CN111598454A - Fresh cold chain logistics online comment sentiment analysis method - Google Patents
Fresh cold chain logistics online comment sentiment analysis method Download PDFInfo
- Publication number
- CN111598454A CN111598454A CN202010415979.4A CN202010415979A CN111598454A CN 111598454 A CN111598454 A CN 111598454A CN 202010415979 A CN202010415979 A CN 202010415979A CN 111598454 A CN111598454 A CN 111598454A
- Authority
- CN
- China
- Prior art keywords
- comment
- fresh
- online
- fresh cold
- cold chain
- 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 48
- 230000008451 emotion Effects 0.000 claims abstract description 52
- 238000011156 evaluation Methods 0.000 claims abstract description 18
- 238000000605 extraction Methods 0.000 claims abstract description 17
- 238000004364 calculation method Methods 0.000 claims abstract description 9
- 238000007781 pre-processing Methods 0.000 claims abstract description 9
- 230000009193 crawling Effects 0.000 claims abstract description 4
- 238000000034 method Methods 0.000 claims description 18
- 230000002996 emotional effect Effects 0.000 claims description 15
- 238000012384 transportation and delivery Methods 0.000 claims description 10
- 238000004806 packaging method and process Methods 0.000 claims description 9
- 238000010801 machine learning Methods 0.000 claims description 5
- 238000012552 review Methods 0.000 claims description 5
- 238000002372 labelling Methods 0.000 claims description 4
- 238000004140 cleaning Methods 0.000 claims description 3
- 238000013135 deep learning Methods 0.000 claims description 3
- 238000003064 k means clustering Methods 0.000 claims description 3
- 230000011218 segmentation Effects 0.000 claims description 3
- 238000012549 training Methods 0.000 claims description 3
- 239000013598 vector Substances 0.000 claims description 3
- 238000011161 development Methods 0.000 abstract description 9
- 238000007726 management method Methods 0.000 abstract description 6
- 238000003058 natural language processing Methods 0.000 abstract description 3
- 230000018109 developmental process Effects 0.000 description 8
- 230000008569 process Effects 0.000 description 5
- 238000011160 research Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 238000013439 planning Methods 0.000 description 2
- 238000004321 preservation Methods 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000001939 inductive effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000007935 neutral effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06395—Quality analysis or management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
- G06F16/355—Class or cluster creation or modification
-
- 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
- G06F16/951—Indexing; Web crawling techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
-
- 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
- G06F40/247—Thesauruses; Synonyms
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
- G06Q10/083—Shipping
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0282—Rating or review of business operators or products
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- General Engineering & Computer Science (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- General Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Artificial Intelligence (AREA)
- Marketing (AREA)
- Databases & Information Systems (AREA)
- Health & Medical Sciences (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Educational Administration (AREA)
- Game Theory and Decision Science (AREA)
- Data Mining & Analysis (AREA)
- Operations Research (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the technical field of natural language processing sentiment analysis and discloses an online fresh cold-chain logistics comment sentiment analysis method which comprises the following steps: crawling online comment information belonging to the logistics category from a fresh shopping platform; carrying out data preprocessing operation on the collected fresh cold-chain logistics online comment information; performing attribute feature extraction by using word2vec aiming at text data, and constructing a viewpoint emotion word bank; constructing a comment viewpoint emotion analysis model, carrying out evaluation dimension weight calculation, and carrying out manual annotation on the contained dimensions and the emotion tendencies of the dimensions; and analyzing the emotion polarity of the evaluation result, and analyzing the language data related to each dimension of the fresh cold chain online comment by using an online comment emotion analysis model. The online fresh cold chain logistics comment sentiment analysis method has the advantages that the logistics service quality system formed by the management of the quality of the fresh cold chain logistics service can be determined in an auxiliary and rapid mode, and therefore the development of the fresh cold chain logistics industry is perfected.
Description
Technical Field
The invention relates to the technical field of natural language processing sentiment analysis, in particular to a method for analyzing sentiment of fresh cold-chain logistics online comments.
Background
At present, the e-commerce industry is rapidly developed, and in order to know the shopping emotion of a consumer and improve the shopping satisfaction of the consumer, the online review of the e-commerce becomes a pre-shopping decision reference for planning shopping consumers. The development of the fresh cold chain logistics can reduce product loss and improve the product preservation rate, so that the research on the fresh cold chain logistics has great significance, and a merchant can improve related services for the demand of consumers in a targeted manner aiming at the online comments of the consumers on the fresh cold chain logistics.
Because a large amount of data can be generated in the online shopping process, effective extraction of the data is extremely important, the currently widely used user comment viewpoint extraction method mainly has the problems that a statistical-based research method generally uses a questionnaire survey mode to collect data, the accuracy of text emotion analysis and the relevance of emotion dictionary scale are high, and therefore the generalization capability of a model is poor and the real-time performance is not high; the method based on the emotion dictionary depends on the emotion dictionary and is limited by the size of the scale of the dictionary; the machine learning-based research method generally uses a form of artificial labeling to construct structured text features, and then uses machine learning classifiers such as naive Bayes, a support vector machine, maximum entropy and the like to perform emotion analysis on a text to be processed, wherein the emotion analysis refers to the process of analyzing, processing, inducing and reasoning the text with subjective emotional colors, belongs to a common method in natural language processing, and mainly has the main function of judging and identifying whether the emotion tendency of the text is positive/negative/neutral from the viewpoint of a user. The problem that how to utilize an emotion analysis method to analyze logistics comment information of cold-chain fresh products in a shopping platform is a problem needing to be researched.
Disclosure of Invention
Technical problem to be solved
Aiming at the defects of the prior art, the invention provides an online comment sentiment analysis method for fresh and fresh cold chain logistics, which has the advantages of assisting and quickly determining the policy target of the quality management of the fresh and fresh cold chain logistics service, forming a logistics service quality system, thereby perfecting the development of the fresh and fresh cold chain logistics industry, solving the problem of quick development of the current electronic commerce industry, and enabling online comment of an e-commerce to become a decision reference before shopping for planning a shopping consumer in order to know the shopping sentiment of the consumer and improve the shopping satisfaction of the consumer. The development of the fresh cold-chain logistics can reduce the product loss and improve the product preservation rate, so that the research on the fresh cold-chain logistics has great significance.
(II) technical scheme
In order to realize the policy goal of assisting and rapidly determining the quality management of the fresh and fresh cold chain logistics service and form a logistics service quality system, thereby perfecting the development of the fresh and fresh cold chain logistics industry, the invention provides the following technical scheme: an online comment sentiment analysis method for fresh and fresh cold chain logistics comprises the following steps:
the method comprises the following steps: crawling online comment information belonging to the logistics category from a fresh shopping platform;
step two: performing data preprocessing operation on the fresh cold-chain logistics online comment information collected in the first step;
step three: performing attribute feature extraction by using word2vec aiming at text data, extracting keywords, and constructing a viewpoint emotion word bank;
step four: constructing a comment viewpoint emotion analysis model, carrying out evaluation dimension weight calculation, and carrying out manual annotation on the contained dimensions and the emotion tendencies of the dimensions;
step five: and analyzing the emotion polarity of the evaluation result, and analyzing the language data related to each dimension of the on-line fresh cold chain comment by using the on-line comment emotion analysis model to obtain the probability of positive tendency of each dimension of the on-line fresh cold chain logistics comment.
Preferably, the logistics online review information of the fresh cold chain in the first step includes: logistics distribution system, dispatching speed, courier service attitude, customer service attitude, packaging integrity and the like.
Preferably, the data preprocessing operation in the second step includes the following steps:
s1, data cleaning: removing missing values and repeated data in the obtained information and helping small online comments;
s2, data labeling and extraction: performing Chinese analysis, part-of-speech tagging and keyword extraction on the fresh cold-chain logistics online comment data;
s3, classifying synonyms: and setting a keyword synonym table by using the Pessen segmentation system, so that the synonym classification is carried out to improve the keyword matching efficiency of the online comment data.
Preferably, the operation of extracting the attribute features by using word2vec in the third step includes the following steps:
a. performing attribute feature extraction by using word2vec for fresh and cold online logistics reviews, performing word frequency statistics on the screened words, and eliminating words with too low occurrence frequency and obviously irrelevant to features;
b. training the fresh and fresh cold chain online logistics comment text by using word2vec, extracting word vectors, and clustering by using a K-MEANS clustering algorithm to determine a K value, so that the fresh and fresh cold chain logistics online comment attribute characteristics are divided into four categories: packaging, delivery system, service attitude, delivery speed.
Preferably, the evaluation dimension weight calculation in the fourth step includes observing the collected fresh cold chain logistics online comment content, and obtaining that the attribute dimensions are different in the attention degree of the user, and the higher the attention degree of the user is, the greater the overall influence on the fresh cold chain logistics online comment is.
Preferably, in the fourth step, the online comments are randomly extracted to manually label the included dimensions and the emotional tendency of the dimensions, and the higher the consistency of the dimension emotion and the overall emotion of the online comments is, that is, the stronger the certainty of the overall emotion is, the higher the weight of the dimension is.
Preferably, the emotion polarity analysis of the evaluation result in the fifth step includes performing emotion analysis on four dimensionality-related corpora including packaging, a delivery system, service attitude and delivery speed of the on-line fresh cold chain logistics comment combined with machine learning and deep learning to obtain scores in each dimensionality, so that the attention situation of the user on logistics when purchasing the fresh cold chain logistics is determined.
(III) advantageous effects
Compared with the prior art, the invention provides an online comment sentiment analysis method for fresh and fresh cold-chain logistics, which has the following beneficial effects:
1. according to the method for analyzing the emotion of the online comment of the fresh cold-chain logistics, online comment information belonging to the logistics category is crawled from a fresh shopping platform; carrying out data preprocessing operation on the collected fresh cold-chain logistics online comment information; performing attribute feature extraction by using word2vec aiming at text data, extracting keywords, and constructing a viewpoint emotion word bank; constructing a comment viewpoint emotion analysis model, carrying out evaluation dimension weight calculation, and carrying out manual annotation on the contained dimensions and the emotion tendencies of the dimensions; analyzing the emotional polarity of the evaluation result, analyzing the language data related to each dimension of the on-line fresh cold chain comments by using an on-line comment emotional analysis model to obtain the positive tendency probability of each dimension of the on-line fresh cold chain logistics comments, by processing the online logistics of the fresh and fresh cold chain and the text information with more complex emotional tendency and adopting a mode of combining various strategies to analyze the emotional tendency of the online comment data of the fresh and fresh cold chain logistics, the feasibility suggestions of consumers on fresh and fresh cold chain logistics can be accurately obtained, the fresh and fresh cold chain logistics service elements are extracted from massive consumer online comments by using the text sentiment analysis method of the fresh and fresh cold chain online logistics comments, the policy objective of fresh and fresh cold chain logistics service quality management can be assisted and quickly determined, a logistics service quality system is formed, and therefore the development of the fresh and fresh cold chain logistics industry is perfected.
Drawings
FIG. 1 is a schematic flow chart of an online comment sentiment analysis method for fresh and fresh cold-chain logistics, which is provided by the invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, an online comment sentiment analysis method for fresh and fresh cold chain logistics includes the following steps:
the method comprises the following steps: crawling online comment information belonging to the logistics category from a fresh shopping platform;
step two: performing data preprocessing operation on the fresh cold-chain logistics online comment information collected in the first step;
step three: performing attribute feature extraction by using word2vec aiming at text data, extracting keywords, and constructing a viewpoint emotion word bank;
step four: constructing a comment viewpoint emotion analysis model, carrying out evaluation dimension weight calculation, and carrying out manual annotation on the contained dimensions and the emotion tendencies of the dimensions;
step five: and analyzing the emotion polarity of the evaluation result, and analyzing the language data related to each dimension of the on-line fresh cold chain comment by using the on-line comment emotion analysis model to obtain the probability of positive tendency of each dimension of the on-line fresh cold chain logistics comment.
Aiming at the fact that the online logistics of the fresh cold chain and text information with complex emotional tendency are processed, the emotional tendency analysis is carried out on the online comment data of the fresh cold chain logistics in a mode of combining various strategies, feasibility suggestions of consumers in the aspect of the fresh cold chain logistics can be accurately obtained, the text emotional analysis method of the fresh cold chain online logistics comment is used for extracting fresh cold chain logistics service elements from massive consumer online comments, the policy objective of the fresh cold chain logistics service quality management can be assisted and rapidly determined, a logistics service quality system is formed, and therefore the development of the fresh cold chain logistics industry is perfected.
The logistics online comment information of the fresh cold chain in the first step comprises: logistics distribution system, dispatching speed, courier service attitude, customer service attitude, packaging integrity and the like.
The data preprocessing operation in the second step comprises the following steps:
s1, data cleaning: removing missing values and repeated data in the obtained information and helping small online comments;
s2, data labeling and extraction: performing Chinese analysis, part-of-speech tagging and keyword extraction on the fresh cold-chain logistics online comment data;
s3, classifying synonyms: and setting a keyword synonym table by using the Pessen segmentation system, so that the synonym classification is carried out to improve the keyword matching efficiency of the online comment data.
In the third step, the operation of extracting the attribute features by using word2vec comprises the following steps:
a. performing attribute feature extraction by using word2vec for fresh and cold online logistics reviews, performing word frequency statistics on the screened words, and eliminating words with too low occurrence frequency and obviously irrelevant to features;
b. training the fresh and fresh cold chain online logistics comment text by using word2vec, extracting word vectors, and clustering by using a K-MEANS clustering algorithm to determine a K value, so that the fresh and fresh cold chain logistics online comment attribute characteristics are divided into four categories: packaging, delivery system, service attitude, delivery speed.
And the evaluation dimension weight calculation in the fourth step comprises the steps of observing the collected fresh cold chain logistics online comment content, obtaining that each attribute dimension is different in the attention degree of the user, wherein the higher the attention degree of the user is, the greater the overall influence on the fresh cold chain logistics online comment is.
In the fourth step, the online comments are randomly extracted to manually label the contained dimensionality and the emotional tendency of the dimensionality, the higher the consistency of the dimensionality emotion and the overall emotion of the online comments is, namely the stronger the decisive effect on the overall emotion is, and the higher the weight of the dimensionality is.
And in the fifth step, emotion polarity analysis is carried out on the evaluation result, wherein emotion analysis is carried out on the four-dimensional related corpora of the packaging, the distribution system, the service attitude and the distribution speed of the on-line fresh cold chain logistics comments by combining machine learning and deep learning, so that the scores in all dimensions are obtained, and therefore the attention condition of the user on the logistics aspect when purchasing the fresh cold chain products is determined.
In conclusion, according to the fresh cold-chain logistics online comment sentiment analysis method, online comment information belonging to logistics categories is crawled from a fresh shopping platform; carrying out data preprocessing operation on the collected fresh cold-chain logistics online comment information; performing attribute feature extraction by using word2vec aiming at text data, extracting keywords, and constructing a viewpoint emotion word bank; constructing a comment viewpoint emotion analysis model, carrying out evaluation dimension weight calculation, and carrying out manual annotation on the contained dimensions and the emotion tendencies of the dimensions; analyzing the emotional polarity of the evaluation result, analyzing the language data related to each dimension of the on-line fresh cold chain comments by using an on-line comment emotional analysis model to obtain the positive tendency probability of each dimension of the on-line fresh cold chain logistics comments, by processing the online logistics of the fresh and fresh cold chain and the text information with more complex emotional tendency and adopting a mode of combining various strategies to analyze the emotional tendency of the online comment data of the fresh and fresh cold chain logistics, the feasibility suggestions of consumers on fresh and fresh cold chain logistics can be accurately obtained, the fresh and fresh cold chain logistics service elements are extracted from massive consumer online comments by using the text sentiment analysis method of the fresh and fresh cold chain online logistics comments, the policy objective of fresh and fresh cold chain logistics service quality management can be assisted and quickly determined, a logistics service quality system is formed, and therefore the development of the fresh and fresh cold chain logistics industry is perfected.
It is to be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (7)
1. A fresh cold chain logistics online comment sentiment analysis method is characterized by comprising the following steps: the method comprises the following steps:
the method comprises the following steps: crawling online comment information belonging to the logistics category from a fresh shopping platform;
step two: performing data preprocessing operation on the fresh cold-chain logistics online comment information collected in the first step;
step three: performing attribute feature extraction by using word2vec aiming at text data, extracting keywords, and constructing a viewpoint emotion word bank;
step four: constructing a comment viewpoint emotion analysis model, carrying out evaluation dimension weight calculation, and carrying out manual annotation on the contained dimensions and the emotion tendencies of the dimensions;
step five: and analyzing the emotion polarity of the evaluation result, and analyzing the language data related to each dimension of the on-line fresh cold chain comment by using the on-line comment emotion analysis model to obtain the probability of positive tendency of each dimension of the on-line fresh cold chain logistics comment.
2. The on-line comment sentiment analysis method of the fresh cold chain logistics according to claim 1, characterized in that: the logistics online comment information of the fresh cold chain in the first step comprises: logistics distribution system, dispatching speed, courier service attitude, customer service attitude, packaging integrity and the like.
3. The on-line comment sentiment analysis method of the fresh cold chain logistics according to claim 1, characterized in that: the data preprocessing operation in the second step comprises the following steps:
s1, data cleaning: removing missing values and repeated data in the obtained information and helping small online comments;
s2, data labeling and extraction: performing Chinese analysis, part-of-speech tagging and keyword extraction on the fresh cold-chain logistics online comment data;
s3, classifying synonyms: and setting a keyword synonym table by using the Pessen segmentation system, so that the synonym classification is carried out to improve the keyword matching efficiency of the online comment data.
4. The on-line comment sentiment analysis method of the fresh cold chain logistics according to claim 1, characterized in that: the third step of using word2vec to extract the attribute features comprises the following steps:
a. performing attribute feature extraction by using word2vec for fresh and cold online logistics reviews, performing word frequency statistics on the screened words, and eliminating words with too low occurrence frequency and obviously irrelevant to features;
b. training the fresh and fresh cold chain online logistics comment text by using word2vec, extracting word vectors, and clustering by using a K-MEANS clustering algorithm to determine a K value, so that the fresh and fresh cold chain logistics online comment attribute characteristics are divided into four categories: packaging, delivery system, service attitude, delivery speed.
5. The on-line comment sentiment analysis method of the fresh cold chain logistics according to claim 1, characterized in that: and the evaluation dimension weight calculation in the fourth step comprises the step of observing the collected fresh cold chain logistics online comment content, and obtaining that the degree of attention of each attribute dimension by the user is different, and the higher the degree of attention of the user is, the greater the overall influence on the fresh cold chain logistics online comment is.
6. The on-line comment sentiment analysis method of the fresh cold chain logistics according to claim 1, characterized in that: in the fourth step, the online comments are randomly extracted to manually label the contained dimensionality and the emotional tendency of the dimensionality, the higher the consistency of the dimensionality emotion and the overall emotion of the online comments is, namely the stronger the decisive degree of the overall emotion is, the higher the weight of the dimensionality is.
7. The on-line comment sentiment analysis method of the fresh cold chain logistics according to claim 1, characterized in that: and analyzing the emotion polarity of the evaluation result in the fifth step, wherein the emotion polarity analysis comprises the step of carrying out emotion analysis on four dimensionality-related linguistic data including packaging, a delivery system, service attitude and delivery speed of the on-line comments of the fresh and fresh cold chain logistics combined with machine learning and deep learning to obtain scores in all dimensionalities, so that the attention situation of a user on the logistics aspect when purchasing the fresh and fresh cold chain products is determined.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010415979.4A CN111598454A (en) | 2020-05-16 | 2020-05-16 | Fresh cold chain logistics online comment sentiment analysis method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010415979.4A CN111598454A (en) | 2020-05-16 | 2020-05-16 | Fresh cold chain logistics online comment sentiment analysis method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111598454A true CN111598454A (en) | 2020-08-28 |
Family
ID=72189794
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010415979.4A Pending CN111598454A (en) | 2020-05-16 | 2020-05-16 | Fresh cold chain logistics online comment sentiment analysis method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111598454A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114398911A (en) * | 2022-01-24 | 2022-04-26 | 平安科技（深圳）有限公司 | Emotion analysis method and device, computer equipment and storage medium |
| GB2601046A (en) * | 2020-09-30 | 2022-05-18 | Ibm | Analyzing received data and calculating risk of damage to a package for delivery |
| CN116862293A (en) * | 2023-06-26 | 2023-10-10 | 广州淘通科技股份有限公司 | Method, system, equipment and storage medium for analyzing operation data |
-
2020
- 2020-05-16 CN CN202010415979.4A patent/CN111598454A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB2601046A (en) * | 2020-09-30 | 2022-05-18 | Ibm | Analyzing received data and calculating risk of damage to a package for delivery |
| CN114398911A (en) * | 2022-01-24 | 2022-04-26 | 平安科技（深圳）有限公司 | Emotion analysis method and device, computer equipment and storage medium |
| CN116862293A (en) * | 2023-06-26 | 2023-10-10 | 广州淘通科技股份有限公司 | Method, system, equipment and storage medium for analyzing operation data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107977798B (en) | Risk assessment method for quality of electronic commerce product | |
| CN111598454A (en) | Fresh cold chain logistics online comment sentiment analysis method | |
| CN108388660B (en) | Improved E-commerce product pain point analysis method | |
| CN109492105B (en) | Text emotion classification method based on multi-feature ensemble learning | |
| CN109101553B (en) | Purchasing user evaluation method and system for industry of non-beneficiary party of purchasing party | |
| CN105468649B (en) | Method and device for judging matching of objects to be displayed | |
| CN111966888B (en) | Aspect class-based interpretability recommendation method and system for fusing external data | |
| Radovanović et al. | Review spam detection using machine learning | |
| Rani et al. | Study and comparision of vectorization techniques used in text classification | |
| Zhang | E-commerce comment sentiment classification based on deep learning | |
| CN113392637B (en) | TF-IDF-based subject term extraction method, device, equipment and storage medium | |
| Biswas et al. | Sentiment analysis on user reaction for online food delivery services using bert model | |
| Suryadi | Predicting repurchase intention using textual features of online customer reviews | |
| Tang et al. | A review of research on detection of fake commodity reviews | |
| Naresh et al. | Comparative Study of Machine Learning Algorithms for Fake Review Detection with Emphasis on SVM | |
| Anuradha et al. | Fuzzy based summarization of product reviews for better analysis | |
| Setiawan et al. | Utilizing Random Forest Algorithm for Sentiment Prediction Based on Twitter Data | |
| Abighail et al. | Sentiment Analysis E-commerce Review | |
| Putri et al. | Product review sentiment analysis at online store jiniso official shop using Naive Bayes Classifier (NBC) method | |
| Hantoro et al. | A Implementation of Text Mining In Sentiment Analysis of Shopee Indonesia Using SVM | |
| Kumar | A Machine Learning-based Automated Approach for Mining Customer Opinion | |
| Bodendorf et al. | Mining customer opinions on the internet-a case study in the automotive industry | |
| Ferdous et al. | Assortment of bangladeshi e-commerce site reviews using machine learning approaches | |
| Liu | Method to Facilitate E-Commerce Buying Power by Using Machine Learning Techniques | |
| Erfina et al. | New Approach of Sarcasm Detection in Indonesian Marketplace Product Review |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20200828 |
|
| WD01 | Invention patent application deemed withdrawn after publication |