CN112016331A - Passenger transport passenger emotion analysis method - Google Patents
Passenger transport passenger emotion analysis method Download PDFInfo
- Publication number
- CN112016331A CN112016331A CN202011187947.XA CN202011187947A CN112016331A CN 112016331 A CN112016331 A CN 112016331A CN 202011187947 A CN202011187947 A CN 202011187947A CN 112016331 A CN112016331 A CN 112016331A
- Authority
- CN
- China
- Prior art keywords
- public
- public opinion
- sentiment
- text
- 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
- 230000008451 emotion Effects 0.000 title claims abstract description 46
- 238000004458 analytical method Methods 0.000 title claims abstract description 41
- 230000002996 emotional effect Effects 0.000 claims abstract description 16
- 238000012544 monitoring process Methods 0.000 claims abstract description 14
- 238000007781 pre-processing Methods 0.000 claims abstract description 5
- 230000011218 segmentation Effects 0.000 claims description 15
- 230000007613 environmental effect Effects 0.000 claims description 3
- 230000007935 neutral effect Effects 0.000 claims description 3
- 238000000034 method Methods 0.000 abstract description 7
- 230000006399 behavior Effects 0.000 abstract 1
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000014509 gene expression Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
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
- G06F16/90—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
- G06F40/211—Syntactic parsing, e.g. based on context-free grammar [CFG] or unification grammars
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
- G06F40/216—Parsing using statistical methods
-
- 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
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- Business, Economics & Management (AREA)
- Artificial Intelligence (AREA)
- Tourism & Hospitality (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Probability & Statistics with Applications (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Document Processing Apparatus (AREA)
- Machine Translation (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a passenger emotion analysis method, which comprises the following steps: capturing public opinion information related to the subway industry from a public opinion information publishing platform according to monitoring keywords, and preprocessing the public opinion information text; selecting an existing emotion dictionary and public opinion data, and constructing a positive and negative emotion word bank and a document corpus which are required by public opinion information text emotion analysis; and performing syntactic analysis and semantic analysis on the preprocessed public opinion information text according to the positive and negative emotion word banks and the document corpus, judging the emotion values of all sentences in the comprehensive public opinion information text, calculating the final emotion value of the text, and analyzing the opinion and emotional tendency of the passenger passengers on the public opinion information. The method can analyze the articles and the user comments of the hot topics in the subway industry by adopting the emotional words, understand the viewpoints and attitudes of netizens on the hot topics, recognize the emotional tendency of the netizens, and better understand the behaviors and viewpoints of the users, thereby providing important basis for the decision of governments, enterprises or other organizations.
Description
Technical Field
The invention relates to the field of passenger transport emotion analysis, in particular to a passenger transport emotion analysis method.
Background
In the current society, with the vigorous development of the internet, the number of netizens is continuously increased, and more people use the internet as a preferred channel for obtaining information. A collection of influential web portals, micro-blogs, micro-letters and blogs are increasingly becoming the most commonly used internet service sites for netizens. However, while the internet is developed vigorously, some problems are generated continuously, and some public opinions influence the image of the subway industry.
Public opinion is short for "public opinion" and refers to the social attitude of the subject's public in generating and holding the orientation of social managers, enterprises, individuals and other organizations as objects and politics, society, morality, etc. around the occurrence, development and change of social events of intermediaries in a certain social space. It is the sum of the expressions of beliefs, attitudes, opinions, emotions, and the like expressed by more people about various phenomena, problems, and the like in the society.
Emotion analysis is a process of processing, analyzing and applying a text with emotion colors, and is a leading research field in natural language processing. The method is a specific application combining a plurality of existing research results, is combined with the microblog serving as a new network social media, and has important practical value. The main purpose of emotion analysis is to identify subjective information from public sentiment information published by various information publishing platforms such as microblogs, WeChats, forums, webpages and the like, and to mine the viewpoints and attitudes of users on comment information such as products, news, hot events and the like.
In the field of subway passenger transport, emotion analysis of passengers is carried out, the dynamics of events can be known in time, wrong and misleading public opinions can be conducted, and correct decisions can be made on the events by knowing the emotion, attitude, opinion and behavior tendency of people of all levels of the society.
Disclosure of Invention
The invention aims to provide a passenger transport passenger emotion analysis method, which adopts emotion word analysis on articles and user comments of hot topics in the subway industry, so that the viewpoint and attitude of netizens on the hot topics are known, the emotional tendency of the netizens is identified, and the behavior and viewpoint of users are better understood, thereby providing important basis for the decision of governments, enterprises or other organizations.
The purpose of the invention is realized by the following technical scheme:
a passenger emotion analysis method comprises the following steps:
s1, capturing public sentiment information related to the subway industry from a public sentiment information publishing platform according to the monitoring keywords, and preprocessing the public sentiment information text;
s2, selecting the existing emotion dictionary and public opinion data, and constructing a positive and negative emotion word bank and a document corpus required by the emotion analysis of public opinion information texts;
s3, carrying out syntactic analysis and semantic analysis on the preprocessed public sentiment information text according to the positive and negative sentiment word banks and the document corpus, judging the sentiment tendency of each sentence in the text, and endowing the sentence with a corresponding sentiment score;
and S4, integrating the emotion values of all sentences in the public opinion information text, calculating the final emotion value of the text, and analyzing the opinion and emotional tendency of the passenger passengers on the public opinion information.
Specifically, the pre-processing of the public opinion information text in the step S1 includes the following sub-steps:
s101, classifying the public opinion information texts according to the text classification parameters;
s102, carrying out word segmentation operation on the classified public opinion information texts by using a Chinese word segmentation technology, and extracting words with word frequency higher than a preset value from various texts as subject words of the texts;
s103, comparing all words generated by word segmentation operation of all public opinion information texts with preset sensitive keywords, regarding the public opinion information matched with the sensitive keywords as sensitive public opinions, and performing early warning.
Specifically, the text classification parameters include passenger flow class, equipment and facilities class, non-civilized riding class, security check class, environmental sanitation class, staff quality class and ticket class.
Specifically, the public opinion information comprises articles and comments issued by the user aiming at hot topics in the subway industry.
Specifically, the emotional tendencies include: positive, negative, neutral and extreme negative purely recited.
Specifically, the step S3 further includes warning the public opinion information as sensitive public opinion when it is determined that a sentence with extremely negative emotional tendency appears in the public opinion information text.
Specifically, the method further comprises the following steps of carrying out sentiment analysis on the sudden public sentiment event:
s501, setting a monitoring time range of the emergent public sentiment events, monitoring the emergent public sentiment events on each public sentiment information publishing platform and capturing texts of the emergent public sentiment events;
s502, performing word segmentation operation on the captured text of the sudden public sentiment event by using a word segmentation technology, extracting words with the word frequency higher than a preset value from the text as subject words of the sudden public sentiment event, and adding the subject words into monitoring keywords;
s503, carrying out syntactic analysis and semantic analysis on the captured sudden public sentiment event text according to the constructed positive and negative sentiment word banks and the document corpus, analyzing the sentiment tendency of the text, giving sentiment scores, and calculating a final sentiment value;
and S504, analyzing the opinions and emotional tendencies of the passenger passengers to the sudden public opinion events by combining the emotional values of all the sudden public opinion event texts.
The invention has the beneficial effects that: according to the scheme, sentiment word analysis is adopted for articles and user comments of the hot topic in the subway industry, the viewpoint and attitude of netizens on the hot topic are known, the sentiment tendency of the netizens is recognized, and the behavior and viewpoint of the user are better understood, so that an important basis is provided for the decision of governments, enterprises or other organizations.
Drawings
FIG. 1 is a flow chart of the method of the present invention.
Detailed Description
In order to more clearly understand the technical features, objects, and effects of the present invention, embodiments of the present invention will now be described with reference to the accompanying drawings.
In this embodiment, as shown in fig. 1, a passenger emotion analysis method includes the following steps:
the method comprises the steps of firstly, capturing public sentiment information related to the subway industry from a public sentiment information publishing platform according to monitoring keywords, classifying the public sentiment information texts according to text classification parameters, then performing word segmentation operation on the classified public sentiment information texts by using a Chinese word segmentation technology, and simultaneously extracting words with the word frequency higher than a preset value from various texts to serve as subject words of the texts. And finally, comparing all the words generated by the word segmentation operation of all the public opinion information texts with preset sensitive keywords, and regarding the public opinion information matched with the sensitive keywords as sensitive public opinions and carrying out early warning. The text classification parameters comprise passenger flow, equipment and facilities, non-civilized riding, security check, environmental sanitation, staff quality and tickets.
And secondly, selecting the existing emotion dictionary and public opinion data, and constructing a positive and negative emotion word bank and a document corpus required by the emotion analysis of the public opinion information text.
And thirdly, performing syntactic analysis and semantic analysis on the preprocessed public sentiment information text according to the positive and negative sentiment word banks and the document corpus, judging the sentiment tendency of each sentence in the text, and endowing the sentences with corresponding sentiment scores. Wherein emotional tendencies include: positive, negative, neutral and extreme negative purely recited. And if the sentences with extremely negative emotional tendency appear in the public opinion information text, the public opinion information is regarded as sensitive public opinion for early warning.
And fourthly, integrating the emotion values of all sentences in the public opinion information text, calculating the final emotion value of the text, and analyzing the opinion and emotional tendency of the passenger passengers on the public opinion information.
In this embodiment, the method further includes performing sentiment analysis on the sudden public sentiment event, and specifically includes the following sub-steps:
firstly, presetting an emergent public opinion event monitoring time range, monitoring each public opinion information publishing platform for the emergent public opinion event in an event monitoring time period, and capturing text related information of the emergent public opinion event when the emergent public opinion event occurs.
Then, the Chinese word segmentation technology is used for carrying out word segmentation on the captured text of the sudden public sentiment event, words with the word frequency higher than a preset value in the text are extracted to serve as subject words of the sudden public sentiment event, and the subject words are added into the monitoring keywords, so that the sudden public sentiment event can be conveniently monitored subsequently.
Secondly, performing syntactic analysis and semantic analysis on the captured sudden public sentiment event text according to the constructed positive and negative sentiment word banks and the document corpus, analyzing the sentiment tendency of the text, giving sentiment scores, and calculating a final sentiment value;
and finally, analyzing the opinions and emotional tendencies of the passenger passengers to the emergent public sentiment events by combining the sentiment values of all the texts of the emergent public sentiment events.
The foregoing shows and describes the general principles and broad features of the present invention and advantages thereof. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, which are described in the specification and illustrated only to illustrate the principle of the present invention, but that various changes and modifications may be made therein without departing from the spirit and scope of the present invention, which fall within the scope of the invention as claimed. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (7)
1. A passenger emotion analysis method is characterized by comprising the following steps:
s1, capturing public sentiment information related to the subway industry from a public sentiment information publishing platform according to the monitoring keywords, and preprocessing the public sentiment information text;
s2, selecting the existing emotion dictionary and public opinion data, and constructing a positive and negative emotion word bank and a document corpus required by the emotion analysis of public opinion information texts;
s3, carrying out syntactic analysis and semantic analysis on the preprocessed public sentiment information text according to the positive and negative sentiment word banks and the document corpus, judging the sentiment tendency of each sentence in the text, and endowing the sentence with a corresponding sentiment score;
and S4, integrating the emotion values of all sentences in the public opinion information text, calculating the final emotion value of the text, and analyzing the opinion and emotional tendency of the passenger passengers on the public opinion information.
2. The passenger emotion analysis method as claimed in claim 1, wherein the pre-processing of the public opinion information text in step S1 includes the following sub-steps:
s101, classifying the public opinion information texts according to the text classification parameters;
s102, carrying out word segmentation operation on the classified public opinion information texts by using a Chinese word segmentation technology, and extracting words with word frequency higher than a preset value from various texts as subject words of the texts;
s103, comparing all words generated by word segmentation operation of all public opinion information texts with preset sensitive keywords, regarding the public opinion information matched with the sensitive keywords as sensitive public opinions, and performing early warning.
3. The passenger emotion analysis method of claim 2, wherein the text classification parameters comprise passenger class, equipment class, non-civilized passenger class, security class, environmental sanitation class, staff quality class and ticket class.
4. The passenger emotion analysis method as defined in claim 1, wherein the public opinion information includes articles and comments issued by users on hot topics in the subway industry.
5. The passenger emotion analysis method of claim 1, wherein the emotion tendencies include: positive, negative, neutral and extreme negative purely recited.
6. The passenger emotion analysis method of claim 4, wherein step S3 further comprises warning that the public opinion information is regarded as sensitive public opinion when it is determined that there is a sentence with an emotion tendency of extreme negative in the text of the public opinion information.
7. The passenger emotion analysis method as claimed in claim 1, further comprising emotion analysis for sudden public sentiment events, specifically comprising the following sub-steps:
s501, setting a monitoring time range of the emergent public sentiment events, monitoring the emergent public sentiment events on each public sentiment information publishing platform and capturing texts of the emergent public sentiment events;
s502, performing word segmentation operation on the captured text of the sudden public sentiment event by using a word segmentation technology, extracting words with the word frequency higher than a preset value from the text as subject words of the sudden public sentiment event, and adding the subject words into monitoring keywords;
s503, carrying out syntactic analysis and semantic analysis on the captured sudden public sentiment event text according to the constructed positive and negative sentiment word banks and the document corpus, analyzing the sentiment tendency of the text, giving sentiment scores, and calculating a final sentiment value;
and S504, analyzing the opinions and emotional tendencies of the passenger passengers to the sudden public opinion events by combining the emotional values of all the sudden public opinion event texts.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011187947.XA CN112016331A (en) | 2020-10-30 | 2020-10-30 | Passenger transport passenger emotion analysis method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011187947.XA CN112016331A (en) | 2020-10-30 | 2020-10-30 | Passenger transport passenger emotion analysis method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112016331A true CN112016331A (en) | 2020-12-01 |
Family
ID=73527750
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011187947.XA Pending CN112016331A (en) | 2020-10-30 | 2020-10-30 | Passenger transport passenger emotion analysis method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112016331A (en) |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106598944A (en) * | 2016-11-25 | 2017-04-26 | 中国民航大学 | Civil aviation security public opinion emotion analysis method |
CN111488432A (en) * | 2020-04-14 | 2020-08-04 | 广东科徕尼智能科技有限公司 | Sentiment analysis method, equipment and storage medium based on user comments |
-
2020
- 2020-10-30 CN CN202011187947.XA patent/CN112016331A/en active Pending
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106598944A (en) * | 2016-11-25 | 2017-04-26 | 中国民航大学 | Civil aviation security public opinion emotion analysis method |
CN111488432A (en) * | 2020-04-14 | 2020-08-04 | 广东科徕尼智能科技有限公司 | Sentiment analysis method, equipment and storage medium based on user comments |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Girgis et al. | Deep learning algorithms for detecting fake news in online text | |
Saeed et al. | An ensemble approach for spam detection in Arabic opinion texts | |
Bouazizi et al. | Sentiment analysis: From binary to multi-class classification: A pattern-based approach for multi-class sentiment analysis in Twitter | |
Khan et al. | TOM: Twitter opinion mining framework using hybrid classification scheme | |
Ghosh et al. | Sentiment identification in code-mixed social media text | |
CN111950273A (en) | Network public opinion emergency automatic identification method based on emotion information extraction analysis | |
Rashid et al. | Feature level opinion mining of educational student feedback data using sequential pattern mining and association rule mining | |
Bsir et al. | Enhancing deep learning gender identification with gated recurrent units architecture in social text | |
Faruque et al. | Ascertaining polarity of public opinions on Bangladesh cricket using machine learning techniques | |
Nisha et al. | A comparative analysis of machine learning approaches in personality prediction using MBTI | |
Dikwatta et al. | Violence detection in social media-review | |
Wongkoblap et al. | Depression detection of twitter posters using deep learning with anaphora resolution: algorithm development and validation | |
Rahman et al. | Sentiment analysis on Twitter data: comparative study on different approaches | |
Sinha et al. | A detailed survey and comparative study of sentiment analysis algorithms | |
Spatiotis et al. | Sentiment analysis for the Greek language | |
Idrus et al. | Sentiment analysis of state officials news on online media based on public opinion using naive bayes classifier algorithm and particle swarm optimization | |
Kancharapu et al. | A comparative study on word embedding techniques for suicide prediction on COVID-19 tweets using deep learning models | |
Billah et al. | Depression detection from Bangla Facebook status using machine learning approach | |
Gidhe et al. | Sarcasm detection of non# tagged statements using MLP-BP | |
Archana et al. | Explicit sarcasm handling in emotion level computation of tweets-A big data approach | |
Bai et al. | An ensemble approach for cyber bullying: Text messages and images | |
CN115292495A (en) | Emotion analysis method and device, electronic equipment and storage medium | |
CN114817533A (en) | Bullet screen emotion analysis method based on time characteristics | |
CN112016331A (en) | Passenger transport passenger emotion analysis method | |
Dey et al. | Sentiment analysis on bengali text using lexicon based approach |
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 |