiEmotional value weight, j indicates to contain the different feature classes of j when front truck system
Not, p is the sum when the comment viewpoint sentence of front truck system；
Calculate the whole emotional value Se (brand) of automobile brand；
Wherein, w is the vehicle system number of current automobile brand, and k is the weight of different vehicle systems, and P is all vehicles of current brand
The comment sum of system.
Beneficial effects of the present invention: through the invention: the Feature Words in car review being identified and returned using ontology
Class obtains the relationship of Feature Words and emotion word by part-of-speech rule combination sentiment dictionary, to excavate user to automobile dissimilarity
Fine granularity, digitized emotion can be converted by consumers' opinions information finally by affection computation with the subjectivity opinion of component
It is worth and carries out emotional semantic classification, improves the accuracy of emotional semantic classification.
Detailed description of the invention
The invention will be further described with reference to the accompanying drawings and examples:
Fig. 1 is flow chart of the invention.
Fig. 2 is part-of-speech tagging schematic diagram of the invention.
Specific embodiment
Further description is made to the present invention below in conjunction with Figure of description:
A kind of car review sentiment analysis method based on automobile body and part-of-speech rule provided by the invention, comprising:
It constructs automotive field ontology dictionary, sentiment dictionary and emotion and adjusts dictionary；
Obtain comment of the user to automobile；
Emotion word, negative word and degree adverb in comment are identified according to sentiment dictionary and emotion adjustment dictionary, according to
Automotive field ontology dictionary identifies automobile Feature Words in comment and automobile Feature Words is mapped to corresponding automotive performance dimension；
The part-of-speech rule of building comment sentence, and determine effective part-of-speech rule；
Sentiment analysis part-of-speech rule set corresponding with effective part-of-speech rule is extracted from user comment；
User feeling value is calculated according to the set of effective sentiment analysis part-of-speech rule；
By the above method, the Feature Words in car review are identified and sorted out using ontology, pass through part-of-speech rule
The relationship that Feature Words and emotion word are obtained in conjunction with sentiment dictionary, to excavate user to the subjectivity of automobile different performance and component
Opinion converts emotional value for consumers' opinions information finally by affection computation and carries out emotional semantic classification, improves emotional semantic classification
Accuracy.
In the present embodiment, the automotive field ontology includes automobile category ontology, automotive performance ontology and automobile component
Ontology；
Wherein, automotive field ontology dictionary is established according to the following method:
Obtain evaluation of the user to automobile, and extract evaluation medium-high frequency notional word, high frequency notional word include automobile brand,
Automobile rank, vehicle system, vehicle, performance indicator and automobile component；
The automotive performance that automobile component is embodied is extracted, and establishes the pass of the mapping between automobile component and performance indicator
System；In this way, it can effectively extract and performance is indirectly commented on containing only automobile component in comment；
High frequency notional word is subjected to classification processing, automobile brand, automobile rank, vehicle system and vehicle are referred to automobile product
Class ontology, is referred to automotive performance ontology for performance indicator, and automobile component is referred to automobile component ontology, passes through above-mentioned side
Method, can accurately be commented in Feature Words of all categories, wherein the contingency table between automotive performance and component is as follows:
In the present embodiment, part-of-speech rule is determined according to the following method:
It chooses M user comment sentence and forms training set, stop words and word segmentation processing shape are removed to comment sentence
At comment viewpoint sentence；
Each word of comment viewpoint sentence is labeled: including part-of-speech tagging, automobile Feature Words mark, negative word mark, feelings
Feel word mark and degree adverb mark；
Word containing automobile Feature Words, negative word, emotion word and degree adverb in comment viewpoint sentence is extracted into group
At part-of-speech rule., for example, pre-processing the mark that can be obtained as shown in Figure 2 to a certain comment, wherein the letter in mark
The meaning of expression is as follows:
Part of speech label
Semantic label
In the present embodiment, effective part-of-speech rule is determined according to the following method:
Calculate the confidence level and support of the part-of-speech rule in the training set of comment viewpoint sentence；
Confidence level and support are compared with the confidence threshold value of setting and support threshold respectively, current part of speech
When the confidence level of rule is greater than support threshold greater than the confidence threshold value and support of setting, current part-of-speech rule is effective
Part-of-speech rule；
Wherein, the support of part-of-speech rule is that the comment to match in all viewpoint sentence Q with part-of-speech rule r in training set is seen
Point sentence quantity q accounts for the ratio of comment viewpoint sentence sum Q；
The confidence level of part-of-speech rule is to account for regular r with the quantity of the matched comment viewpoint sentence q of part-of-speech rule r to cover viewpoint
The ratio of sentence quantity.
In the present embodiment, the emotional value of user is calculated according to the following method:
The automobile Feature Words in viewpoint sentence and the journey before and after emotion word corresponding with the automobile Feature Words, emotion word will be commented on
It spends adverbial word and negative word forms an emotion member；
Calculate the emotional value Se (t) of the Feature Words t of each comment viewpoint sentence:
Wherein, Se (t) is in comment viewpoint sentence
The emotional value of Feature Words t, S (wk) it is emotion word w in emotion memberkEmotional value, wei (d) be emotion member in degree word weight, l
For the number of negative word in emotion member, n is the number for commenting on the emotion member in viewpoint sentence；
Calculate automobile feature class AsiEmotional value Se (Asi):
Wherein, i indicates feature class AsiIn automobile Feature Words different comprising i, N is characterized As in classiInclude Feature Words t
Viewpoint sentence sum；
Calculate the emotional value Se (car of Automobile systemj):
Wherein, q is different feature class AsiEmotional value weight, j indicates to contain the different feature classes of j when front truck system
Not, p is the sum when the comment viewpoint sentence of front truck system；
Calculate the whole emotional value Se (brand) of automobile brand；
Wherein, w is the vehicle system number of current automobile brand, and k is the weight of different vehicle systems, and P is all vehicles of current brand
The comment sum of system；It is then front evaluation when user feeling value is less than zero is then unfavorable ratings when user feeling value is greater than 0.
Finally, it is stated that the above examples are only used to illustrate the technical scheme of the present invention and are not limiting, although referring to compared with
Good embodiment describes the invention in detail, those skilled in the art should understand that, it can be to skill of the invention
Art scheme is modified or replaced equivalently, and without departing from the objective and range of technical solution of the present invention, should all be covered at this
In the scope of the claims of invention.
Claims (5)
1. a kind of car review sentiment analysis method based on automobile body and part-of-speech rule, it is characterised in that: include:
It constructs automotive field ontology dictionary, sentiment dictionary and emotion and adjusts dictionary；
Obtain comment of the user to automobile；
According to emotion word, negative word and the degree adverb in sentiment dictionary and emotion adjustment dictionary identification comment, according to automobile
Domain body dictionary identifies automobile Feature Words in comment and automobile Feature Words is mapped to corresponding automotive performance dimension；
The part-of-speech rule of building comment sentence, and determine effective part-of-speech rule；
Sentiment analysis part-of-speech rule set corresponding with effective part-of-speech rule is extracted from user comment；
User feeling value is calculated according to effective sentiment analysis part-of-speech rule set.
2. the car review sentiment analysis method based on automobile body and part-of-speech rule, feature exist according to claim 1
In: the automotive field ontology includes automobile category ontology, automotive performance ontology and automobile component ontology；
Wherein, automotive field ontology dictionary is established according to the following method:
Evaluation of the user to automobile is obtained, and extracts evaluation medium-high frequency notional word, high frequency notional word includes automobile brand, automobile
Rank, vehicle system, vehicle, performance indicator and automobile component；
The automotive performance that automobile component is embodied is extracted, and establishes the mapping relations between automobile component and performance indicator；
High frequency notional word is subjected to classification processing, automobile brand, automobile rank, vehicle system and vehicle are referred to automobile category sheet
Body, is referred to automotive performance ontology for performance indicator, and automobile component is referred to automobile component ontology.
3. the car review sentiment analysis method based on automobile body and part-of-speech rule, feature exist according to claim 1
In: part-of-speech rule is determined according to the following method:
It chooses M user comment sentence and forms training set, stop words is removed to comment sentence and word segmentation processing formation is commented
By viewpoint sentence；
To comment viewpoint sentence each word carry out part-of-speech tagging: including automobile Feature Words mark, negative word mark, emotion word mark with
And degree adverb mark；
Part of speech assemblage characteristic in analysis comment viewpoint sentence, extracts and combines to the effective part of speech of sentiment analysis.
4. the car review sentiment analysis method based on automobile body and part-of-speech rule, feature exist according to claim 3
In: effective part-of-speech rule is determined according to the following method:
Calculate the confidence level and support of the part-of-speech rule in the training set of comment viewpoint sentence；
Confidence level and support are compared with the confidence threshold value of setting and support threshold respectively, current part-of-speech rule
Confidence level be greater than setting confidence threshold value and support be greater than support threshold when, current part-of-speech rule be effective part of speech
Rule；
Wherein, the support of part-of-speech rule is the comment viewpoint sentence to match in all viewpoint sentence Q with part-of-speech rule r in training set
Quantity q accounts for the ratio of comment viewpoint sentence sum Q；
The confidence level of part-of-speech rule is to account for regular r with the quantity of the matched comment viewpoint sentence q of part-of-speech rule r to cover viewpoint sentence number
The ratio of amount.
5. the car review sentiment analysis method based on automobile body and part-of-speech rule, feature exist according to claim 1
In: the emotional value of user is calculated according to the following method:
The automobile Feature Words in viewpoint sentence and the degree pair before and after emotion word corresponding with the automobile Feature Words, emotion word will be commented on
Word and negative word form an emotion member；
Calculate the emotional value Se (t) of the Feature Words t of each comment viewpoint sentence:
Wherein, Se (t) is feature in comment viewpoint sentence
The emotional value of word t, S (wk) it is emotion word w in emotion memberkEmotional value, wei (d) be emotion member in degree word weight, l is feelings
The number of negative word in sense member, n are the number for commenting on the emotion member in viewpoint sentence；
Calculate automobile feature class AsiEmotional value Se (Asi):
Wherein, i indicates feature class AsiIn automobile Feature Words different comprising i, N is characterized As in classiSight comprising Feature Words t
The sum of point sentence；
Calculate the emotional value Se (car of Automobile systemj):
Wherein, q is different feature class AsiEmotional value weight, j indicates to contain the different feature classifications of j when front truck system, and p is
When the sum of the comment viewpoint sentence of front truck system；
Calculate the whole emotional value Se (brand) of automobile brand；
Wherein, w is the vehicle system number of current automobile brand, and k is the weight of different vehicle systems, and P is all vehicle systems of current brand
Comment sum.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811020000.2A CN109190121A (en) | 2018-09-03 | 2018-09-03 | Car review sentiment analysis method based on automobile body and part-of-speech rule |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811020000.2A CN109190121A (en) | 2018-09-03 | 2018-09-03 | Car review sentiment analysis method based on automobile body and part-of-speech rule |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109190121A true CN109190121A (en) | 2019-01-11 |
Family
ID=64917889
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811020000.2A Pending CN109190121A (en) | 2018-09-03 | 2018-09-03 | Car review sentiment analysis method based on automobile body and part-of-speech rule |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109190121A (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109816443A (en) * | 2019-01-18 | 2019-05-28 | 安徽商贸职业技术学院 | A kind of user's pain spot quantization method based on sentiment analysis |
| CN110032735A (en) * | 2019-03-21 | 2019-07-19 | 合肥工业大学 | The analysis method of implicit viewpoint feeling polarities |
| CN110415071A (en) * | 2019-07-03 | 2019-11-05 | 西南交通大学 | A kind of competing product control methods of automobile based on opining mining analysis |
| CN112053080A (en) * | 2020-09-15 | 2020-12-08 | 上海唐硕信息科技有限公司 | Brand scoring method based on user experience perception |
| CN112395484A (en) * | 2020-11-18 | 2021-02-23 | 天津大学 | User satisfaction evaluation method for automatically driving automobile |
| CN112527963A (en) * | 2020-12-17 | 2021-03-19 | 深圳市欢太科技有限公司 | Multi-label emotion classification method and device based on dictionary, equipment and storage medium |
| CN113378577A (en) * | 2021-05-08 | 2021-09-10 | 重庆航天信息有限公司 | Food safety evaluation text emotional tendency analysis method |
| CN113378578A (en) * | 2021-05-08 | 2021-09-10 | 重庆航天信息有限公司 | Food and medicine public opinion analysis method |
| CN115659961A (en) * | 2022-11-01 | 2023-01-31 | 广东美云智数科技有限公司 | Method, apparatus and computer storage medium for extracting text viewpoints |
| CN116822533A (en) * | 2023-07-25 | 2023-09-29 | 北京卓思天成数据咨询股份有限公司 | Automobile design defect monitoring and identifying method |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103455562A (en) * | 2013-08-13 | 2013-12-18 | 西安建筑科技大学 | Text orientation analysis method and product review orientation discriminator on basis of same |
| CN103473262A (en) * | 2013-07-17 | 2013-12-25 | 北京航空航天大学 | Automatic classification system and automatic classification method for Web comment viewpoint on the basis of association rule |
| CN104268197A (en) * | 2013-09-22 | 2015-01-07 | 中科嘉速(北京)并行软件有限公司 | Industry comment data fine grain sentiment analysis method |
| CN104731923A (en) * | 2015-03-26 | 2015-06-24 | 无锡中科泛在信息技术研发中心有限公司 | Construction method for Internet product review excavation noumenon lexicon |
| CN105868185A (en) * | 2016-05-16 | 2016-08-17 | 南京邮电大学 | Part-of-speech-tagging-based dictionary construction method applied in shopping comment emotion analysis |
| CN107203520A (en) * | 2016-03-16 | 2017-09-26 | 中国科学院上海高等研究院 | The method for building up of hotel's sentiment dictionary, the sentiment analysis method and system of comment |
| CN107491531A (en) * | 2017-08-18 | 2017-12-19 | 华南师范大学 | Chinese network comment sensibility classification method based on integrated study framework |
-
2018
- 2018-09-03 CN CN201811020000.2A patent/CN109190121A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103473262A (en) * | 2013-07-17 | 2013-12-25 | 北京航空航天大学 | Automatic classification system and automatic classification method for Web comment viewpoint on the basis of association rule |
| CN103455562A (en) * | 2013-08-13 | 2013-12-18 | 西安建筑科技大学 | Text orientation analysis method and product review orientation discriminator on basis of same |
| CN104268197A (en) * | 2013-09-22 | 2015-01-07 | 中科嘉速(北京)并行软件有限公司 | Industry comment data fine grain sentiment analysis method |
| CN104731923A (en) * | 2015-03-26 | 2015-06-24 | 无锡中科泛在信息技术研发中心有限公司 | Construction method for Internet product review excavation noumenon lexicon |
| CN107203520A (en) * | 2016-03-16 | 2017-09-26 | 中国科学院上海高等研究院 | The method for building up of hotel's sentiment dictionary, the sentiment analysis method and system of comment |
| CN105868185A (en) * | 2016-05-16 | 2016-08-17 | 南京邮电大学 | Part-of-speech-tagging-based dictionary construction method applied in shopping comment emotion analysis |
| CN107491531A (en) * | 2017-08-18 | 2017-12-19 | 华南师范大学 | Chinese network comment sensibility classification method based on integrated study framework |
Non-Patent Citations (3)
| Title |
|---|
| 唐晓波 等: "基于特征本体的微博产品评论情感分析", 《图书情报工作》 * |
| 姚天昉 等: "一个用于汉语汽车评论的意见挖掘系统", 《中文信息处理前沿进展——中国中文信息学会二十五周年学术会议论文集》 * |
| 李敏: "基于情感本体树的多属性汽车评价系统", 《中国优秀硕士学位论文全文数据库-信息科技辑》 * |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109816443A (en) * | 2019-01-18 | 2019-05-28 | 安徽商贸职业技术学院 | A kind of user's pain spot quantization method based on sentiment analysis |
| CN110032735B (en) * | 2019-03-21 | 2023-04-07 | 合肥工业大学 | Analysis method for sentiment polarity of implicit viewpoint |
| CN110032735A (en) * | 2019-03-21 | 2019-07-19 | 合肥工业大学 | The analysis method of implicit viewpoint feeling polarities |
| CN110415071A (en) * | 2019-07-03 | 2019-11-05 | 西南交通大学 | A kind of competing product control methods of automobile based on opining mining analysis |
| CN110415071B (en) * | 2019-07-03 | 2024-02-27 | 西南交通大学 | Automobile competitive product comparison method based on viewpoint mining analysis |
| CN112053080A (en) * | 2020-09-15 | 2020-12-08 | 上海唐硕信息科技有限公司 | Brand scoring method based on user experience perception |
| CN112395484A (en) * | 2020-11-18 | 2021-02-23 | 天津大学 | User satisfaction evaluation method for automatically driving automobile |
| CN112527963A (en) * | 2020-12-17 | 2021-03-19 | 深圳市欢太科技有限公司 | Multi-label emotion classification method and device based on dictionary, equipment and storage medium |
| CN112527963B (en) * | 2020-12-17 | 2024-05-03 | 深圳市欢太科技有限公司 | Dictionary-based multi-label emotion classification method and device, equipment and storage medium |
| CN113378577A (en) * | 2021-05-08 | 2021-09-10 | 重庆航天信息有限公司 | Food safety evaluation text emotional tendency analysis method |
| CN113378578A (en) * | 2021-05-08 | 2021-09-10 | 重庆航天信息有限公司 | Food and medicine public opinion analysis method |
| CN115659961A (en) * | 2022-11-01 | 2023-01-31 | 广东美云智数科技有限公司 | Method, apparatus and computer storage medium for extracting text viewpoints |
| CN115659961B (en) * | 2022-11-01 | 2023-08-04 | 美云智数科技有限公司 | Method, apparatus and computer storage medium for extracting text views |
| CN116822533A (en) * | 2023-07-25 | 2023-09-29 | 北京卓思天成数据咨询股份有限公司 | Automobile design defect monitoring and identifying method |
| CN116822533B (en) * | 2023-07-25 | 2024-02-02 | 北京卓思天成数据咨询股份有限公司 | Automobile design defect monitoring and identifying method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109190121A (en) | Car review sentiment analysis method based on automobile body and part-of-speech rule | |
| Taboada et al. | Analyzing appraisal automatically | |
| CN107506480B (en) | Double-layer graph structure recommendation method based on comment mining and density clustering | |
| Lerman et al. | Sentiment summarization: evaluating and learning user preferences | |
| CN107862087B (en) | Emotion analysis method and device based on big data and deep learning and storage medium | |
| CN105787025B (en) | Network platform public account classification method and device | |
| CN103150333B (en) | Opinion leader identification method in microblog media | |
| CN102682130B (en) | Text sentiment classification method and system | |
| CN102929860B (en) | Chinese clause emotion polarity distinguishing method based on context | |
| CN105426514A (en) | Personalized mobile APP recommendation method | |
| CN106484829B (en) | A kind of foundation and microblogging diversity search method of microblogging order models | |
| TW201115370A (en) | Systems and methods for capturing and managing collective social intelligence information | |
| Gan et al. | Restaurant Rating: Industrial Standard and Word-of-Mouth--A Text Mining and Multi-dimensional Sentiment Analysis | |
| CN104199822A (en) | Method and system for identifying demand classification corresponding to searching | |
| CN105138508A (en) | Preference diffusion based context recommendation system | |
| CN111259141A (en) | Social media corpus emotion analysis method based on multi-model fusion | |
| CN105740382A (en) | Aspect classification method for short comment texts | |
| CN105630768A (en) | Cascaded conditional random field-based product name recognition method and device | |
| CN103995853A (en) | Multi-language emotional data processing and classifying method and system based on key sentences | |
| CN107103093B (en) | Short text recommendation method and device based on user behavior and emotion analysis | |
| CN105488522B (en) | Merge the search engine user information requirement satisfaction assessment method of multiple view and semi-supervised learning | |
| CN106708938A (en) | Method and device for assisting recommendation | |
| CN107944911A (en) | A kind of recommendation method of the commending system based on text analyzing | |
| CN110706028A (en) | Commodity evaluation emotion analysis system based on attribute characteristics | |
| CN107818173B (en) | Vector space model-based Chinese false comment filtering method |
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: 20190111 |