CN108694247B - Typhoon disaster analysis method based on microblog topic popularity - Google Patents
Typhoon disaster analysis method based on microblog topic popularity Download PDFInfo
- Publication number
- CN108694247B CN108694247B CN201810466379.3A CN201810466379A CN108694247B CN 108694247 B CN108694247 B CN 108694247B CN 201810466379 A CN201810466379 A CN 201810466379A CN 108694247 B CN108694247 B CN 108694247B
- Authority
- CN
- China
- Prior art keywords
- microblog
- disaster
- data
- typhoon
- popularity
- 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.)
- Active
Links
- 238000004458 analytical method Methods 0.000 title claims abstract description 10
- 238000000034 method Methods 0.000 claims abstract description 17
- 238000004364 calculation method Methods 0.000 claims abstract description 13
- 238000004140 cleaning Methods 0.000 claims description 9
- 238000012216 screening Methods 0.000 claims description 4
- 230000015572 biosynthetic process Effects 0.000 claims description 3
- 238000004445 quantitative analysis Methods 0.000 claims description 3
- 238000012546 transfer Methods 0.000 claims description 3
- 238000011156 evaluation Methods 0.000 abstract description 13
- 238000010200 validation analysis Methods 0.000 abstract description 2
- 238000011160 research Methods 0.000 description 14
- 230000000694 effects Effects 0.000 description 6
- 230000006870 function Effects 0.000 description 4
- 238000009825 accumulation Methods 0.000 description 2
- 230000007423 decrease Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000013210 evaluation model Methods 0.000 description 2
- WURBVZBTWMNKQT-UHFFFAOYSA-N 1-(4-chlorophenoxy)-3,3-dimethyl-1-(1,2,4-triazol-1-yl)butan-2-one Chemical compound C1=NC=NN1C(C(=O)C(C)(C)C)OC1=CC=C(Cl)C=C1 WURBVZBTWMNKQT-UHFFFAOYSA-N 0.000 description 1
- XCTGXGVGJYACEI-BYNFETKLSA-O Delphin Natural products O([C@H]1[C@@H](O)[C@H](O)[C@H](O)[C@H](CO)O1)c1c(-c2cc(O)c(O)c(O)c2)[o+]c2c(c(O[C@H]3[C@H](O)[C@@H](O)[C@H](O)[C@@H](CO)O3)cc(O)c2)c1 XCTGXGVGJYACEI-BYNFETKLSA-O 0.000 description 1
- 241000282414 Homo sapiens Species 0.000 description 1
- 241001415846 Procellariidae Species 0.000 description 1
- 238000000540 analysis of variance Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- XCTGXGVGJYACEI-LCENJUANSA-O delphinidin 3-O-beta-D-glucoside-5-O-beta-D-glucoside Chemical compound O[C@@H]1[C@@H](O)[C@H](O)[C@@H](CO)O[C@H]1OC(C(=[O+]C1=CC(O)=C2)C=3C=C(O)C(O)=C(O)C=3)=CC1=C2O[C@H]1[C@H](O)[C@@H](O)[C@H](O)[C@@H](CO)O1 XCTGXGVGJYACEI-LCENJUANSA-O 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- FGIUAXJPYTZDNR-UHFFFAOYSA-N potassium nitrate Chemical compound [K+].[O-][N+]([O-])=O FGIUAXJPYTZDNR-UHFFFAOYSA-N 0.000 description 1
- 238000007781 pre-processing 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
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- 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
- G06Q50/265—Personal security, identity or safety
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Economics (AREA)
- Tourism & Hospitality (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- Game Theory and Decision Science (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Computer Security & Cryptography (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a typhoon disaster situation analysis method based on microblog topic popularity, which explores the quantitative relation between the microblog topic popularity and typhoon disaster grade, thereby providing a more efficient new method for rapid evaluation of disaster situations. On a provincial scale, a calculation formula of the hot degree of the microblog topic is provided based on microblog feature data such as the total microblog release number, the total microblog active users and the like and a social factor of population; and then, analyzing the quantitative relation of the calculation result based on the relevance between the microblog topic popularity and the disaster. By performing curve fitting on the scattered points of the data, the invention finally obtains an H-alpha curve equation with better range significance and goodness of fit, namely: h2.0769 ln (α) + 15.383. The validation result of the 2014-2015 year data on the equation proves the effectiveness of the equation in the rapid disaster evaluation again.
Description
Technical Field
The invention relates to a typhoon disaster situation analysis method, in particular to a typhoon disaster situation analysis method based on the popularity of microblog topics.
Background
Typhoon disasters are one of the disasters which cause the most serious economic loss and pose great threats to human beings all the year round. Over the past 10 years, annual direct economic losses due to typhoon disasters worldwide have been as high as $ 500 billion, with china accounting for about 15% of the total losses. With the increasing population and social wealth, the southeast coastal region of China also faces increasingly serious typhoon threats. In disaster rescue, one of the biggest challenges at present is to obtain real-time disaster information of disaster areas.
The appearance of a series of social media such as twitter, facebook, microblog and the like changes the communication mode of people. The microblog is one of the largest social media platforms in China and can provide public published real-time information for relevant departments. By 2012, the number of active users on the microblog day is as high as 0.462 hundred million, more than 1 hundred million pieces of microblog information are issued, and the number of microblog users is still increasing with the lapse of time. Meanwhile, when the microblog user uses the mobile phone to issue the message, the microblog user can share the position information of the microblog user, and the microblog data with the position information can be better used for related work and research of disaster rescue.
Based on the advantages of social media data, more and more disaster research utilizes it to explore disaster levels in disaster areas. The Chinese scholars mainly explore the relationship between the actual disaster situation and the information activity degree related to the microblog disaster. For example, research has been conducted to compare microblog information of topics related to the olympic games and typhoon disasters, and it is found that the microblog message distribution positions of the typhoon disasters are mostly distributed in disaster areas and around the disaster areas, while the microblog message distribution positions of the olympic games are scattered and do not show obvious rules. Foreign scholars mainly use twitter data to carry out more extensive research work. Some scholars explore the effectiveness of twitter in regional disaster perception, and some explore the actual extraction work and monitoring effect of twitter disaster information. Among them, kryvashieye et al found that twitter-related information activity exhibits a strong correlation with tropical cyclone path based on twitter-tropical cyclone related data (kryvashieye, Chen, obradvich, et al. Meanwhile, the research by Yago et al also confirmed that the peak of Twitter-related information activity is occurring at the stage of the onset of typhoon and gradually decreases as the disaster-eliminating activity of typhoon decreases (Mart i n, Li, cutter. However, most of the current research is mainly based on social media and typhoon disaster data, and the qualitative relationship of the social media and typhoon disaster data is explored.
Disclosure of Invention
Aiming at the technical problems in the background art, the typhoon disaster situation analysis method based on the microblog topic popularity provided by the invention comprises the following steps:
(1) acquiring tropical cyclone data, wherein the tropical cyclone data comprises information of cyclone numbers, paths, time and wind strength;
(2) carrying out disaster assessment of typhoon, which comprises
(2-1) establishing a dimensionless transfer function for each single disaster index based on the grade of each single disaster index of typhoons nationwide;
(2-2) calculating the association degree (alpha) of the single disaster index based on a grey association degree theory, and representing the disaster level by the association degree (alpha);
(3) acquiring and cleaning microblog data, which comprises the following steps:
(3-1) acquiring microblog data, wherein the microblog data comprise attribute information such as release content, release positions, user IDs (identity) of release messages, user fan numbers and the like; the microblog data all contain position information;
(3-2) screening out microblog data of the area affected by each typhoon based on the release position information of the microblog data;
(3-3) screening out microblog data of each typhoon in a period from appearance to dissipation based on the release time information of the microblog data;
(3-4) performing data cleaning based on the microblog release content, and cleaning microblog data irrelevant to the typhoon disaster theme in the microblog content;
(4) evaluating the popularity H of the microblog topic, wherein the calculation formula of the popularity H of the microblog topic is as follows:
the method comprises the following steps that U represents the total number of users releasing disaster related information, M represents the total number of microblogs related to disasters, F represents the number of fans of each microblog-releasing user, P represents the population number of a street to which a microblog-releasing position belongs, V represents whether an authenticated user exists or not, and if the authenticated user exists, V is 1.5; if the user is not authenticated, V is 1;
(5) carrying out quantitative analysis on the hot degree H of the microblog topic and the correlation degree (alpha) representing the disaster level, wherein a curve formula fitting the hot degree H and the correlation degree (alpha) is as follows:
H＝2.0769ln(α)+15.383
preferably, the tropical cyclone data obtained in step (1) is tropical cyclone data extracted from CMA tropical cyclone optimal path data set (tcdata.
Preferably, the names of the extracted tropical cyclone data include bebijia, winbia, threo, cimatern, delphin, eucryt, sumai, nitre, phente, petrel.
Preferably, the single disaster index in step (2-1) includes four common disaster indexes of a disaster area of crops, the number of dead people, the number of house collapse and direct economic loss.
Preferably, the microblog data in the step (3-3) are acquired for a period of time from the formation of the typhoon to three days after the cessation of the typhoon.
The invention creatively explores the quantitative relation between the popularity of the microblog topics and the typhoon disaster situation and the like for the first time. Under the Chinese provincial scale, the relationship between the microblog topic popularity and various influence factors is analyzed by utilizing microblog data with position information and county-level population data. And then, based on the data which is the topic popularity calculation result and the relevance and describes the disaster level condition, the quantitative relation between the microblog topic and the disaster level is explored.
Drawings
The principle and specific implementation of the method for analyzing typhoon disaster based on microblog topic popularity of the present invention will be described in detail with reference to the accompanying drawings.
Fig. 1 is a graph of the 10 field tropical cyclone path in 2013.
Figure 2 is a graph of the 9 tropical cyclone path in 2014-2015.
FIG. 3 is 2013 'typhoon disaster' topic microblog release thermodynamic diagram
Fig. 4 is a relationship between the disaster relevance (α) and the street-level population P of the microblog release location.
FIG. 5 is a graph of a result of fitting microblog topic popularity H and relevance (alpha) data.
Detailed Description
1 typhoon disaster data acquisition and pretreatment
1.1 acquisition of typhoon data
According to the invention, 10 times of tropical cyclone data of China which logs in 2013 are extracted from a CMA tropical cyclone optimal path data set (tcdata. typhon. org. cn), and the names of the tropical cyclone data are Bebijia, Wimbia, Suli, Simalan, Feiyan, Youguet, Tanmei, Gantai, Phite and Haiyan (shown in figure 1). The acquired tropical cyclone data mainly includes information such as cyclone number, path, time, wind strength, and the like.
To verify the final result obtained by the present invention, the article re-extracts 9 times tropical cyclone data (as shown in fig. 2) for landing in china in 2014-2015 based on CMA tropical cyclone optimal path data set (tcdata. Among them, "Wilmason" and "McEdm" tropical cyclone, which landed in China in 2014, were not selected as the study subjects because of their influence on provinces and duration overlapping.
1.2 disaster assessment of typhoons
At present, a unified evaluation system is not formed in the typhoon disaster situation level, and evaluation is mostly carried out on the basis of disaster situations of different bearing bodies. The invention aims to evaluate the overall grade condition of the disaster by a comprehensive factor, so a typhoon disaster comprehensive evaluation model (Wangxuirong, WangwandMaqingyun. typhoon disaster comprehensive grade evaluation model and application. weather, 2010,36(1):66-71.) proposed by scholars of Wangxiang and the like is selected, and the typhoon disaster comprehensive grade is evaluated on the basis of four common disaster index data of the disaster area of crops, the number of dead people, the number of house collapse and direct economic loss.
The 4 index basic data used for typhoon disaster evaluation of the invention are from the annual book of the Chinese meteorological disasters, and the annual book specifically introduces the typhoon condition of logging in China all the year round and the disaster-suffered conditions of provincial administrative areas and disaster-bearing bodies influenced by each typhoon.
When a typhoon disaster comprehensive assessment model provided by scholars of Wang Xieleng and the like is applied to disaster grade assessment, the method mainly comprises two steps. First, a dimensionless transfer function is established for 4 individual disaster indicators based on the nationwide level of each individual disaster indicator (see table 1).
TABLE 1 grading of individual disaster indicators in China
Then based on grey correlation degree theory (Yangshigal, natural disaster grade division and disaster comparison model discussion, natural disaster academic newspaper, 1997,36(1): 66-71; Fourier, grey system theory and application thereof. Beijing, science and technology publisher, 1992,191-199.), 4 index correlation degrees are calculated, and the correlation degrees represent the disaster grade. In practical calculation, however, the correlation coefficient lambda is not introduced, and the correlation degree (alpha) is directly solved by adopting the conversion function result of the 4-term index. The relationship between disaster level and degree of association is shown in table 2.
TABLE 2 correspondence between disaster level and degree of association
Table 3 and table 4 show evaluation results of 4 disaster indexes, association degrees, and disaster grades of typhoons studied in 20153 and 2015, wherein the disaster grade results do not include the grade of "disaster damage".
Table 3.2013 single index and grade evaluation result of typhoon disaster
Table 4.2014-2015 typhoon disaster single index and grade evaluation result
2. Preprocessing of microblog data and evaluation of microblog topic popularity
2.1 microblog data acquisition and cleaning
The national microblog data set of 2013-2015 used by the invention is from the extreme sea longitudinal and transverse liability company. In practical use, the research screens and cleans microblog data to a certain degree.
In the research process, the microblog data used by the invention mainly comprises important attribute information such as release content, release positions, user IDs (identity) of release messages, user fan numbers and the like. Because the microblog forwarding content and part of the original content do not carry position information, only original microblog data with the position information are obtained in the research.
Secondly, based on the release position information of the microblog data, the microblog data of the provinces influenced by each typhoon are screened out. Research by related scholars has proved that the liveness of the social media disaster related information and the distance from the social media disaster related information to the typhoon path show a good inverse relationship, namely, the closer the position to the typhoon path in the map, the higher the liveness of the social media disaster related information. The main reason for this is that locations closer to the path of the typhoon are more susceptible to the attack of the typhoon, or closer to the disaster area, and therefore more social media users publish disaster-related messages in these locations. In conclusion, the microblog data of disaster-suffering provinces can be better used for disaster assessment.
Then, based on the release time information of the microblog data, microblog data of each typhoon in the period from the occurrence to the dissipation are screened out in the research. Considering that the related departments can carry out works such as early warning, evacuation and rescue and the like before and after the typhoon comes, the acquisition period of the microblog data is expanded from the formation of the typhoon to three days after the typhoon stops.
And finally, data cleaning based on microblog release content. In order to obtain microblog data of a topic related to a typhoon disaster, microblog data irrelevant to the topic of the typhoon disaster in microblog contents are cleaned in the research. The typhoon disaster topic lexicon (as shown in table 5) used for data cleaning in the invention is collected from linguistic data such as news and comments related to typhoons.
Finally, 35991 pieces of microblog data from 32586 microblog users in 2013 are obtained in the research.
TABLE 5 typhoon-related feature vocabulary
2.2 microblog topic popularity evaluation
The microblog topic popularity (H) provided by the invention is a comprehensive index for describing the liveness of microblog related topics.
The calculation of the index mainly relates to basic data such as the total number of active users, the total number of microblog releases, the number of fan of the users, whether the users are authenticated and the like. In general, the more fans of users who issue microblogs, the more easily the microblogs have a large influence on people. Meanwhile, microblog information issued by the authenticated user is more authoritative and is more easily concerned by people.
Based on the position information of the cleaned microblog data, the invention draws a thermodynamic diagram (as shown in fig. 3) of the microblog disaster related information, and very intuitively displays the information such as typhoon paths, relief conditions, microblog release density and the like. As can be seen from the graph, within the provincial administrative district, the microblog release density does not increase along with the reduction of the distance of the path to the typhoon, but obviously increases in the region with flat ground, large cities and multiple populations. Therefore, the region with high microblog release density can be presumed to suffer more loss when typhoon comes because of more population and social wealth accumulation, so that the influence of a larger range is brought; meanwhile, due to the fact that the economy is relatively developed, the population is concentrated, and a larger number of microblog users can publish disaster-related information. Based on the method, the calculation result of the microblog topic popularity can be well corrected by guessing the population number factor, and a strong correlation exists between the calculation result and the disaster grade.
Based on the above contents, two factors are mainly considered when calculating the popularity of the microblog topic. The method comprises the following steps of firstly, microblog data characteristics such as total number of users, total number of microblog releases and the like; the second is a social factor, i.e., population size. The microblog topic popularity result obtained by using the social factor calculation can better reflect the disaster situation of the disaster area.
Considering various influence factors of the microblog topic popularity, the invention provides a calculation formula of the microblog topic popularity (H):
the method comprises the following steps that U represents the total number of users releasing disaster related information, M represents the total number of microblogs related to disasters, F represents the number of fans of each microblog-releasing user, P represents the population number of a street to which a microblog-releasing position belongs, V represents whether an authenticated user exists or not, and if the authenticated user exists, V is 1.5; if the user is not authenticated, V is 1.
At present, most scholars only consider the characteristics of microblog data such as the total number of users and the total number of microblog releases when researching the relation between disaster and microblog activeness. The invention creatively brings social factors such as population into the consideration range of the formula (1), and develops a new idea for improving the accuracy of rapid evaluation of disaster situations.
3 analysis of relationship between population factor and disaster grade
In order to further verify the correction effect of population factors on the hot degree result of the microblog topic, the relationship between the population factors and the disaster grade is analyzed based on the street-level population data P of the association degree of the typhoon disaster and the microblog release position.
Analysis results fig. 4 visually shows the correlation between the two. In the graph, each circle represents the street-level population number of a microblog release position under the relevance value of a typhoon event; the width of the circle represents the total number of microblogs with the same population at the street level of the release position. On the whole, the population factor and the disaster level have better correlation.
From fig. 4, it can be seen that when the degree of association (α) is less than 0.24, the street-level population number of the microblog release location does not exceed 3 x 105. When the degree of association (α) is greater than 0.24 and less than 0.53, more circles appear at 3 × 105～7*105In the meantime. When the degree of association (α) is greater than 0.53, it appears in the population number 3 x 105～7*105The width of the circle in between appears to increase significantly; at the same time, the population is less than 3 x 105The circles of (a) also increase significantly, as does the width.
The occurrence of this phenomenon is well understood. In large and medium-sized urban areas in the coast of southeast China, along with the gathering of population and the continuous accumulation of social wealth, typhoons suffer great loss when they come, and the disaster situation is more serious. Correspondingly, due to dense population, the microblog users are relatively more, and the microblog release density of related subjects is higher when typhoon comes. Therefore, the population factor can reflect the disaster serious condition of the disaster area and the popularity of the microblog related topics to a certain extent.
Quantitative analysis between 4 microblog topic heat degree and disaster level
According to the method, based on a formula (4-1), the province and comprehensive microblog topic heat (H) influenced by each typhoon event is calculated, and the quantitative relation between H and alpha is analyzed by combining the association degree (alpha) data results of tables 3 and 4. The analysis results are shown in FIG. 5.
It can be found from the H- α data scatter in fig. 5 that there is a strong positive correlation between H and α, that is, as the popularity of the microblog topic increases, the disaster level also increases.
Based on the H-alpha data scatter, a fitted curve of H-alpha can be drawn. In consideration of the fact that the total number of microblog users in a disaster area is constant in real life, the daily microblog release amount of each person is usually less than 20, and therefore the heat degree of the microblog topic cannot be increased without limit. Based on practical considerations, the invention adopts a logarithmic function to fit the data scatter points, and the fitting result is shown in fig. 5.
The fitted curve formula is as follows:
H＝2.0769ln(α)+15.383 (2)
the regression equation is 0.000 in significance (see Table 6), R2Is 0.363 (as in fig. 5), the goodness of fit is higher.
TABLE 6 results of ANOVA
aThe argument being degree of association
Based on the data of the heat degree and the relevance degree of the microblog topics in the years of the formulas (2) and 2014-za 2015, the disaster prediction and the actual value are compared, the ratio of the root mean square error to the real average value is less than 12%, and the effectiveness of the fitting curve formula is proved again.
The research proves that the popularity of the microblog topics rises along with the increase of the grade of the typhoon disaster.
Conclusion
The invention explores the quantitative relation between the popularity of the microblog topics and the typhoon disaster grade, thereby providing a more efficient new method for the rapid evaluation of the disaster. On a provincial scale, a calculation formula of the hot degree of the microblog topic is provided based on microblog feature data such as the total microblog release number, the total microblog active users and the like and a social factor of population; and then, analyzing the quantitative relation of the calculation result based on the relevance between the microblog topic popularity and the disaster. By performing curve fitting on the scattered points of the data, the invention finally obtains an H-alpha curve equation with better range significance and goodness of fit, namely: h2.0769 ln (α) + 15.383. The validation result of the 2014-2015 year data on the equation proves the effectiveness of the equation in the rapid disaster evaluation again.
Claims (7)
1. A typhoon disaster situation analysis method based on microblog topic popularity comprises the following steps:
(1) acquiring tropical cyclone data;
(2) performing a disaster assessment of typhoon, comprising:
(2-1) establishing a dimensionless transfer function for each single disaster index based on the grade of each single disaster index of typhoons nationwide;
(2-2) calculating the association degree alpha of the single disaster index based on a grey association degree theory, and representing the disaster level by the association degree alpha;
(3) acquiring and cleaning microblog data, which comprises the following steps:
(3-1) acquiring microblog data, wherein the microblog data comprise release content, release positions, user IDs (identity) of release messages and user fan number attribute information; the microblog data all contain position information;
(3-2) screening out microblog data of the area affected by each typhoon based on the release position information of the microblog data;
(3-3) screening out microblog data of each typhoon in a period from appearance to dissipation based on the release time information of the microblog data;
(3-4) performing data cleaning based on the microblog release content, and cleaning microblog data irrelevant to the typhoon disaster theme in the microblog content;
(4) evaluating the popularity H of the microblog topic, wherein the calculation formula of the popularity H of the microblog topic is as follows:
the method comprises the following steps that U represents the total number of users releasing disaster related information, M represents the total number of microblogs related to disasters, F represents the number of fans of each microblog-releasing user, P represents the population number of a street to which a microblog-releasing position belongs, V represents whether an authenticated user exists or not, and if the authenticated user exists, V is 1.5; if the user is not authenticated, V is 1;
(5) and carrying out quantitative analysis on the hot degree H of the microblog topic and the correlation degree alpha representing the disaster level, and fitting a curve of the hot degree H and the correlation degree alpha.
2. The method of claim 1, wherein the step (5) of fitting a curve formula of H and the degree of correlation α is as follows:
H＝2.0769ln(α)+15.383。
3. the method of claim 1, wherein the tropical cyclone data obtained in step (1) is tropical cyclone data extracted from a CMA tropical cyclone optimal path data set.
4. The method of claim 1, wherein the tropical cyclone data comprises information of cyclone number, path, time, wind intensity.
5. The method of claim 3, wherein the names of the tropical cyclonic data obtained include Bebijia, Wimbia, Suli, Wemelphalan, Feiyan, Ewing, Tanmei, Ganit, Philide, Haiyan.
6. The method according to claim 1, wherein the single disaster indicator in the step (2-1) comprises four common disaster indicators of crop disaster area, number of dead people, number of house collapse, and direct economic loss.
7. The method according to claim 1, wherein the microblog data in the step (3-3) is acquired for a period of time from the formation of a typhoon to three days after the cessation of the typhoon.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810466379.3A CN108694247B (en) | 2018-05-08 | 2018-05-08 | Typhoon disaster analysis method based on microblog topic popularity |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810466379.3A CN108694247B (en) | 2018-05-08 | 2018-05-08 | Typhoon disaster analysis method based on microblog topic popularity |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108694247A CN108694247A (en) | 2018-10-23 |
| CN108694247B true CN108694247B (en) | 2020-11-20 |
Family
ID=63846349
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810466379.3A Active CN108694247B (en) | 2018-05-08 | 2018-05-08 | Typhoon disaster analysis method based on microblog topic popularity |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108694247B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111239812A (en) * | 2019-05-17 | 2020-06-05 | 北京市地震局 | Social media big data and machine learning-based seismic intensity rapid evaluation method |
| CN113408563B (en) * | 2020-09-01 | 2022-08-16 | 武汉大学 | Enteromorpha disaster spatial distribution estimation method under dynamic space-time correlation of microblog public sentiments |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106874448A (en) * | 2017-02-10 | 2017-06-20 | 中国农业大学 | A kind of method and apparatus that earthquake descriptor is excavated from microblogging |
| CN106897400A (en) * | 2017-02-10 | 2017-06-27 | 中国农业大学 | The method for visualizing and system of earthquake information in a kind of network social intercourse media |
| CN107562814A (en) * | 2017-08-14 | 2018-01-09 | 中国农业大学 | A kind of earthquake emergency and the condition of a disaster acquisition of information sorting technique and system |
| CN107590196A (en) * | 2017-08-15 | 2018-01-16 | 中国农业大学 | Earthquake emergency information screening and evaluating system and system in a kind of social networks |
-
2018
- 2018-05-08 CN CN201810466379.3A patent/CN108694247B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106874448A (en) * | 2017-02-10 | 2017-06-20 | 中国农业大学 | A kind of method and apparatus that earthquake descriptor is excavated from microblogging |
| CN106897400A (en) * | 2017-02-10 | 2017-06-27 | 中国农业大学 | The method for visualizing and system of earthquake information in a kind of network social intercourse media |
| CN107562814A (en) * | 2017-08-14 | 2018-01-09 | 中国农业大学 | A kind of earthquake emergency and the condition of a disaster acquisition of information sorting technique and system |
| CN107590196A (en) * | 2017-08-15 | 2018-01-16 | 中国农业大学 | Earthquake emergency information screening and evaluating system and system in a kind of social networks |
Non-Patent Citations (4)
| Title |
|---|
| Analysis of Retweet on Twitter under the Disaster Situation;Fujio Toriumi et al.;《IEICE》;20120621;第112卷(第94期);第19-24页 * |
| Leveraging Twitter to gauge evacuation compliance:Spatiotemporal analysis of Hurricane Matthew;Martin Li et al.;《PLOS ONE》;20170628;第1-22页 * |
| Rapid assessment of disaster damage using social media activity;Yury Kryvasheyeu et al.;《Science Advances》;20160311;第1-11页 * |
| 台风灾害综合等级评估模型及应用;王秀荣 等;《气象》;20100131;第36卷(第1期);第66-71页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108694247A (en) | 2018-10-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Peper et al. | Equations for predicting diameter, height, crown width, and leaf area of San Joaquin Valley street trees | |
| CN108694247B (en) | Typhoon disaster analysis method based on microblog topic popularity | |
| CN107274324A (en) | A kind of method that accident risk assessment is carried out based on cloud service | |
| Li et al. | Mapping seasonal sentiments of people visiting blue spaces in urban wetlands: A pilot study on inland cities of China | |
| Xia et al. | Priority sites and conservation gaps of wintering waterbirds in the Yangtze River floodplain | |
| Wu et al. | Mining typhoon victim information based on multi-source data fusion using social media data in China: a case study of the 2019 Super Typhoon Lekima | |
| CN106548439A (en) | A kind of system for residential quarters Ecology Environment Evaluation | |
| Rosyadi et al. | Energy operations for resident and its implications for economic growth: Indonesia's new capital city as a case study | |
| Liang et al. | Evolution trend and hot topic measurement of climate migration research under the influence of climate change | |
| Misra et al. | Climate scenarios: a Florida-Centric view | |
| Xie et al. | Generic security concern influencing individual response to natural hazards: evidence from Shanghai, C hina | |
| Li et al. | Validating the usefulness and calibration of a two-dimensional situation model of urgency-adaptability for cities responding to climate change—Taking Shenzhen as case study | |
| Tepley | Age structure, developmental pathways, and fire regime characterization of Douglas-fir/western hemlock forests in the central western Cascades of Oregon | |
| Revich | Climate change alters human health in Russia | |
| Karimi et al. | Investigating determinants of stakeholders’ participation on rangeland projects: The case of Goltape Township, Saqqez County | |
| Marwasta et al. | Spatial distribution of slums and its association with disaster vulnerability in Yogyakarta City | |
| Richiedei et al. | A first reflection on the correlation between urban density and the spread of COVID-19 in Italy | |
| Low et al. | The Gulf region’s commitment to a sustainable lifestyle: A bibliometric study | |
| Wu et al. | Estimation of scrub typhus incidence and spatiotemporal multicomponent characteristics from 2016 to 2023 in Zhejiang Province, China | |
| Low et al. | 2 The Gulf region’s commitment to a sustainable lifestyle | |
| Zhu et al. | Research on the Optimal Forest Management Plan Based on Entropy Weight Method | |
| Jia et al. | Research Review on Evaluation Index for Age-friendly Community-a Case Study of Tianjin City | |
| Ramailis et al. | Gender Mainstreaming in Natural Disaster Management: Study of Planning for Strengthening Women's Capacity Against Disasters in Bantul District | |
| Hongguo et al. | Study on Risk Management of Epidemic Prevention in High Rise Residential Areas of Urban Community from the Perspective of COVlD-19: A Case Study of L Community in Handan City. | |
| CN117151470A (en) | Provincial scale fire risk prediction method based on forest fire prediction expansion |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |