CN110866126A - College online public opinion risk assessment method - Google Patents
College online public opinion risk assessment method Download PDFInfo
- Publication number
- CN110866126A CN110866126A CN201911157105.7A CN201911157105A CN110866126A CN 110866126 A CN110866126 A CN 110866126A CN 201911157105 A CN201911157105 A CN 201911157105A CN 110866126 A CN110866126 A CN 110866126A
- Authority
- CN
- China
- Prior art keywords
- public opinion
- knowledge
- college
- data
- risk assessment
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- 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
- G06F16/335—Filtering based on additional data, e.g. user or group profiles
-
- 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
- G06F16/338—Presentation of query results
-
- 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
- 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
- G06F16/9535—Search customisation based on user profiles and personalisation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a college online public opinion risk assessment method, which is based on a professional website flow analysis tool to monitor college websites in real time, and is used for collecting public opinion multimedia information and keywords and public opinion data researched in the field of colleges and universities on the basis of a theme network online crawler technology in a targeted manner to construct a college online public opinion risk assessment knowledge map. The knowledge graph is constructed by a bottom-up scheme, and the real data of each knowledge unit is stored in a data layer and then stored in a graph database through a triple; a mode layer is arranged above the data layer, and the management of the knowledge graph is further realized through the approach of an ontology base; and extracting entities from the open link data, selecting the entities with higher confidence degrees, adding the entities into a knowledge base, and then constructing a top-level ontology mode. The invention does not relate to media data in the science and technology industry and does not process microblog texts. The invention obtains entity data through field investigation from college networks and colleges.
Description
Technical Field
The invention relates to a data processing technology, in particular to a college online public opinion risk assessment method.
Background
Almost all teachers and students in colleges have become a part of the internet group. The network bears thought collision, emotion communication, information exchange and pressure release of many people, and the complexity easily causes the college network public opinion to be full of different impacts of the front side and the back side. The positive network public opinion can encourage teachers to uprate, expand the influence of colleges and universities, promote the image of colleges and universities, and the negative labeling propagation easily influences the attitude, viewpoint or behavior of people, incites the negative emotion of people, causes difficulty for public opinion disposal and closing tearing, even generates public opinion crisis, threatens the stable union of society.
In recent years, many scholars in China begin to research the network public opinion index system, and hope to monitor, evaluate or warn the public opinion through the establishment of the system. 2016, Song Yuan super and the like, and a monitoring index system is constructed from 3 dimensions of a public opinion theme, public opinion transmission and a public opinion audience according to a data cube and a snowflake type mode; in 2017, Wang Jing Ru and the like screen indexes by a method of combining correlation analysis and principal component analysis and set index weights of all levels based on a BP neural network to establish a crisis monitoring index system; and according to the ovarian jade ice in 2018, the establishment of an online public opinion evaluation index system is provided by using a hierarchical analysis method.
The invention patent application 201910277297.9 discloses an assessment method and system for enterprise network public opinion potential risk, the method comprises obtaining a positive network public opinion value based on enterprise network positive evaluation, and obtaining a negative network public opinion value based on enterprise network negative evaluation; and predicting the default distance of the network reputation of the enterprise based on the positive network public opinion value and the negative network public opinion value, obtaining the probability of the network reputation of the enterprise based on the default distance of the network reputation, and obtaining the potential risk value of the network reputation of the enterprise according to the probability of the network reputation.
The invention patent application 201711241476.4 discloses a method and a device for online public opinion risk assessment, wherein the method comprises the following steps: acquiring data according to network resources in a network resource library to obtain network public opinion data; extracting element information of the network public opinion data, and performing data analysis on the network public opinion according to the element information to obtain an analysis result; and performing risk assessment on the network public opinion data according to the analysis result and the keywords in the keyword dictionary. Calling a corresponding web crawler according to the attributes of network resources in a network resource library to perform periodic data acquisition, and performing deduplication and normalization processing on the acquired data to obtain network public opinion data.
The invention patent application 201710169810.3 discloses a method and a device for constructing a knowledge graph, which aims at constructing the knowledge graph aiming at media data in the science and technology industry. The media data has a large number of entities and relations, and a knowledge graph is constructed in order to effectively mine the potential value of a technological innovation project, warn the potential investment risk and help each service of the first-level market financial investment industry to improve the efficiency. The method for constructing the knowledge graph is to effectively identify the most valuable node based on the public sentiment judgment node value of the media original data in the science and technology industry. No manual intervention is used.
The invention patent application 201710827984.4 discloses a public opinion knowledge graph construction method based on hot events, which is characterized by processing microblog texts, constructing text clusters, calculating topic categories to which each text cluster belongs, identifying the hot events in each cluster according to the categories, and counting the multidimensional attribute of each hot event: identifying important characters and mechanisms participating in the hot event discussion, and acquiring multi-dimensional attributes of the important characters and the mechanisms; and finally, establishing a multi-dimensional attribute system and a relationship type of the event, the character and the mechanism, and establishing the public opinion knowledge graph by taking the event, the character and the mechanism as entities and the relationship among the event, the character and the mechanism as correlation.
At present, the ecological, media pattern and propagation mode of internet public opinion are deeply changed, the former public opinion risk assessment indexes are not suitable, the existing network public opinion assessment system is not found from the aspects of construction principles, safe network product hardware equipment, software algorithm models and the like, and the network public opinion risk assessment system aiming at colleges and universities is not found.
Disclosure of Invention
The invention aims to provide a college online public opinion risk assessment method.
The technical scheme adopted by the invention is as follows:
a college online public opinion risk assessment method comprises the following steps:
step 1, collecting target public opinion keyword information of college websites by using a topic network online crawler technology, and simultaneously crawling media information to form network public opinion information together;
step 2, converting or extracting non-text information in the network public opinion information into text information;
step 3, extracting knowledge of the collected unstructured and semi-structured data to obtain structured data information required by the knowledge map, and storing the structured data information to a data layer of the knowledge map;
step 4, integrating the structured data with a third-party database, aligning the data obtained by knowledge extraction with entities, and then completing knowledge fusion by using quality evaluation and ontology extraction;
step 5, analyzing the logical relation of the data after the knowledge fusion to form an ontology model of the knowledge graph;
step 6, judging whether the ontology model accords with the actual logic or not; if so, the knowledge graph is constructed; otherwise, returning to the step 4 to perform knowledge fusion again;
step 7, optimizing existing mining results by using a visual tool to generate a data synthesis cube, and creating multi-dimensional views of various documents to reveal various spatial mapping relations, so that an online public opinion monitoring analysis report can be completed on the premise of ensuring reliability and effectiveness;
and 8, sorting the network public sentiments from high to low according to the situation, and pushing the public sentiments in the front row to a decision maker in real time.
Further, media information is crawled with a Python Spider in step 1, and short videos are collected with emphasis.
Further, the specific steps of collecting the target public opinion keyword information of the college website in the step 1 are as follows:
step 1-1, collecting specified target topic keywords by utilizing a topic network online crawler technology and expressing the specified target topic keywords as vectors of the specified target topic keywords;
step 1-2, calculating the correlation degree between the corresponding webpage content and the target topic keyword according to the correlation degree between the content and the topic keyword,
and 1-3, analyzing the relevance evaluation of the webpage in combination with the hyperlink, and selecting and downloading the hyperlink of the corresponding webpage according to the comparison result of the relevance evaluation result and the set threshold value by the downloading program code.
Therefore, compared with the common network online crawler, the technology needs less web pages to be stored, can save a lot of related operating equipment or network storage resources, and can effectively meet the related requirements of a user on the theme of searching for the specified keywords.
Further, in the step 2, the sound and the video are converted into texts, and text labels of the expression packages are obtained and used for constructing the public opinion risk knowledge graph.
Further, in the step 3, the knowledge extraction adopts a hidden Markov model to perform entity extraction, determines the relationship category between entities in the unstructured public opinion text on the basis of entity recognition, and forms structured data for storage and retrieval. The quality of entity extraction determines the depth and the breadth of the online public opinion risk knowledge graph in colleges and universities.
Further, the knowledge extraction in step 3 includes entity extraction, relationship extraction and event extraction.
Furthermore, in the step 3, dimension reduction processing is performed on the web texts with huge data volumes when necessary during knowledge extraction, entries with high weight values are reserved, and oriented emotion sensitive words are eliminated.
Further, the step 3 specifically comprises the following steps:
step 3-1, carrying out normalized preheating processing on the text information, and carrying out structural and semantic retreating on the acquired HTML document through formatting;
and 3-2, performing feature extraction on the formed semi-structural data by using a natural language processing technology to confirm the relationship types among the text entities and form structured data.
Further, the relationship categories in step 3-2 include synonymy, antisense, master slave.
Further, in the step 7, a university online public opinion risk assessment knowledge graph is drawn by using CiteSpace text visualization analysis software or through a percentile DeepFinder system platform.
By adopting the technical scheme, the invention fully utilizes the existing software to automatically acquire network hot news and emergency events for a period of time and form keywords for feedback; and the entity data is obtained through on-site research from the Internet and colleges and universities to realize uniform aggregation, so that a public opinion risk assessment knowledge graph logic architecture is formed. The existing software is used for automatically acquiring network hot news and emergencies for a period of time. The invention collects the public opinion multimedia information and keywords based on the topic network online crawler technology in a targeted manner on the basis of monitoring the college website by a professional website flow analysis tool, and also constructs the college network public opinion risk assessment knowledge map by public opinion data researched in the field by colleges and universities. The knowledge graph is constructed by a bottom-up scheme, and the real data of each knowledge unit is stored in a data layer and then stored in a graph database through a triple; a mode layer is arranged above the data layer, and the management of the knowledge graph is further realized through the approach of an ontology base; and extracting entities from the open link data, selecting the entities with higher confidence degrees, adding the entities into a knowledge base, and then constructing a top-level ontology mode. The invention does not relate to media data in the science and technology industry and does not process microblog texts. The invention obtains entity data through field investigation from college networks and colleges.
Drawings
The invention is described in further detail below with reference to the accompanying drawings and the detailed description;
fig. 1 is a flow chart illustrating a college online public opinion risk assessment method according to the present invention.
Detailed Description
As shown in fig. 1, the invention discloses a college online public opinion risk assessment method, which comprises the following steps:
step 1, collecting target public opinion keyword information of college websites by using a topic network online crawler technology, and simultaneously crawling media information to form network public opinion information together;
specifically, the step 1 of collecting the target public opinion keyword information of the college website specifically comprises the following steps:
step 1-1, collecting specified target topic keywords by utilizing a topic network online crawler technology and expressing the specified target topic keywords as vectors of the specified target topic keywords;
step 1-2, calculating the correlation degree of the corresponding webpage content and the target topic keyword according to the correlation degree of the content and the topic keyword;
and 1-3, analyzing the relevance evaluation of the webpage in combination with the hyperlink, and selecting and downloading the hyperlink of the corresponding webpage according to the comparison result of the relevance evaluation result and the set threshold value by the downloading program code.
Step 2, converting or extracting non-text information in the network public opinion information into text information; specifically, converting voice and video into texts, and acquiring text labels of the expression packets for constructing public opinion risk knowledge maps;
and 3, performing knowledge extraction on the collected unstructured and semi-structured data to obtain structured data information required by the knowledge graph, and storing the structured data information to a data layer of the knowledge graph.
Further, in the step 3, the knowledge extraction adopts a hidden Markov model to perform entity extraction, determines the relationship category between entities in the unstructured public opinion text on the basis of entity recognition, and forms structured data for storage and retrieval.
Further, the knowledge extraction in step 3 includes entity extraction, relationship extraction and event extraction. The quality of entity extraction determines the depth and the breadth of the online public opinion risk knowledge graph in colleges and universities.
Furthermore, in the step 3, dimension reduction processing is performed on the web texts with huge data volumes when necessary during knowledge extraction, entries with high weight values are reserved, and oriented emotion sensitive words are eliminated.
Further, the step 3 specifically comprises the following steps:
step 3-1, carrying out normalized preheating processing on the text information, and carrying out structural and semantic retreating on the acquired HTML document through formatting;
and 3-2, performing feature extraction on the formed semi-structural data by using a natural language processing technology to confirm the relationship types among the text entities and form structured data. The relationship category includes synonymy, antisense, master slave.
Step 4, integrating the structured data with a third-party database, aligning the data obtained by knowledge extraction with entities, and then completing knowledge fusion by using quality evaluation and ontology extraction;
step 5, analyzing the logical relation of the data after the knowledge fusion to form an ontology model of the knowledge graph;
step 6, judging whether the ontology model accords with the actual logic or not; if so, the knowledge graph is constructed; otherwise, returning to the step 4 to perform knowledge fusion again;
step 7, optimizing existing mining results by using a visual tool to generate a data synthesis cube, and creating multi-dimensional views of various documents to reveal various spatial mapping relations, so that an online public opinion monitoring analysis report can be completed on the premise of ensuring reliability and effectiveness; specifically, as a preferred embodiment, a network public opinion risk assessment knowledge graph of colleges and universities is drawn by using CiteSpace text visual analysis software or a percentile DeepFinder system platform in the step 7;
and 8, sorting the network public sentiments from high to low according to the situation, and pushing the public sentiments in the front row to a decision maker in real time.
The following is a detailed description of the specific principles of the present invention:
the school verifies that network products such as a server, a router, a firewall, a personal computer, a mobile phone and the like are information security quality of basic resources directly facing departments and individual users of the colleges and universities through information security evaluation standards, potential risks of the products are found to a certain extent, and equipment with security threats is prevented from being put into use; meanwhile, the network product which accesses the internet through campus network authentication can monitor and track the safety quality of the network product effectively for a long time. The method can quickly locate the risk loophole, timely discover the risk hot topic and provide information support for decision actions of school supervision departments.
The invention utilizes a professional website flow analysis tool to monitor the college website in real time and collect the network public opinion information in a targeted manner. Important attention information such as hot events, hot topics and the like of the online social network platform of colleges and universities is monitored in real time, and instantaneity and comprehensiveness of public opinion early discovery are improved. The invention specifically comprises the following parts:
1. extracting and collecting network public opinion information:
collecting public opinion keyword information by using a topic network online crawler technology, crawling media information by using Python Spider, and collecting short videos in a focused manner;
the method comprises the steps of utilizing a topic network online crawler technology to collect specified target topic keywords, finishing vector representation aiming at the specified target topic keywords (or a keyword list), effectively calculating the correlation degree of corresponding webpage contents and topics according to the correlation degree of the contents and the topic keywords, simultaneously finishing the correlation degree evaluation of the webpage according to a set threshold value and combining hyperlink analysis, and determining which queue hyperlink is selected by downloading program codes according to the evaluation result. In practical application, when the technology is adopted for collection, all webpages do not need to be collected by a program, so that compared with the common online crawler, the technology has the advantages that the number of the webpages needing to be stored is relatively small, a lot of related operating equipment or network storage resources can be saved, and meanwhile, the related requirements of a user on the theme of searching for the specified keywords can be effectively met;
students in colleges and universities are keen to upload short video broadcast hotspot social events at present. A mobile phone with a camera can enable ordinary people to become video publishers and topic promoters, and complete complex news collection tasks of media reporters such as going out of the mirror, interviewing, clipping and publishing. Because the short video is more realistic than characters and pictures, the trust and participation of audiences are enhanced, the short video becomes an important carrier for triggering public opinion attention, and becomes a more convenient content form and a new path for public opinion information propagation in the mobile internet era.
2. Constructing and analyzing an online public opinion risk assessment knowledge graph:
the real data of each knowledge unit of the knowledge map is stored in a data layer and then stored in a map database through a triple; and a mode layer is arranged above the data layer, and the management of the knowledge graph is further realized through an ontology library.
The invention performs analysis mining on collected texts, expression packages, sounds and videos. The voice and the video can be converted into texts, text labels of the expression packages are obtained, a public opinion risk knowledge graph is constructed, and public opinion information mining is carried out.
The invention fully utilizes the existing software to automatically acquire network hot news and emergency events for a period of time and form keywords for feedback. Entity data are obtained through on-site research from the Internet and colleges and universities, uniform aggregation is achieved, and public opinion risk assessment knowledge graph logic architecture is formed.
The method adopts a bottom-up scheme to construct the online public opinion risk assessment knowledge graph of colleges and universities, extracts entities from some open link data, selects the entities with higher confidence degree and adds the entities into a knowledge base, and then constructs a top-level ontology mode.
Specifically, constructing the knowledge graph includes the following aspects.
2-1, knowledge extraction: extracting structured data information required by the knowledge graph from unstructured and semi-structured data, and storing the data information into a data layer of the knowledge graph;
the text information is first normalized and pre-heated, and the acquired HTML document is re-processed structurally and semantically through formatting. And then, performing feature extraction on the formed semi-structural data by methods such as a natural language processing technology and the like, and finding out the synonymous relationship and the like in the semi-structural data. The data volume of the web text is huge, dimension reduction can be carried out when necessary, and only entries with higher weights are reserved. For the emotional sensitive words with obvious tendentiousness, the words should be eliminated;
the knowledge extraction includes entity extraction, relationship extraction and event extraction. The hidden Markov model is adopted for entity extraction, the relationship category between entities in the unstructured public opinion text is determined on the basis of entity recognition, and structured data is formed for storage and retrieval. The quality of entity extraction determines the depth and the breadth of the online public opinion risk knowledge graph in colleges and universities.
2-2, knowledge fusion: performing data integration through a third-party database and structured data, performing entity alignment on the data obtained by knowledge extraction, and then performing quality evaluation and ontology extraction to complete knowledge fusion work;
2-3, knowledge graph construction: analyzing the logical relationship of the data obtained by the knowledge fusion processing to form an ontology model of the knowledge graph, judging the ontology model, using the condition which accords with the actual logic to construct the knowledge graph, otherwise, returning to the knowledge inference to perform the knowledge fusion again;
2-4, analysis stage: by means of CiteSpace text visual analysis software or a percentile DeepFinder system platform, a college online public opinion risk assessment knowledge graph is drawn, the existing mining results are optimized by means of visual work, a data synthesis cube is generated, multi-dimensional views of various documents are created, various spatial mapping relations are comprehensively disclosed, and therefore online public opinion monitoring analysis reports can be completed on the premise that reliability and effectiveness are guaranteed. And carrying out multidimensional statistical analysis on the internet information, and calculating public sentiment indexes such as emotion and hotword of each department organization in colleges and universities so as to provide support for public sentiment research and judgment. By analyzing the opinion, development trend, propagation source, propagation path, distribution of institute systems and institutions in schools and the like of public sentiment events, development process, key nodes and propagation influence of the events can be mastered conveniently, and targeted response measures are made.
The method of the invention is convenient for schools to early warn in time and respond conveniently: the college online public opinion risk assessment method shows real-time change of public opinion situation in the modes of word cloud pictures, maps, thermodynamic diagrams, instrument panels, radar pictures, dynamic curves and the like, and helps a decision maker to quickly grasp the public opinion situation. Furthermore, the method can inform the concerned information to the user in time through desktop reminding, QQ, WeChat, mail or short message and the like, thereby ensuring the effectiveness of the online and offline early warning modes.
The method of the invention can push hot events, key bloggers dynamic and latest sensitive public opinions of all institutions of colleges and universities in real time, and ensure that a decision maker can master the key public opinions in time; the emergency of each department of colleges and universities is broadcasted in real time, and the decision maker can know and quickly make a decision in time through popup early warning, so that public sentiment situation spreading and expansion are prevented. In addition, the method allows quick interaction through authorization so as to facilitate the fact clarification or appeal response of network public opinions.
By adopting the technical scheme, the method and the system make full use of the existing software to automatically acquire network hot news and emergency events for a period of time and form keywords for feedback; and the entity data is obtained through on-site research from the Internet and colleges and universities to realize uniform aggregation, so that a public opinion risk assessment knowledge graph logic architecture is formed. The existing software is used for automatically acquiring network hot news and emergencies for a period of time. The invention collects the public opinion multimedia information and keywords based on the topic network online crawler technology in a targeted manner on the basis of monitoring the college website by a professional website flow analysis tool, and also constructs the college network public opinion risk assessment knowledge map by public opinion data researched in the field by colleges and universities. The knowledge graph is constructed by a bottom-up scheme, and the real data of each knowledge unit is stored in a data layer and then stored in a graph database through a triple; a mode layer is arranged above the data layer, and the management of the knowledge graph is further realized through the approach of an ontology base; and extracting entities from the open link data, selecting the entities with higher confidence degrees, adding the entities into a knowledge base, and then constructing a top-level ontology mode. The invention does not relate to media data in the science and technology industry and does not process microblog texts. The invention obtains entity data through field investigation from college networks and colleges.
Claims (10)
1. A college online public opinion risk assessment method is characterized in that: which comprises the following steps:
step 1, collecting target public opinion keyword information of college websites by using a topic network online crawler technology, and simultaneously crawling media information to form network public opinion information together;
step 2, converting or extracting non-text information in the network public opinion information into text information;
step 3, extracting knowledge of the collected unstructured and semi-structured data to obtain structured data information required by the knowledge map, and storing the structured data information to a data layer of the knowledge map;
step 4, integrating the structured data with a third-party database, aligning the data obtained by knowledge extraction with entities, and then completing knowledge fusion by using quality evaluation and ontology extraction;
step 5, analyzing the logical relationship of the data after the knowledge fusion to form an ontology model of the knowledge map,
step 6, judging whether the ontology model accords with the actual logic or not; if so, the knowledge graph is constructed; otherwise, returning to the step 4 to perform knowledge fusion again;
step 7, optimizing existing mining results by using a visual tool to generate a data synthesis cube, and creating multi-dimensional views of various documents to reveal various spatial mapping relations to form a network public opinion monitoring analysis report;
and 8, pushing the public sentiments in the front of the sequence to the decision maker in real time according to the network public sentiment monitoring analysis report.
2. The college cyber public opinion risk assessment method according to claim 1, wherein: in step 1, media information is crawled by a Python Spider, and short videos are collected in a focused mode.
3. The college cyber public opinion risk assessment method according to claim 1, wherein: the specific steps of collecting the target public opinion keyword information of the college website in the step 1 are as follows:
step 1-1, collecting specified target topic keywords by utilizing a topic network online crawler technology and expressing the specified target topic keywords as vectors of the specified target topic keywords;
step 1-2, calculating the correlation degree between the corresponding webpage content and the target topic keyword according to the correlation degree between the content and the topic keyword,
and 1-3, analyzing the relevance evaluation of the webpage in combination with the hyperlink, and selecting and downloading the hyperlink of the corresponding webpage according to the comparison result of the relevance evaluation result and the set threshold value by the downloading program code.
4. The college cyber public opinion risk assessment method according to claim 1, wherein: and 2, converting the sound and the video into texts, and acquiring text labels of the expression packets to construct a public opinion risk knowledge graph.
5. The college cyber public opinion risk assessment method according to claim 1, wherein: the step 3 specifically comprises the following steps:
step 3-1, carrying out normalized preheating processing on the text information, and carrying out structural and semantic retreating on the acquired HTML document through formatting;
and 3-2, performing feature extraction on the formed semi-structural data by using a natural language processing technology to confirm the relationship types among the text entities and form structured data.
6. The method of claim 5, wherein the method comprises the steps of: the relationship types in the step 3-2 comprise a synonymy relationship, an antisense relationship and a master-slave relationship.
7. The college cyber public opinion risk assessment method according to claim 1, wherein: and the knowledge extraction in the step 3 comprises entity extraction, relation extraction and event extraction.
8. The college cyber public opinion risk assessment method according to claim 1, wherein: and 3, extracting knowledge, namely extracting entities by using a hidden Markov model, determining the relationship types among the entities in the unstructured public sentiment text on the basis of entity identification, and forming structured data for storage and taking.
9. The college cyber public opinion risk assessment method according to claim 1, wherein: and 3, performing dimensionality reduction on the web texts with huge data volumes when the knowledge is extracted in the step 3 if necessary, reserving terms with high weight values and eliminating tendency emotion sensitive words.
10. The college cyber public opinion risk assessment method according to claim 1, wherein: and 7, drawing a network public opinion risk assessment knowledge graph of colleges and universities by using CiteSpace text visual analysis software or a percentile DeepFinder system platform.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911157105.7A CN110866126A (en) | 2019-11-22 | 2019-11-22 | College online public opinion risk assessment method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911157105.7A CN110866126A (en) | 2019-11-22 | 2019-11-22 | College online public opinion risk assessment method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110866126A true CN110866126A (en) | 2020-03-06 |
Family
ID=69655751
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911157105.7A Pending CN110866126A (en) | 2019-11-22 | 2019-11-22 | College online public opinion risk assessment method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110866126A (en) |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111428090A (en) * | 2020-03-10 | 2020-07-17 | 北京明略软件系统有限公司 | Method and device for realizing data processing, computer storage medium and terminal |
| CN111581394A (en) * | 2020-04-30 | 2020-08-25 | 北京印刷学院 | Large-scale knowledge topographic map drawing method |
| CN111581982A (en) * | 2020-05-06 | 2020-08-25 | 首都师范大学 | Ontology-based prediction method for public opinion early warning grade of medical dispute case |
| CN111881302A (en) * | 2020-07-23 | 2020-11-03 | 民生科技有限责任公司 | Bank public opinion analysis method and system based on knowledge graph |
| CN111931027A (en) * | 2020-08-17 | 2020-11-13 | 深圳新闻网传媒股份有限公司 | Intelligent news public opinion early warning system |
| CN111984786A (en) * | 2020-08-17 | 2020-11-24 | 深圳新闻网传媒股份有限公司 | Intelligent whistle blowing early warning method based on news information and server |
| CN112131392A (en) * | 2020-08-01 | 2020-12-25 | 赛飞特工程技术集团有限公司 | Public health epidemic situation early warning method and system based on knowledge graph |
| CN112214663A (en) * | 2020-10-22 | 2021-01-12 | 上海明略人工智能(集团)有限公司 | Method, system, device, storage medium and mobile terminal for obtaining public opinion volume |
| CN112287116A (en) * | 2020-10-29 | 2021-01-29 | 上海朋程勤学文化传播有限公司 | College and university data analysis method based on knowledge graph |
| CN112668384A (en) * | 2020-08-07 | 2021-04-16 | 深圳市唯特视科技有限公司 | Knowledge graph construction method and system, electronic equipment and storage medium |
| CN112685621A (en) * | 2021-01-06 | 2021-04-20 | 深圳市网联安瑞网络科技有限公司 | Network public opinion detection system and method integrating public opinion wind direction tracking and civil opinion prediction |
| CN112732781A (en) * | 2020-12-30 | 2021-04-30 | 深圳市网联安瑞网络科技有限公司 | Network situation dynamic drawing system and method fusing data quality multi-dimensional evaluation |
| CN112883278A (en) * | 2021-03-23 | 2021-06-01 | 西安电子科技大学昆山创新研究院 | Bad public opinion propagation inhibition method based on big data knowledge graph of smart community |
| CN113220973A (en) * | 2021-05-31 | 2021-08-06 | 北京海纳数聚科技有限公司 | Public opinion truth testing method based on knowledge reasoning technology |
| CN113570182A (en) * | 2021-05-06 | 2021-10-29 | 深圳怀新企业投资顾问股份有限公司 | Reputation risk management capability assessment method, reputation risk management capability assessment device, reputation risk management equipment and storage medium |
| CN113779195A (en) * | 2021-08-31 | 2021-12-10 | 西南电子技术研究所（中国电子科技集团公司第十研究所） | Hot event state evaluation method |
| CN114565486A (en) * | 2022-01-12 | 2022-05-31 | 黑龙江科技大学 | Method for constructing course learning system |
| CN115422948A (en) * | 2022-11-04 | 2022-12-02 | 文灵科技(北京)有限公司 | Event level network identification system and method based on semantic analysis |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102509350A (en) * | 2011-09-30 | 2012-06-20 | 北京航空航天大学 | Cube-based sports event information visualization method |
| CN106709052A (en) * | 2017-01-06 | 2017-05-24 | 电子科技大学 | Keyword based topic-focused web crawler design method |
| CN107783973A (en) * | 2016-08-24 | 2018-03-09 | 慧科讯业有限公司 | The methods, devices and systems being monitored based on domain knowledge spectrum data storehouse to the Internet media event |
| CN109241429A (en) * | 2018-09-05 | 2019-01-18 | 食品安全与营养（贵州）信息科技有限公司 | A kind of food safety public sentiment monitoring method and system |
| CN109977278A (en) * | 2019-02-21 | 2019-07-05 | 中国电子科技集团公司第二十八研究所 | Visual presentation system, method, equipment and the storage medium of public sentiment data |
| US20190278796A1 (en) * | 2016-09-22 | 2019-09-12 | Dogma Srl. | Method and system for searching, publishing and managing the lite cycle of multimedia contents related to public events and the user experience |
-
2019
- 2019-11-22 CN CN201911157105.7A patent/CN110866126A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102509350A (en) * | 2011-09-30 | 2012-06-20 | 北京航空航天大学 | Cube-based sports event information visualization method |
| CN107783973A (en) * | 2016-08-24 | 2018-03-09 | 慧科讯业有限公司 | The methods, devices and systems being monitored based on domain knowledge spectrum data storehouse to the Internet media event |
| US20190278796A1 (en) * | 2016-09-22 | 2019-09-12 | Dogma Srl. | Method and system for searching, publishing and managing the lite cycle of multimedia contents related to public events and the user experience |
| CN106709052A (en) * | 2017-01-06 | 2017-05-24 | 电子科技大学 | Keyword based topic-focused web crawler design method |
| CN109241429A (en) * | 2018-09-05 | 2019-01-18 | 食品安全与营养（贵州）信息科技有限公司 | A kind of food safety public sentiment monitoring method and system |
| CN109977278A (en) * | 2019-02-21 | 2019-07-05 | 中国电子科技集团公司第二十八研究所 | Visual presentation system, method, equipment and the storage medium of public sentiment data |
Non-Patent Citations (1)
| Title |
|---|
| 肖维泽: "基于知识图谱的多媒体网络舆情语义识别案例库构建", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (23)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111428090A (en) * | 2020-03-10 | 2020-07-17 | 北京明略软件系统有限公司 | Method and device for realizing data processing, computer storage medium and terminal |
| CN111581394A (en) * | 2020-04-30 | 2020-08-25 | 北京印刷学院 | Large-scale knowledge topographic map drawing method |
| CN111581394B (en) * | 2020-04-30 | 2023-06-23 | 北京印刷学院 | Large-scale knowledge topography drawing method |
| CN111581982A (en) * | 2020-05-06 | 2020-08-25 | 首都师范大学 | Ontology-based prediction method for public opinion early warning grade of medical dispute case |
| CN111581982B (en) * | 2020-05-06 | 2023-02-17 | 首都师范大学 | Ontology-based prediction method for public opinion early warning grade of medical dispute case |
| CN111881302A (en) * | 2020-07-23 | 2020-11-03 | 民生科技有限责任公司 | Bank public opinion analysis method and system based on knowledge graph |
| CN111881302B (en) * | 2020-07-23 | 2023-11-28 | 民生科技有限责任公司 | Knowledge graph-based bank public opinion analysis method and system |
| CN112131392A (en) * | 2020-08-01 | 2020-12-25 | 赛飞特工程技术集团有限公司 | Public health epidemic situation early warning method and system based on knowledge graph |
| CN112668384A (en) * | 2020-08-07 | 2021-04-16 | 深圳市唯特视科技有限公司 | Knowledge graph construction method and system, electronic equipment and storage medium |
| CN111984786A (en) * | 2020-08-17 | 2020-11-24 | 深圳新闻网传媒股份有限公司 | Intelligent whistle blowing early warning method based on news information and server |
| CN111931027A (en) * | 2020-08-17 | 2020-11-13 | 深圳新闻网传媒股份有限公司 | Intelligent news public opinion early warning system |
| CN112214663A (en) * | 2020-10-22 | 2021-01-12 | 上海明略人工智能(集团)有限公司 | Method, system, device, storage medium and mobile terminal for obtaining public opinion volume |
| CN112287116A (en) * | 2020-10-29 | 2021-01-29 | 上海朋程勤学文化传播有限公司 | College and university data analysis method based on knowledge graph |
| CN112732781A (en) * | 2020-12-30 | 2021-04-30 | 深圳市网联安瑞网络科技有限公司 | Network situation dynamic drawing system and method fusing data quality multi-dimensional evaluation |
| CN112685621A (en) * | 2021-01-06 | 2021-04-20 | 深圳市网联安瑞网络科技有限公司 | Network public opinion detection system and method integrating public opinion wind direction tracking and civil opinion prediction |
| CN112883278A (en) * | 2021-03-23 | 2021-06-01 | 西安电子科技大学昆山创新研究院 | Bad public opinion propagation inhibition method based on big data knowledge graph of smart community |
| CN113570182A (en) * | 2021-05-06 | 2021-10-29 | 深圳怀新企业投资顾问股份有限公司 | Reputation risk management capability assessment method, reputation risk management capability assessment device, reputation risk management equipment and storage medium |
| CN113220973A (en) * | 2021-05-31 | 2021-08-06 | 北京海纳数聚科技有限公司 | Public opinion truth testing method based on knowledge reasoning technology |
| CN113220973B (en) * | 2021-05-31 | 2023-10-24 | 北京海纳数聚科技有限公司 | Public opinion verification method based on knowledge reasoning technology |
| CN113779195A (en) * | 2021-08-31 | 2021-12-10 | 西南电子技术研究所（中国电子科技集团公司第十研究所） | Hot event state evaluation method |
| CN113779195B (en) * | 2021-08-31 | 2023-12-22 | 西南电子技术研究所（中国电子科技集团公司第十研究所） | Hot event state evaluation method |
| CN114565486A (en) * | 2022-01-12 | 2022-05-31 | 黑龙江科技大学 | Method for constructing course learning system |
| CN115422948A (en) * | 2022-11-04 | 2022-12-02 | 文灵科技(北京)有限公司 | Event level network identification system and method based on semantic analysis |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110866126A (en) | College online public opinion risk assessment method | |
| Castillo | Big crisis data: social media in disasters and time-critical situations | |
| Younis | Sentiment analysis and text mining for social media microblogs using open source tools: an empirical study | |
| Goswami et al. | A survey of event detection techniques in online social networks | |
| Hu et al. | Text analytics in social media | |
| Carvalho et al. | MISNIS: An intelligent platform for twitter topic mining | |
| Xu et al. | Building the multi-modal storytelling of urban emergency events based on crowdsensing of social media analytics | |
| CN112749341B (en) | Important public opinion recommendation method, readable storage medium and data processing device | |
| Nan et al. | Real-time monitoring of smart campus and construction of Weibo public opinion platform | |
| CN107918644A (en) | News subject under discussion analysis method and implementation system in reputation Governance framework | |
| Hsu et al. | Integrating machine learning and open data into social Chatbot for filtering information rumor | |
| Alves et al. | A spatial and temporal sentiment analysis approach applied to Twitter microtexts | |
| Belcastro et al. | Using social media for sub-event detection during disasters | |
| Ouyang et al. | Sentistory: multi-grained sentiment analysis and event summarization with crowdsourced social media data | |
| Xu et al. | Research on topic recognition of network sensitive information based on SW-LDA model | |
| Sun | Research on the credibility of social media information based on user perception | |
| Ramachandran et al. | Event detection from Twitter–a survey | |
| Horák et al. | Technological approaches to detecting online disinformation and manipulation | |
| Yang et al. | An automatic crisis information recognition model based on BP neural networks | |
| Wang et al. | Topic discovery method based on topic model combined with hierarchical clustering | |
| Chen et al. | A semantic graph-based approach for mining common topics from multiple asynchronous text streams | |
| Xu et al. | Generating risk maps for evolution analysis of societal risk events | |
| Duong et al. | Neurosymbolic AI for mining public opinions about wildfires | |
| Cherichi et al. | Big data analysis for event detection in microblogs | |
| Cherichi et al. | Using big data values to enhance social event detection pattern |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200306 |