CN113378578A - Food and medicine public opinion analysis method - Google Patents

Food and medicine public opinion analysis method Download PDF

Info

Publication number
CN113378578A
CN113378578A CN202110498441.9A CN202110498441A CN113378578A CN 113378578 A CN113378578 A CN 113378578A CN 202110498441 A CN202110498441 A CN 202110498441A CN 113378578 A CN113378578 A CN 113378578A
Authority
CN
China
Prior art keywords
words
food
medicine
sentence
word
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.)
Granted
Application number
CN202110498441.9A
Other languages
Chinese (zh)
Other versions
CN113378578B (en
Inventor
莫军
杨小珊
黄先亮
谭明天
詹洪胜
许晶冰
毛庆
谭敏
高中华
王自强
唐运涛
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Chongqing Aerospace Information Co ltd
Chongqing Institute for Food and Drug Control
Original Assignee
Chongqing Aerospace Information Co ltd
Chongqing Institute for Food and Drug Control
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Chongqing Aerospace Information Co ltd, Chongqing Institute for Food and Drug Control filed Critical Chongqing Aerospace Information Co ltd
Priority to CN202110498441.9A priority Critical patent/CN113378578B/en
Publication of CN113378578A publication Critical patent/CN113378578A/en
Application granted granted Critical
Publication of CN113378578B publication Critical patent/CN113378578B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

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
    • 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
    • G06F16/3331—Query processing
    • G06F16/334—Query execution
    • G06F16/3344—Query execution using natural language analysis
    • 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
    • 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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/044—Recurrent networks, e.g. Hopfield networks

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Databases & Information Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Artificial Intelligence (AREA)
  • General Health & Medical Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Evolutionary Computation (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

The invention provides a method for analyzing food and medicine public sentiment, which comprises the following steps: collecting a web text, and preprocessing the web text; carrying out sentence division processing on the preprocessed web text, and picking out repeated comment sentences in the web text; performing word segmentation on each comment sentence after sentence segmentation processing, and extracting food and medicine characteristic words in the text; calculating the similarity between the characteristic words of the food and the medicine, and if any two similarities are smaller than a set threshold value, rejecting one of the characteristic words; constructing a classification dictionary, and classifying the food and medicine characteristic words in each comment sentence into corresponding dictionary categories; constructing an emotion dictionary, and identifying food and medicine characteristic words, emotion words, degree words and negative words from the comment sentences; determining a basic emotion value of an emotion word, a weight value of a degree word and a weight value of a negative word; the method can accurately process the evaluation published by the user on the network and obtain the accurate emotional tendency value, thereby providing accurate public opinion reference basis for manufacturers of food and medicine and quality supervision departments, and providing accurate data support for the establishment of quality feedback and market supervision measures.

Description

Food and medicine public opinion analysis method
Technical Field
The invention relates to a public opinion analysis method, in particular to a food and medicine public opinion analysis method.
Background
Food and medicine are two main subjects related to livelihood, and the types of food and medicine on the market are not enumerated, however, the evaluation of a user after using a certain brand of food or medicine is related to the implementation of the following behaviors such as quality feedback, market supervision and the like of the food and medicine.
With the development of network technology and computer technology, the evaluation of users on food or medicine is often stated in a network manner such as microblog or bar, and in the prior art, the analysis on web texts related to food and medicine public sentiment is based on sentiment analysis, namely, the web texts are processed and sentiment value calculated, but the existing sentiment analysis method has low accuracy, so that the evaluation tendency of users cannot be accurately grasped.
Therefore, in order to solve the above technical problems, it is necessary to provide a new technical means.
Disclosure of Invention
In view of the above, the present invention provides a public opinion analysis method for food and medicine, which can accurately process the evaluations issued by users on the internet and obtain accurate emotional tendency values, thereby providing accurate public opinion reference bases for food and medicine manufacturers and quality supervision departments, and providing accurate data support for quality feedback and market supervision measures.
The invention provides a food and medicine public opinion analysis method, which comprises the following steps:
s1, collecting a web text, and preprocessing the web text;
s2, carrying out sentence dividing processing on the preprocessed web texts, and rejecting repeated comment sentences in the web texts;
s3, performing word segmentation on each comment sentence after sentence segmentation to extract food and medicine characteristic words in the text; calculating the similarity between the characteristic words of the food and the medicine, and if any two similarities are smaller than a set threshold value, rejecting one of the characteristic words;
s4, constructing a classification dictionary, and classifying the food and medicine feature words in each comment sentence into corresponding dictionary categories;
s5, constructing an emotion dictionary, and identifying food and medicine characteristic words, emotion words, degree words and negative words from the comment sentences;
s6, determining a basic emotion value, a weighted value of the degree word and a weighted value of the negative word of the emotion word;
and S7, constructing a food and medicine emotional tendency value calculation model, and determining the public sentiment tendency of the collected web text according to the emotional tendency value calculation model.
Further, step S1 specifically includes:
s11, ordering the web texts, and eliminating stop words and irrelevant words in the web texts;
s12, carrying out reference resolution on the network text processed in the step S1:
s121, performing word-reference detection on the web text based on the fasttext classification model;
s122, extracting entity words in the network text based on a BilSTM _ CRF deep learning model;
and S123, replacing the reference words of the network text with corresponding entity words.
Further, in step S3, the similarity between the food and medicine feature words is calculated by the following method:
Figure BDA0003055419620000021
wherein beta is a similarity coefficient between the food and medicine characteristic word A and the food and medicine characteristic word B; dis (A, B) is the semantic distance between the food and medicine characteristic words A and B, wherein beta is more than or equal to 1.5.
Further, the public opinion tendency of the web text is determined according to the following method:
and (3) judging the total emotion value S of the web text to be compared with a set emotion value range [ -1,1 ]:
when S is less than-1, the evaluation tendency of the network text to the food and the medicine is negative evaluation;
when S is more than 1, the evaluation tendency of the web text on the food and medicine is positive evaluation;
when S is more than or equal to-1 and less than or equal to 1, the evaluation of the network text on the food and the medicine is neutral evaluation;
and recording the negative evaluation of the web text on the food and the medicine as a negative evaluation set, recording the positive evaluation of the web text as a positive evaluation set, and recording the neutral evaluation of the web text as a neutral evaluation set.
Further, the total emotion value S of the web text is determined by the following method:
s1+ S2+ S3, wherein S1 is the emotional tendency value of the general statement sentence in the network text, S2 is the emotional tendency value of the turning sentence in the network text, and S3 is the emotional tendency value of the conditional sentence.
Further, the emotional tendency value of a general statement sentence is calculated by the following method:
Figure BDA0003055419620000031
wherein, wdegIs the weight of the degree word in the ith statement sentence, Se is the emotion value of the emotion characteristic word in the ith statement sentence, wnegThe average weight of the negative words in the ith statement sentence is Q, the number of the general statement sentences in the network text is Q, and the number of the negative words in the statement sentences is m.
Further, the emotional tendency value of the turning sentence is calculated by the following method:
Figure BDA0003055419620000032
wherein, wneg1Average weight of negation words being positive emotional characteristic words in turning sentences, wneg2Average weight of negative words, w, of negative emotion feature words in turning sentencesdeg1Weight of degree word of positive emotion feature word in turning sentence, wdeg2The weight of the degree word of the negative emotion characteristic word in the turning sentence, r1Weight adjustment coefficient for degree word in turning sentence, t1The weight adjustment coefficient of the negative word in the turning sentence is obtained; se1For the sentiment value of the positive sentiment feature word in the turning sentence, Se2The weight of the negative emotion feature words in the turning sentences and q is the number of the turning sentences.
Further, the emotional tendency value of the progressive sentence is calculated by the following method:
Figure BDA0003055419620000041
wherein Se is the emotion value of the emotion feature words of the progressive sentence, wdegWeight of degree word for progressive sentence, wnegIs the average weight of the negative words in the progressive sentence, m is the number of the negative words, r2For degree words in progressive sentencesWeight adjustment coefficient of (d), t2The coefficients are adjusted for the weights of the negative words in the progressive sentence.
The invention has the beneficial effects that: by the method and the device, the evaluation published by the user on the network can be accurately processed, and the accurate emotional tendency value can be obtained, so that accurate public opinion reference basis can be provided for manufacturers of food and medicine and quality supervision departments, and accurate data support can be provided for the establishment of quality feedback and market supervision measures.
Drawings
The invention is further described below with reference to the following figures and examples:
FIG. 1 is a schematic flow chart of the present invention.
Detailed Description
The invention is described in further detail below with reference to the drawings of the specification:
the invention provides a food and medicine public opinion analysis method, which comprises the following steps:
s1, collecting a web text, and preprocessing the web text;
s2, carrying out sentence dividing processing on the preprocessed web texts, and rejecting repeated comment sentences in the web texts;
s3, performing word segmentation on each comment sentence after sentence segmentation to extract food and medicine characteristic words in the text; calculating the similarity between the characteristic words of the food and the medicine, and if any two similarities are smaller than a set threshold value, rejecting one of the characteristic words;
s4, constructing a classification dictionary, and classifying the food and medicine feature words in each comment sentence into corresponding dictionary categories;
s5, constructing an emotion dictionary, and identifying food and medicine characteristic words, emotion words, degree words and negative words from the comment sentences; for the description of the food and medicine characteristic words, namely the related characteristics of food or medicine, such as package, safety, additive content and the like, the emotional words such as good, bad and good, the degree words including the most, very and especially and the like, and the negatives including not, bad and the like, the words can be realized by establishing a corresponding dictionary through the existing method, and the description is omitted;
s6, determining a basic emotion value, a weighted value of the degree word and a weighted value of the negative word of the emotion word; wherein, the basic emotion value of the emotion word is determined by adopting the existing algorithm, such as TF-IDF algorithm; the degree words and the negative words are respectively established with a degree word weight value comparison table and a negative word weight value comparison table by the existing method, and then the corresponding comparison table is inquired according to the degree words and the negative words to determine;
s7, constructing a food and medicine emotional tendency value calculation model, and determining the public sentiment tendency of the collected web text according to the emotional tendency value calculation model, by the method, the evaluation published on the web by the user can be accurately processed, and the accurate emotional tendency value can be obtained, so that accurate public sentiment reference bases can be provided for food and medicine manufacturers and quality supervision departments, and accurate data support is provided for quality feedback and market supervision measure formulation.
In this embodiment, step S1 specifically includes:
s11, ordering the web texts, and eliminating stop words and irrelevant words in the web texts; in the network comments, the language organization of the user is often not ordered but rather disordered, so the text needs to be ordered, the language expression is rationalized and accurate by adjusting the sequence of words, and some stop words and irrelevant words are included in the text (for example, evaluating the safety of a certain food, and appearing "i buy a lot", which is irrelevant).
S12, carrying out reference resolution on the network text processed in the step S1:
s121, performing word-reference detection on the web text based on the fasttext classification model;
s122, extracting entity words in the network text based on a BilSTM _ CRF deep learning model;
s123, replacing the reference words of the network text with corresponding entity words; by the aid of the method, the emotional characteristic words, the degree words and the negative words related to the emotional characteristic words can be accurately determined, and accordingly accuracy of subsequent processing is guaranteed.
In this embodiment, in step S3, the similarity between the food and medicine feature words is calculated by the following method:
Figure BDA0003055419620000061
wherein beta is a similarity coefficient between the food and medicine characteristic word A and the food and medicine characteristic word B; dis (A, B) is a semantic distance between the food and medicine characteristic word A and the food and medicine characteristic word B, wherein beta is larger than or equal to 1.5 and is not larger than 4, corresponding values are taken according to actual evaluation objects, the semantic distance Dis (A, B) is realized by adopting the existing algorithm, and the method is not repeated.
In this embodiment, the public opinion tendency of the web text is determined according to the following method:
and (3) judging the total emotion value S of the web text to be compared with a set emotion value range [ -1,1 ]:
when S is less than-1, the evaluation tendency of the network text to the food and the medicine is negative evaluation;
when S is more than 1, the evaluation tendency of the web text on the food and medicine is positive evaluation;
when S is more than or equal to-1 and less than or equal to 1, the evaluation of the network text on the food and the medicine is neutral evaluation;
according to the method, negative evaluations of the web texts on food and medicine are recorded as a negative evaluation set, positive evaluations of the web texts are recorded as a positive evaluation set, and neutral evaluations of the web texts are recorded as a neutral evaluation set, and each evaluation set is specific to a corresponding dictionary type, so that accurate data support is provided for subsequent quality feedback and market supervision.
In this embodiment, the total emotion value S of the web text is determined by the following method:
s1+ S2+ S3, wherein S1 is the emotional tendency value of the general statement sentence in the network text, S2 is the emotional tendency value of the turning sentence in the network text, and S3 is the emotional tendency value of the conditional sentence.
Specific addresses: the emotional tendency value of a general statement sentence is calculated by the following method:
Figure BDA0003055419620000062
wherein, wdegIs the weight of the degree word in the ith statement sentence, Se is the emotion value of the emotion characteristic word in the ith statement sentence, wnegThe average weight of the negative words in the ith statement sentence is Q, the number of the general statement sentences in the network text is Q, and the number of the negative words in the statement sentences is m.
The emotional tendency value of the turning sentence is calculated by the following method:
Figure BDA0003055419620000071
wherein, wneg1Average weight of negation words being positive emotional characteristic words in turning sentences, wneg2Average weight of negative words, w, of negative emotion feature words in turning sentencesdeg1Weight of degree word of positive emotion feature word in turning sentence, wdeg2The weight of the degree word of the negative emotion characteristic word in the turning sentence, r1Weight adjustment coefficient for degree word in turning sentence, t1The weight adjustment coefficient of the negative word in the turning sentence is obtained; se1For the sentiment value of the positive sentiment feature word in the turning sentence, Se2The weight of the negative emotion feature words in the turning sentences and q is the number of the turning sentences.
The emotional tendency value of the progressive sentence is calculated by the following method:
Figure BDA0003055419620000072
wherein Se is the emotion value of the emotion feature words of the progressive sentence, wdegWeight of degree word for progressive sentence, wnegIs the average weight of the negative words in the progressive sentence, m is the number of the negative words, r2Adjusting the coefficients for the weights of degree words in progressive sentences, t2In order to adjust the weight of the negative words in the progressive sentence, in the above, the corresponding emotion value is determined by different sentence patterns, which can effectively ensure the accuracy of the final evaluation result.
Finally, the above embodiments are only for illustrating the technical solutions of the present invention and not for limiting, although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions may be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all of them should be covered in the claims of the present invention.

Claims (8)

1. An edible medicine public opinion analysis method is characterized in that: the method comprises the following steps:
s1, collecting a web text, and preprocessing the web text;
s2, carrying out sentence dividing processing on the preprocessed web texts, and rejecting repeated comment sentences in the web texts;
s3, performing word segmentation on each comment sentence after sentence segmentation to extract food and medicine characteristic words in the text; calculating the similarity between the characteristic words of the food and the medicine, and if any two similarities are smaller than a set threshold value, rejecting one of the characteristic words;
s4, constructing a classification dictionary, and classifying the food and medicine feature words in each comment sentence into corresponding dictionary categories;
s5, constructing an emotion dictionary, and identifying food and medicine characteristic words, emotion words, degree words and negative words from the comment sentences;
s6, determining a basic emotion value, a weighted value of the degree word and a weighted value of the negative word of the emotion word;
and S7, constructing a food and medicine emotional tendency value calculation model, and determining the public sentiment tendency of the collected web text according to the emotional tendency value calculation model.
2. The method for analyzing public opinion on food and medicine according to claim 1, characterized in that: in step S1, the method specifically includes:
s11, ordering the web texts, and eliminating stop words and irrelevant words in the web texts;
s12, carrying out reference resolution on the network text processed in the step S1:
s121, performing word-reference detection on the web text based on the fasttext classification model;
s122, extracting entity words in the network text based on a BilSTM _ CRF deep learning model;
and S123, replacing the reference words of the network text with corresponding entity words.
3. The method for analyzing public opinion on food and medicine according to claim 1, characterized in that: in step S3, the similarity between the food and drug feature words is calculated by the following method:
Figure FDA0003055419610000011
wherein beta is a similarity coefficient between the food and medicine characteristic word A and the food and medicine characteristic word B; dis (A, B) is the semantic distance between the food and medicine characteristic words A and B, wherein beta is more than or equal to 1.5.
4. The method for analyzing public opinion on food and medicine according to claim 1, characterized in that: determining the public opinion tendency of the network text according to the following method:
and (3) judging the total emotion value S of the web text to be compared with a set emotion value range [ -1,1 ]:
when S is less than-1, the evaluation tendency of the network text to the food and the medicine is negative evaluation;
when S is more than 1, the evaluation tendency of the web text on the food and medicine is positive evaluation;
when S is more than or equal to-1 and less than or equal to 1, the evaluation of the network text on the food and the medicine is neutral evaluation;
and recording the negative evaluation of the web text on the food and the medicine as a negative evaluation set, recording the positive evaluation of the web text as a positive evaluation set, and recording the neutral evaluation of the web text as a neutral evaluation set.
5. The method for analyzing public opinion on food and medicine according to claim 4, characterized in that: the total emotion value S of the web text is determined by the following method:
s1+ S2+ S3, wherein S1 is the emotional tendency value of the general statement sentence in the network text, S2 is the emotional tendency value of the turning sentence in the network text, and S3 is the emotional tendency value of the conditional sentence.
6. The method for analyzing public opinion on food and medicine according to claim 5, characterized in that: the emotional tendency value of a general statement sentence is calculated by the following method:
Figure FDA0003055419610000021
wherein, wdegIs the weight of the degree word in the ith statement sentence, Se is the emotion value of the emotion characteristic word in the ith statement sentence, wnegThe average weight of the negative words in the ith statement sentence is Q, the number of the general statement sentences in the network text is Q, and the number of the negative words in the statement sentences is m.
7. The method for analyzing public opinion on food and medicine according to claim 5, characterized in that: the emotional tendency value of the turning sentence is calculated by the following method:
Figure FDA0003055419610000031
wherein, wneg1Average weight of negation words being positive emotional characteristic words in turning sentences, wneg2Average weight of negative words, w, of negative emotion feature words in turning sentencesdeg1The right of degree word of positive emotion characteristic word in turning sentenceHeavy, wdeg2The weight of the degree word of the negative emotion characteristic word in the turning sentence, r1Weight adjustment coefficient for degree word in turning sentence, t1The weight adjustment coefficient of the negative word in the turning sentence is obtained; se1For the sentiment value of the positive sentiment feature word in the turning sentence, Se2The weight of the negative emotion feature words in the turning sentences and q is the number of the turning sentences.
8. The method for analyzing public opinion on food and medicine according to claim 5, characterized in that: the emotional tendency value of the progressive sentence is calculated by the following method:
Figure FDA0003055419610000032
wherein Se is the emotion value of the emotion feature words of the progressive sentence, wdegWeight of degree word for progressive sentence, wnegIs the average weight of the negative words in the progressive sentence, m is the number of the negative words, r2Adjusting the coefficients for the weights of degree words in progressive sentences, t2The coefficients are adjusted for the weights of the negative words in the progressive sentence.
CN202110498441.9A 2021-05-08 2021-05-08 Food and medicine public opinion analysis method Active CN113378578B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110498441.9A CN113378578B (en) 2021-05-08 2021-05-08 Food and medicine public opinion analysis method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110498441.9A CN113378578B (en) 2021-05-08 2021-05-08 Food and medicine public opinion analysis method

Publications (2)

Publication Number Publication Date
CN113378578A true CN113378578A (en) 2021-09-10
CN113378578B CN113378578B (en) 2023-04-18

Family

ID=77570836

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110498441.9A Active CN113378578B (en) 2021-05-08 2021-05-08 Food and medicine public opinion analysis method

Country Status (1)

Country Link
CN (1) CN113378578B (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117273617A (en) * 2023-11-17 2023-12-22 北京亿家老小科技有限公司 Big data-based supply chain and purchasing double-chain management platform

Citations (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101894102A (en) * 2010-07-16 2010-11-24 浙江工商大学 Method and device for analyzing emotion tendentiousness of subjective text
CN102663046A (en) * 2012-03-29 2012-09-12 中国科学院自动化研究所 Sentiment analysis method oriented to micro-blog short text
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
CN105005553A (en) * 2015-06-19 2015-10-28 四川大学 Emotional thesaurus based short text emotional tendency analysis method
CN105022805A (en) * 2015-07-02 2015-11-04 四川大学 Emotional analysis method based on SO-PMI (Semantic Orientation-Pointwise Mutual Information) commodity evaluation information
CN105843796A (en) * 2016-03-28 2016-08-10 北京邮电大学 Microblog emotional tendency analysis method and device
CN106250365A (en) * 2016-07-21 2016-12-21 成都德迈安科技有限公司 The extracting method of item property Feature Words in consumer reviews based on text analyzing
US20180005279A1 (en) * 2016-06-30 2018-01-04 International Business Machines Corporation System, method, and recording medium for emotionally intelligent advertising
CN108647257A (en) * 2018-04-24 2018-10-12 北京科技大学 A kind of microblog emotional determines method
CN109190121A (en) * 2018-09-03 2019-01-11 重庆工商大学 Car review sentiment analysis method based on automobile body and part-of-speech rule
CN110362679A (en) * 2019-06-05 2019-10-22 北京大学（天津滨海）新一代信息技术研究院 A kind of financial field comment sensibility classification method and system based on sentiment dictionary
CN110826317A (en) * 2019-11-07 2020-02-21 成都国腾实业集团有限公司 Text emotion analysis method based on dictionary and rule
CN111831824A (en) * 2020-07-16 2020-10-27 民生科技有限责任公司 Public opinion positive and negative face classification method

Patent Citations (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101894102A (en) * 2010-07-16 2010-11-24 浙江工商大学 Method and device for analyzing emotion tendentiousness of subjective text
CN102663046A (en) * 2012-03-29 2012-09-12 中国科学院自动化研究所 Sentiment analysis method oriented to micro-blog short text
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
CN105005553A (en) * 2015-06-19 2015-10-28 四川大学 Emotional thesaurus based short text emotional tendency analysis method
CN105022805A (en) * 2015-07-02 2015-11-04 四川大学 Emotional analysis method based on SO-PMI (Semantic Orientation-Pointwise Mutual Information) commodity evaluation information
CN105843796A (en) * 2016-03-28 2016-08-10 北京邮电大学 Microblog emotional tendency analysis method and device
US20180005279A1 (en) * 2016-06-30 2018-01-04 International Business Machines Corporation System, method, and recording medium for emotionally intelligent advertising
CN106250365A (en) * 2016-07-21 2016-12-21 成都德迈安科技有限公司 The extracting method of item property Feature Words in consumer reviews based on text analyzing
CN108647257A (en) * 2018-04-24 2018-10-12 北京科技大学 A kind of microblog emotional determines method
CN109190121A (en) * 2018-09-03 2019-01-11 重庆工商大学 Car review sentiment analysis method based on automobile body and part-of-speech rule
CN110362679A (en) * 2019-06-05 2019-10-22 北京大学（天津滨海）新一代信息技术研究院 A kind of financial field comment sensibility classification method and system based on sentiment dictionary
CN110826317A (en) * 2019-11-07 2020-02-21 成都国腾实业集团有限公司 Text emotion analysis method based on dictionary and rule
CN111831824A (en) * 2020-07-16 2020-10-27 民生科技有限责任公司 Public opinion positive and negative face classification method

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
KONSTANTY HANIEWICZ 等: "Towards the Lexicon-Based Sentiment Analysis of Polish Texts: Polarity Lexicon" *
侯秀艳: "面向产品评论的跨领域情感倾向性研究" *
兰玉婷: "基于特征本体和情感词典的微博产品评论情感分析", 《中国优秀硕士学位论文全文数据库 信息科技辑》 *

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117273617A (en) * 2023-11-17 2023-12-22 北京亿家老小科技有限公司 Big data-based supply chain and purchasing double-chain management platform
CN117273617B (en) * 2023-11-17 2024-01-19 北京亿家老小科技有限公司 Big data-based supply chain and purchasing double-chain management platform

Also Published As

Publication number Publication date
CN113378578B (en) 2023-04-18

Similar Documents

Publication Publication Date Title
CN105989040B (en) Intelligent question and answer method, device and system
CN108733748B (en) Cross-border product quality risk fuzzy prediction method based on commodity comment public sentiment
CN108388660B (en) Improved E-commerce product pain point analysis method
CN108038240A (en) Based on content, the social networks rumour detection method of user's multiplicity
CN111563384B (en) Evaluation object identification method and device for E-commerce products and storage medium
CN111104526A (en) Financial label extraction method and system based on keyword semantics
CN108596637B (en) Automatic E-commerce service problem discovery system
CN109858029A (en) A kind of data preprocessing method improving corpus total quality
CN108363784A (en) A kind of public sentiment trend estimate method based on text machine learning
CN113378578B (en) Food and medicine public opinion analysis method
US11288701B2 (en) Method and system for determining equity index for a brand
Prakash et al. Data preprocessing in sentiment analysis using Twitter data
CN111026868A (en) Multi-dimensional public opinion crisis prediction method, terminal device and storage medium
WO2021012684A1 (en) Method and system for establishing market sentiment monitoring system
Putra et al. Sentiment analysis on marketplace review using hybrid lexicon and svm method
CN111966944A (en) Model construction method for multi-level user comment security audit
CN112434862A (en) Financial predicament method and device for enterprise on market
Prakhash et al. Categorizing food names in restaurant reviews
EP3961189B1 (en) Cigarette mainstream smoke spectral data sensory evaluation method
Singh et al. Twitter sentiment analysis for stock prediction
CN107885730A (en) Translation knowledge method for distinguishing validity under more interpreter's patterns
CN114742281A (en) Public event network public opinion popularity prediction method based on grey model
TWI712948B (en) Method for document sentimental analysis, apparatus and computer program product thereof
CN113378577B (en) Food safety evaluation text emotional tendency analysis method
CN113378576B (en) Food safety data mining 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
GR01 Patent grant
GR01 Patent grant