CN103455705A - Analysis and prediction system for cooperative correlative tracking and global situation of network social events - Google Patents
Analysis and prediction system for cooperative correlative tracking and global situation of network social events Download PDFInfo
- Publication number
- CN103455705A CN103455705A CN2013101971291A CN201310197129A CN103455705A CN 103455705 A CN103455705 A CN 103455705A CN 2013101971291 A CN2013101971291 A CN 2013101971291A CN 201310197129 A CN201310197129 A CN 201310197129A CN 103455705 A CN103455705 A CN 103455705A
- Authority
- CN
- China
- Prior art keywords
- event
- social
- social event
- information
- tracking
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000004458 analytical method Methods 0.000 title claims abstract description 47
- 230000004927 fusion Effects 0.000 claims abstract description 27
- 238000000034 method Methods 0.000 claims description 56
- 230000008569 process Effects 0.000 claims description 28
- 238000011161 development Methods 0.000 claims description 23
- 230000018109 developmental process Effects 0.000 claims description 23
- 230000009193 crawling Effects 0.000 claims description 22
- 230000000007 visual effect Effects 0.000 claims description 17
- 238000005516 engineering process Methods 0.000 claims description 11
- 238000012545 processing Methods 0.000 claims description 9
- 238000012098 association analyses Methods 0.000 claims description 5
- 230000010429 evolutionary process Effects 0.000 claims description 5
- 238000009412 basement excavation Methods 0.000 claims description 4
- 238000005065 mining Methods 0.000 claims description 3
- 238000000605 extraction Methods 0.000 description 5
- 244000097202 Rathbunia alamosensis Species 0.000 description 4
- 235000009776 Rathbunia alamosensis Nutrition 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 230000002123 temporal effect Effects 0.000 description 3
- 230000006399 behavior Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000007418 data mining Methods 0.000 description 2
- 230000007812 deficiency Effects 0.000 description 2
- 239000008267 milk Substances 0.000 description 2
- 210000004080 milk Anatomy 0.000 description 2
- 235000013336 milk Nutrition 0.000 description 2
- 244000025254 Cannabis sativa Species 0.000 description 1
- 235000012766 Cannabis sativa ssp. sativa var. sativa Nutrition 0.000 description 1
- 235000012765 Cannabis sativa ssp. sativa var. spontanea Nutrition 0.000 description 1
- 241001269238 Data Species 0.000 description 1
- 235000010254 Jasminum officinale Nutrition 0.000 description 1
- 240000005385 Jasminum sambac Species 0.000 description 1
- 229920000877 Melamine resin Polymers 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 235000009120 camo Nutrition 0.000 description 1
- 235000005607 chanvre indien Nutrition 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000000295 complement effect Effects 0.000 description 1
- 239000012141 concentrate Substances 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 235000013305 food Nutrition 0.000 description 1
- 238000013277 forecasting method Methods 0.000 description 1
- 239000004615 ingredient Substances 0.000 description 1
- 230000000977 initiatory effect Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 240000004308 marijuana Species 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- JDSHMPZPIAZGSV-UHFFFAOYSA-N melamine Chemical compound NC1=NC(N)=NC(N)=N1 JDSHMPZPIAZGSV-UHFFFAOYSA-N 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 239000000843 powder Substances 0.000 description 1
- 230000003449 preventive effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000011524 similarity measure Methods 0.000 description 1
- 230000007480 spreading Effects 0.000 description 1
- 230000001502 supplementing effect Effects 0.000 description 1
- 230000000699 topical effect Effects 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
Images
Abstract
The invention relates to an analysis and prediction system for cooperative correlative tracking and global situation of network social events. The system comprises an information fusion unit, a tracking unit, and an analysis and prediction unit. The information fusion unit is used for fusing multimodal features of network social event data to obtain fused information of the multimodal data of social events, thus establishing a semantic description model for the multimodal data of cross-social events. The tracking unit is connected with the information fusion unit and is used for acquiring sematic correlative tracking data of the social events on each aspect according to cross-modal property, cross-platform property and trans-time-and-space property of the network social events in face of network contents including rich multimedia information on the basis of the semantic description model for the multimodal data of the cross-social events. The analysis and prediction unit connected with the tracking unit is used for acquiring social-event-based global situation analysis and prediction data on the basis of the semantic correlative tracking data.
Description
Technical field
The invention belongs to association tracking and the electric powder prediction of a networked society event, relate to a kind of collaborative associated tracking and global state potential analysis and prediction framework system about a networked society event.
Background technology
Along with popularizing fast of internet, network has become indispensable instrument in the most people life.Netizen's quantity increases fast, becomes gradually a huge colony, according to China Internet network state of development statistical report, shows, by by the end of December, 2012, Chinese webpage quantity is 1,227 hundred million, than increasing by 41.7% the same period in 2011.Above statistics shows, we have lived in the network data of magnanimity.We not only need these network datas are reasonably stored, and need research how to process the data of magnanimity in network, thus the potentially useful information after obtaining it and being hidden in the mass network data.In the face of the mass text on internet, image, video data, the large-scale data how the social hotspots event produced is effectively organized, obtains, excavates and is monitored and become a urgent application demand.
A hot news event, along with the time development changes, along with the development of event, has new important News Stories to occur, and the story of haveing been friends in the past is withered away.When this media event of user search, an important task is found news topic exactly, finds out the correlativity between each News Stories, and the procedure chart that builds an event development with this, and the development train of thought of this event topic is set up.Therefore, when a focus incident of search, the user wishes that the Search Results of seeing not is a series of news item of only arranging according to text relevant, allow the user go relation between each story of searching event and the progress of event in the rambling news item of a pile, and should be the relation that can event be developed according to the development of event, the development of event, the information such as the evolutionary process of event topic, with clearly a kind of, patterned showing interface is to the user, allow the user can know fast the evolution of whole event, and allow the user understand fast and analyze the theme of this event.How rapidly, provide the user information needed accurately, in right amount, and the association between illustration information to a certain extent, the complete evolution process of a focus incident is presented to the user, for the user provides intelligent information retrieval service, and allow the user understand fast and analyze the theme of this event, become the common problem of being concerned about of academia and industry member.
Have the characteristics such as virtual property, disguise, diversity, perviousness and randomness due to internet, when a focus incident occurs, increasing netizen is ready to express by Internet channel the viewpoint of oneself.Now, Information Communication and suggestion are unprecedentedly fast alternately, and the expression demand of network public opinion is also day by day polynary.If can not effectively guide, negative network public-opinion will form larger threat to social public security.Make a general survey of the national conditions of international big environment and China, network security, social stability and the supervision of focus incident all is faced with to great challenge.The Jasmine revolution of Middle East is in the rapid spread of every country and the propagation interaction of the network information, and a series of focus incidents that affect hundreds of millions online friends such as " Qidong, Jiangsu 728 events " that occur in the recent period of China, " battle of Sino-Japan Diaoyu Island " propagate rapidly and the online friend participates in widely, social event that we face the extremely sternness that analyzes a situation has been described invariably on network.China is in the critical period of all-round construction well-to-do level and harmonious society; need especially politics and the social environment of a safety and stability; therefore government and related management person need badly for public opinion information on network and effectively excavate, analyze and process, and hold the best opportunity of processing critical incident.Yet; only rely on manual type to be difficult to tackle collection and the processing of the network information of magnanimity; need to merge several information; by suitable computer technology; analyze current social hotspots event and accident, to public sentiment negative in network and misleading speech in time, make a response rapidly, excavate the cause of each process of formation event in network; rumour and crisis are strangled in invisible, thereby improve supervision and the processing power to focus incident and accident.
The tracking of existing social event and prediction algorithm have just been used the text message of single platform.Also on text message is understood, clustering technique is the basic fundamental of data mining and pattern-recognition, by text message is carried out to the theme that cluster obtains social event, traditional clustering method is for the burst of social event and the characteristic such as regional, its Topics Crawling degree of accuracy is not high, is difficult to a complete event is carried out to its semantic description.Because except text message, event also has its abundant visual information.Concerning an event, it has different user comments in different websites, yet, may there be closely similar visual information these two websites, such as, image or video, these information are very useful for the bridge that builds an event entries differentiation across time inter-network station.For example, event " US presidential election in 2012 ", each entry of this event is associated greatly about Obama's image.Therefore, adopt multimodal information fusion more can correctly be described social event.And different platforms also can make up mutually and strengthen.For example, most events is to come from official media on Google News, but they also have many user comments on Flickr.Therefore, information can be helped each other on different platforms, and especially the weak tendency of the advantage in a platform in supplementing another platform is more effective.Crucial challenge is how to find effective method to build two semantic gaps between platform.For this situation, if can incorporate visual information, social event is set up to a unified multi-modal information and describe, and on different platform, social event is worked in coordination with to association effectively, thereby realize the event semantics description system of cross-platform multimodal information fusion.The collaborative tracking of social event based on cross-platform multimedia messages and global state potential analysis and Forecasting Methodology can combine multi-platform multi-modal information effectively, thereby improve this deficiency.
The existing tracking for a networked society event and Study on Forecasting Method be also in the starting stage, neither one is complete so far flow process and frame system.The present invention is that the collaborative associated of a social event Network Based followed the tracks of and the frame system of predicting, effectively make up the deficiency of classic method, realized the cross-module state based on the multi-modal information semantic fusion, collaborative associated tracking and global state potential analysis and prediction cross-platform with spanning space-time.
Summary of the invention
(1) technical matters that will solve
The complete frame system that the purpose of this invention is to provide the collaborative tracking prediction of a kind of social event Network Based.For the multi-modal characteristic of a networked society event data, on different modalities, platform and space-time, the focus social event is worked in coordination with to associated tracking effectively; After following the tracks of a plurality of events, we can be the As time goes on visual demonstration of the process of whole event; Result based on following the tracks of, can also obtain the complete description of a social event, association analysis and Topics Crawling model by these information, can excavate theme and the spin of social event, and utilize the method for statistical learning, learn the overall situation of this social event, can realize global state potential analysis and prediction based on social event, propose collaborative associated the tracking and global state potential analysis and prediction framework about a networked society event for this reason.
(2) technical scheme
For achieving the above object, the invention provides collaborative associated the tracking and global state potential analysis and prognoses system about a networked society event, this system comprises:
The information fusion unit, multi-modal characteristic to a networked society event data is merged, use natural language understanding and image and Video processing analytical technology, for the fuse information of the multi-modal data that obtain social event, structure is across the semantic description model of the multi-modal data of social event;
Tracking cell is connected with the information fusion unit, multi-modal data semantic descriptive model based on across social event, in the face of comprising the Web content that enriches multimedia messages, the cross-module state attribute had for a networked society event, cross-platform attribute and attribute spanning space-time, in conjunction with collaborative associated tracking technique, obtain the semantic association tracking data of social event on each attribute;
Analysis is connected with tracking cell with predicting unit, the associated tracking data of semantic-based, obtain the whole procedural information of a social event along with Time evolution, by social event Topics Crawling model, social event model prediction and social event Statistical Prediction Model mining process information, excavate theme and the spin of the social event of procedural information, thereby know the overall situation of this social event, obtain global state potential analysis and predicted data based on social event.
Beneficial effect of the present invention: the present invention has adopted multimodal information fusion and the modeling of social event, used based on cross-platform, the collaborative associated tracking of the social event of cross-module state and these three different attributes spanning space-time, excavate theme and the spin of each social event, and utilize the method for statistical learning, thereby dope the track of its follow-up developments, collaborative associated the tracking and global state potential analysis and prediction framework system about a networked society event finally proposed, comprise collaborative associated the tracking and global state potential analysis and Forecasting Methodology about the social event of multimedia messages.This invention has solved the description of different focus social event complete evolution process on different modalities, platform and space-time on the network and to its tracking and forecasting problem, the associated track algorithm of the many hypothesis of the collaborative probability wherein use proposed can greatly improve system to social event the correct precision of tracking in each time period, thereby provide more accurately the evolution of whole event, the analysis of user friendly understanding and public sentiment and prediction.
The accompanying drawing explanation
Fig. 1 a is the complete frame system of the collaborative associated tracking of network-oriented social event of the present invention and prognoses system with Fig. 1 b;
Fig. 2 is text based Topics Crawling semantic description schematic diagram in the present invention;
Fig. 3 is the Topics Crawling semantic description schematic diagram based on image/video in the present invention;
Fig. 4 is cross-module state semantic association signal picture in the present invention;
Fig. 5 is cross-platform semantic association signal picture in the present invention;
Fig. 6 is semantic association signal picture spanning space-time in the present invention;
Fig. 7 is the multi-modal Topics Crawling signal picture based on social event in the present invention;
Each Fig. 8 Shi Yitiao highway recent years in period road surface jam situation distribution schematic diagram sheet;
Embodiment
For making the purpose, technical solutions and advantages of the present invention clearer, below in conjunction with specific embodiment, and, with reference to accompanying drawing, the present invention is described in more detail.
It as shown in Fig. 1 a and Fig. 1 b, is the complete frame system of the collaborative tracking of network-oriented social event of the present invention and prognoses system, the present invention realizes obtaining each social event complete description from start to end for collaborative tracking and global state potential analysis and the prediction of a networked society event of multimedia messages.Like this can be the As time goes on visual demonstration of whole event process, with a kind of clearly, patterned showing interface is to the user, allow the user can know fast the evolution of whole event, and can excavate the semantic topic of each event, can know the spin of social event, and utilize the method for statistical learning, and learn the overall situation of this social event, can realize global state potential analysis and prediction based on social event.Structure of the present invention is as Fig. 1 a and Fig. 1 b demonstration, and it comprises three these systems of ingredient and comprises: information fusion unit 1 tracking cell 2 and analysis and predicting unit, realize that the technical scheme of described system is as described below:
The multimodal information fusion of 1 social event and modeling
Utilize information fusion unit 1, multi-modal characteristic to a networked society event data is merged, use natural language understanding and image and Video processing analytical technology, for the fuse information of the multi-modal data that obtain social event, structure is across the semantic description model of the multi-modal data of social event;
Wherein, described structure is across the semantic description model of the multi-modal data of social event, for extracting the text of each social event and the feature across media information of vision, and the text of each social event, vision carried out to the semantic hierarchies excavation across media information, thereby realize the semantic description of social event, the semantic knowledge-base of the information fusion of structure based on multi-modal, thus the multi-modal semantic description of each social event obtained.
Wherein, the multi-modal data fusion packets of information of described social event, containing the text analyzing based on natural language understanding and based on image and Video processing, realizes the event semantics description system of multimodal information fusion, realizes that multi-modal semantic information merges.
Wherein, the Topics Crawling semantic description based on text analyzing and image and video, take boosting algorithm to choose effective text subject and image and video theme.
1.1 the text analyzing based on natural language understanding
For text message, consider to use the topic model (LDA of distortion, Latent Dirichlet Allocation) obtain the subject information of its each event, and utilize the contextual information of text, the further description of realization event text, foundation is with entity, event and theme as the semantic description system of core, mainly from the following aspects, is inquired into:
A) Entity recognition is with associated
Name in the extraction text is mentioned, pronoun is mentioned and a name part of speech is mentioned, and couple together censuring mentioning of same entitative concept, the method that also will utilize statistical translation and text retrieval to combine is set up the correspondence of Chinese and English entity, realizes the associated of multilingual information and integrates.
B) event extraction and description
Consider that event type recognition and element extraction are closely-related with the syntax-semantic parsing centered by verb, take full advantage of syntactic-semantic feature and superficial feature, carry out event type recognition and event element extraction.Use the topic model (LDA) be out of shape to realize the description of social event text.
1.2 based on the image/video treatment technology
By image and video, we can very conveniently understand each social event effectively.We,, by considering the structural information of image and video, utilize sparse study and dictionary learning, thereby set up the unified vision semantic description system based on the word bag model.
1.3 the semantic information based on multi-modal merges
The social event content comprises the multi-modal informations such as text, image, video and sound, in text-processing, we consider the description that the topic model (LDA) of use distortion obtains its each event, image/video is processed, consider its space structure relation, utilize sparse study and dictionary learning, build the visual theme model, thereby obtain the visual theme of each event, and according to the semantic description of the further realization event of visual theme.
As shown in text based Topics Crawling semantic description in Fig. 2 the present invention, given all collection of document D, we adopt the topic model (LDA) of distortion to excavate the theme Z of event
1, Z
2z
iz
k, then based on theme Z
1, Z
2z
iz
kset up the word W of the semantic description of document
1, W
2w
jw
n.
As shown in the Topics Crawling semantic description based on image/video in Fig. 3 the present invention, the Topics Crawling semantic description based on image/video set i, the picture of given all events or video set, excavate the picture of each event or the subject categories C of video
1, C
2c
ic
k, based on subject categories C
1, C
2c
ic
kset up each Feature Descriptor W of the semantic association of picture or video
1, W
2w
jw
n.
Topics Crawling semantic description based on text and image and video, take boosting algorithm to choose effective text subject and image and video theme, thereby realize the event semantics description system of multimodal information fusion, realized that the social event of multimodal information fusion is described.
The collaborative associated trace model of 2 social events
Utilize tracking cell 2 to be connected with information fusion unit 1, multi-modal data semantic descriptive model based on across social event, in the face of comprising the Web content that enriches multimedia messages, the cross-module state attribute had for a networked society event, cross-platform attribute and attribute spanning space-time, in conjunction with collaborative associated tracking technique, obtain the semantic association tracking data of social event on each attribute;
Wherein, the semantic association tracking data of described social event on each attribute, for the semantic relevant Web content in internet is gathered together, form a set that can reflect the social event common theme.
Wherein, for the cross-platform attribute of a networked society event, propose collaborative probability and suppose tracking more, realize collaborative associated tracking of semanteme of a plurality of social event data on two platforms, follow the tracks of for the cross-module state that realizes a networked society event and association spanning space-time.
The collaborative associated trace model of social event, gather together semantic relevant Web content in internet, forms a set that can reflect the social event common theme.In the face of comprising the Web content that enriches multimedia messages, there is cross-platform, cross-module state and the attribute such as spanning space-time for a networked society event, in conjunction with technology such as Cooperative Study associations, realize collaborative associated follow the tracks of of social event on each attribute.
2.1 cross-module state semantic association
Semantic association for the cross-module state, its objective is and realize the association of social event between different modalities, as shown in cross-module state semantic association in Fig. 4 the present invention, for America, presidential elections and these two a networked society events of emission Mars Reconnaissance Orbiter, a plurality of images in a plurality of texts in its textview field and vision territory are made to the semantic association of cross-module state, realized occurring in the related text in same period and the semantic association that image carries out the cross-module state.
We intend adopting the characteristics of the multimedia convergence analysis to excavate the potential semantic correlationship of different modalities, mediaspace at characteristic layer, the information of different media is mapped in a more high-dimensional public space, choose suitable estimating at the same space, thereby weigh the similarity of message sample, and use across the implicit semantic association matrix of media characteristic and portray.Build on this basis the Latent Semantic Indexing of modal characteristics, for projecting to an implicit semantic space across media sample, set up across media content the mapping on the different characteristic space with associated.
2.2 cross-platform semantic association
Here cross-platform association means the incidence relation between multi-source platform (as People's Net and Sina's microblogging).The generation of social event and development and each subevent experienced often are present on a plurality of platforms on network simultaneously, for example the information of an event all can have corresponding description on two platforms (People's Net and Sina's microblogging), and complement each other, therefore study cross-platform complex relationship and be necessary, thereby find and the cross-platform semantic relation of mined information sample.The cross-platform attribute of social event is normally come by a certain subevent initiation of social event, then produce a large amount of network speeches on each platform of cyberspace, therefore the key of cross-platform semantic association is to pass through the cooperative compensating association based on each subevent, realizes the information correspondence on different platform.In Fig. 5 the present invention shown in cross-platform semantic association, this is the social event of " Greece's protest " and " controversial issue of Sino-Japan Diaoyu Island ", the evolution process of its each subevent has corresponding description on People's Net and Sina's microblogging, the associated trace model of the many hypothesis of the collaborative probability that utilizes us to propose is set up associated to the data of these two platforms, can carry out these two social events each information constantly on People's Net and these two platforms of Sina's microblogging interrelated and supplementary, thereby more know clearly the specifying information that this event occurs constantly at this, can analyze exactly each subevent, better social event is carried out to monitor and predict.
2.3 semantic association spanning space-time
Geographic position and the temporal difference of referring to spanning space-time here.Because, after a social event occurs, on different spaces, people are different to the view of this event, and can change along with the change of time.So, we need to set up a kind of semantic association spanning space-time, and the different information that an event is presented in different geographical is described out, thereby make the decision maker grasp connecting each other and distinguishing between each region, guiding better the public opinion development of event, is country's service.We are using the word in this event text as sample space, for each message sample, known " m-place of word-time " tlv triple, we are by the similarity measure of model time scale and geographic space, calculate between each sample in Di Li Wei Ge and temporal correlativity, then for certain word in sample space " dictionary ", add up respectively following four frequency values: simultaneously in certain time interval and certain regional frequency occurred, not in certain time interval but in certain regional frequency occurred, in certain time interval but not in certain regional frequency occurred, and these four amounts of frequency that also do not occur in certain area in certain time interval, by to base in spatiotemporal frequency analysis, obtain the temperature coefficient of each word in certain space and time, merge geographic position and temporal correlativity according to this temperature coefficient, and then obtain the association of semanteme spanning space-time.As shown in semantic association spanning space-time in Fig. 6 the present invention, this is the Spatio-temporal Evolution process that event " H7N9 " spreads, it spreads and outburst presents provincialism and timeliness, Shanghai and Anhui are latest finds, then peripheral provinces and cities begin to extend, all space-time expansion among a small circle at the beginning, but, centre has a burst constantly, such as April 3, suddenly H7N9 the infected is also found in Beijing, spreading of H7N9 is also to present space-time characterisation, need to be to a kind of semantic association spanning space-time of this event establishment, an event is described out in the different information that do not presented in the same time in different geographical, thereby make the decision maker grasp connecting each other and distinguishing between each region, better event there are analysis and the judgement of a reason.
Global state potential analysis and the prediction of 3 social events
Utilize to analyze and be connected with tracking cell 2 with predicting unit 3, the associated tracking data of semantic-based, obtain the whole procedural information of a social event along with Time evolution, by social event Topics Crawling model, social event model prediction and social event Statistical Prediction Model mining process information, excavate theme and the spin of the social event of procedural information, thereby know the overall situation of this social event, obtain global state potential analysis and predicted data based on social event.
Wherein, global state potential analysis and the predicted data of described social event, obtain summary detailed information and the event evolving trend of a plurality of events in different time sections, obtain each social event complete description from start to end, and the As time goes on visual demonstration of whole event process, the relation that can event be developed according to the development of event, the development of event, the evolutionary process information of event topic, with a kind of clearly, patterned showing interface is to the user; By the association analysis to these integrated society event informations, excavate theme and the spin of this social event, and utilize the method for statistical learning, thereby dope the track of its follow-up developments, disclose the characteristic of dissemination, know the overall situation of this social event.
Wherein, described global state potential analysis based on social event and predicted data are all information of each event of obtaining according to tracking data, take the method for Topics Crawling model and statistical learning, dope theme and the tendency of each social event, for exactly social event being carried out to global state potential analysis and prediction.
The propagation of a social event is a typical dynamic process, it is a process constantly developed along with spin along with the time, no matter from time dimension or space dimension, any one social event behavior is not simple isolated, complicated relation is arranged between each behavior, and the generation of each social event also has dominant or recessive sign.Social event has the multi-modal informations such as a large amount of texts, image and video on network, information fusion and the modeling of the state of the cross-module to social event of using us to propose, can detailed the showing the evolution process of a social event, association analysis by these information, can excavate theme and the spin of social event, and utilize the method for statistical learning, and knowing the overall situation of this social event, we have creatively proposed the forecast model of three kinds of different society events.
3.1 social event Topics Crawling
Social event has a large amount of texts on network, the multi-modal information such as image and video, cross-platform information fusion and the modeling by the cross-module state to social event, can at length show the evolution process of a social event, then multi-modal information is carried out to the theme modeling, like this can be the As time goes on visual demonstration of whole event process, the relation that can event be developed according to the development of event on the one hand, the development of event, the information such as the evolutionary process of event topic, with clearly a kind of, patterned showing interface is to the user, allow the user can know fast the evolution of whole event, and allow the user understand fast and analyze the theme of this event, can analyze better overall situation and the public feelings information of social event on the other hand, carry out corresponding spin and public sentiment monitoring.
After each social event is followed the tracks of, can carry out corresponding text subject and visual theme and excavate, finally can obtain the subject information of each evolution process of social event, thereby the tracking defence of social event and the monitoring of public sentiment are had to significant help.As Fig. 7 illustrates the multi-modal Topics Crawling based on social event in the present invention, by event (" America, presidential elections in 2012 ") is carried out to the cross-module state, tracking cross-platform and spanning space-time, the event that obtained is evolution process constantly at each, by topic model, text and the image of the whole process of event carried out to Topics Crawling, the event on Fig. 7 of having obtained is text subject and visual theme constantly at each, then, by these each text subject and visual theme constantly, carry out association and statistics, the excavation of realization to event topic, last visual demonstration, facilitate the user to understand and the analysis of public opinion.
3.2 social event statistical forecast
The method that the evolution process of social event proposes by us can at length be depicted, and can obtain the theme distribution situation of this social event, so we just can carry out corresponding analysis and prediction to this social event.We intend all information of each event resulting according to the result of following the tracks of, take the method for statistical learning, dope the tendency of each social event, can carry out analysis monitoring to social event exactly like this, government decision person can take corresponding counter-measure that negative public opinion is contained among rudiment in time.In whole predetermined period, can set up a benchmark by basic data, then As time goes on, more and more abundanter according to the information of the resulting event of result of following the tracks of, thereby make the future trend of event more and more obvious, by the prediction of the method realization event of statistical Data Mining.
3.3 social event model prediction
Many social events are that common spatiotemporal mode is arranged, in a time period of 1 year, all can occur, we can according to social event recent years, a situation arises, identical social event is analyzed meticulously, the modeling method of using us to propose, draw the theme distribution situation of its social event, we just can carry out corresponding analysis and prediction to this social event, thereby after knowing, when section occurs this similar social event maximum possible, can accomplish in advance preventive measure.
Fig. 8 is road surface jam situation distribution plan in each a certain highway recent years in period, the highway jam situation was to present different situations along with asynchronism(-nization) in 1 year, but, this social event is all similar in this development track in several years, it is common event, we can be to these common event modelings, adopt figure coupling isotype method for digging, the development track in this event each period after can analysis and prediction, thereby, for the decision maker provides information reliably, can prevent accordingly and remedy in specific period.
Collaborative associated the tracking and global state potential analysis and Forecasting Methodology of 4 a networked society events of the present invention, comprise the steps:
Step S1: text and visual information to each social event are carried out feature extraction, these are carried out to the semantic hierarchies excavation across media information, thereby realize the semantic description of social event, build the semantic knowledge-base of the multi-modal information fusion based on social event, thereby obtained the multi-modal semantic description model of each social event.
Step S2: semantic relevant Web content in internet is gathered together, form a set that can reflect the social event common theme.In the face of comprising the Web content that enriches multimedia messages, there is cross-platform, cross-module state and the attribute such as spanning space-time for a networked society event, in conjunction with technology such as Cooperative Study associations, realize the collaborative associated trace model of social event on each attribute.
Step S3: by step 2, can obtain summary detailed information and the event evolving trend of a plurality of events in different time sections, can obtain thus each social event complete description from start to end.Like this can be the As time goes on visual demonstration of whole event process, the relation that can event be developed according to the development of event, the development of event, the information such as evolutionary process of event topic, with a kind of clearly, patterned showing interface is to the user.By the association analysis to these integrated society event informations, can excavate theme and the spin of this social event, and utilize the method for statistical learning, thereby dope the track of its follow-up developments, disclose the characteristic of dissemination, know the overall situation of this social event.
5 implementation results
In order to assess the present invention, we have carried out some experimental studies, from Google's news (Google News) and Flickr, have selected 18 topical subject as the focus social event of studying, and data set is as shown in table 1, it covers politics, economy, technology, amusement, military affairs, the themes such as society.3583 documents and 6742 images are arranged on Google's news, 4356 documents and 4356 images are arranged on Flickr.
The English news of the Google of table 1 the invention process effect and Flickr pictorial information data set
Table 2 is that the present invention is on the English news of Google and these two platforms of Flickr pictorial information, for the comparison of cross-platform and single platform tracking results.As can be seen from Table 2, method of the present invention is followed the tracks of significant effect is arranged in the association on cross-platform to each social event, compares at text or this single piece of information of vision, utilizes multi-modal information fusion technology, can obtain better social event and describe.Adding a plurality of platforms, using cross-platform collaborative associated the tracking, the tracking of the single platform of comparing, can access better tracking accuracy.
The comparison that the English news data of table 2 Google of the present invention is concentrated cross-platform and single platform tracking results
The table 3 Topics Crawling information to each social event that is the present invention in the English news of Google and Flickr pictorial information data centralization.As can be seen from Table 3, method of the present invention has good effect in the Topics Crawling information on cross-platform to each social event, event 1 is " controversial issue of Sino-Japan Diaoyu Island ", event 2 is " hemps of the U.S. legalize process ", event 3 is " Norway's attacks in 2011 ", event 4 is " Chinese milk scandal events in 2008 ", and event 5 is " America, presidential elections processes in 2012 ".The descriptor that event 1 is excavated has China, Japan, Diaoyu Island, Taiwan, monitor, military etc., significant reaction the subject information of this event 1, proving again the reliability of system.
Table 3 the present invention concentrates the Topics Crawling to social event in the English news data of Google
| |
|
|
|
|
| China | mari?juana | breivik | milk | Obama |
| Japan | cannabis | police | melamine | Romney |
| islands | medical | Norway | food | Republican |
| Senkaku | law | Norwegian | Chinese | president |
| Taiwan | possession | Oslo | scandal | election |
| watch | decriminalize | July | children | state |
| military | US | attacks | Sanlu | US |
Above experiment has fully confirmed validity and the completeness of this invention.
The above; it is only the embodiment in the present invention; but protection scope of the present invention is not limited to this; anyly be familiar with the people of this technology in the disclosed technical scope of the present invention; can understand conversion or the replacement expected; all should be encompassed in of the present invention comprise scope within, therefore, protection scope of the present invention should be as the criterion with the protection domain of claims.
Claims (8)
1. collaborative associated the tracking and global state potential analysis and prognoses system of an a networked society event, is characterized in that, this system comprises:
The information fusion unit, multi-modal characteristic to a networked society event data is merged, use natural language understanding and image and Video processing analytical technology, for the fuse information of the multi-modal data that obtain social event, structure is across the semantic description model of the multi-modal data of social event;
Tracking cell is connected with the information fusion unit, multi-modal data semantic descriptive model based on across social event, in the face of comprising the Web content that enriches multimedia messages, the cross-module state attribute had for a networked society event, cross-platform attribute and attribute spanning space-time, in conjunction with collaborative associated tracking technique, obtain the semantic association tracking data of social event on each attribute;
Analysis is connected with tracking cell with predicting unit, the associated tracking data of semantic-based, obtain the whole procedural information of a social event along with Time evolution, by social event Topics Crawling model, social event model prediction and social event Statistical Prediction Model mining process information, excavate theme and the spin of the social event of procedural information, thereby know the overall situation of this social event, obtain global state potential analysis and predicted data based on social event.
2. the collaborative association of a networked society event is followed the tracks of and global state potential analysis and prognoses system as claimed in claim 1, it is characterized in that, described structure is across the semantic description model of the multi-modal data of social event, for extracting the text of each social event and the feature across media information of vision, and the text of each social event, vision carried out to the semantic hierarchies excavation across media information, thereby realize the semantic description of social event, the semantic knowledge-base of the information fusion of structure based on multi-modal, thus the multi-modal semantic description of each social event obtained.
3. the collaborative association of a networked society event is followed the tracks of and global state potential analysis and prognoses system as claimed in claim 1, it is characterized in that, the semantic association tracking data of described social event on each attribute, for the semantic relevant Web content in internet is gathered together, form a set that can reflect the social event common theme.
4. the collaborative association of a networked society event is followed the tracks of and global state potential analysis and prognoses system as claimed in claim 1, it is characterized in that, global state potential analysis and the predicted data of described social event, obtain summary detailed information and the event evolving trend of a plurality of events in different time sections, obtain each social event complete description from start to end, and the As time goes on visual demonstration of whole event process, the relation that can event be developed according to the development of event, the development of event, the evolutionary process information of event topic, with clearly a kind of, patterned showing interface is to the user, by the association analysis to these integrated society event informations, excavate theme and the spin of this social event, and utilize the method for statistical learning, thereby dope the track of its follow-up developments, disclose the characteristic of dissemination, know the overall situation of this social event.
5. the collaborative association of a networked society event is followed the tracks of and global state potential analysis and prognoses system as claimed in claim 1, it is characterized in that, the multi-modal data fusion packets of information of described social event is containing the text analyzing based on natural language understanding and based on image and Video processing, realize the event semantics description system of multimodal information fusion, realize that multi-modal semantic information merges.
6. the collaborative association of a networked society event is followed the tracks of and global state potential analysis and prognoses system as claimed in claim 5, it is characterized in that, Topics Crawling semantic description based on text analyzing and image and video, take boosting algorithm to choose effective text subject and image and video theme.
7. the collaborative association of a networked society event is followed the tracks of and global state potential analysis and prognoses system as claimed in claim 1, it is characterized in that, cross-platform attribute for a networked society event, propose collaborative probability and suppose tracking more, realize collaborative associated tracking of semanteme of a plurality of social event data on two platforms, follow the tracks of for the cross-module state that realizes a networked society event and association spanning space-time.
8. the collaborative association of a networked society event is followed the tracks of and global state potential analysis and prognoses system as claimed in claim 1, it is characterized in that, described global state potential analysis based on social event and predicted data are all information of each event of obtaining according to tracking data, take the method for Topics Crawling model and statistical learning, dope theme and the tendency of each social event, for exactly social event being carried out to global state potential analysis and prediction.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2013101971291A CN103455705A (en) | 2013-05-24 | 2013-05-24 | Analysis and prediction system for cooperative correlative tracking and global situation of network social events |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2013101971291A CN103455705A (en) | 2013-05-24 | 2013-05-24 | Analysis and prediction system for cooperative correlative tracking and global situation of network social events |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN103455705A true CN103455705A (en) | 2013-12-18 |
Family
ID=49738060
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2013101971291A Pending CN103455705A (en) | 2013-05-24 | 2013-05-24 | Analysis and prediction system for cooperative correlative tracking and global situation of network social events |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103455705A (en) |
Cited By (23)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103699761A (en) * | 2014-01-13 | 2014-04-02 | 中国人民解放军国防科学技术大学 | Method and device for displaying general artificial social situation based on data flow mapping |
| CN103699663A (en) * | 2013-12-27 | 2014-04-02 | 中国科学院自动化研究所 | Hot event mining method based on large-scale knowledge base |
| CN103955505A (en) * | 2014-04-24 | 2014-07-30 | 中国科学院信息工程研究所 | Micro-blog-based real-time event monitoring method and system |
| CN105354280A (en) * | 2015-10-30 | 2016-02-24 | 中国科学院自动化研究所 | Social event tracking and evolving method based on social media platform |
| CN105630845A (en) * | 2014-11-19 | 2016-06-01 | 北京航天长峰科技工业集团有限公司 | Specific network information based analysis research and judgment method |
| CN105808722A (en) * | 2016-03-08 | 2016-07-27 | 苏州大学 | Information discrimination method and system |
| CN106126558A (en) * | 2016-06-16 | 2016-11-16 | 东软集团股份有限公司 | A kind of public sentiment monitoring method and device |
| CN106295565A (en) * | 2016-08-10 | 2017-01-04 | 中用环保科技有限公司 | Monitor event identifications based on big data and in real time method of crime prediction |
| US9742719B2 (en) | 2014-06-02 | 2017-08-22 | International Business Machines Corporation | Method for real-time viral event prediction from social data |
| CN107590733A (en) * | 2017-08-08 | 2018-01-16 | 杭州灵皓科技有限公司 | Platform methods of risk assessment is borrowed based on the net of geographical economy and social networks |
| CN107958322A (en) * | 2017-10-09 | 2018-04-24 | 中国电子科技集团公司第二十八研究所 | A kind of urban network spatial synthesis governing system |
| CN108846043A (en) * | 2018-05-30 | 2018-11-20 | 深圳市锐安信息安全技术有限公司 | Network trace mining analysis method and system based on internet big data |
| CN109635995A (en) * | 2018-10-25 | 2019-04-16 | 中国电子科技集团公司电子科学研究院 | A kind of social security events anomaly method and device based on multidimensional data |
| CN110019812A (en) * | 2018-02-27 | 2019-07-16 | 中国科学院计算技术研究所 | A kind of user is from production content detection algorithm and system |
| CN110825839A (en) * | 2019-11-07 | 2020-02-21 | 成都国腾实业集团有限公司 | Incidence relation analysis method for targets in text information |
| CN110855467A (en) * | 2019-08-19 | 2020-02-28 | 中国电子科技集团公司第三十研究所 | Network comprehensive situation prediction method based on computer vision technology |
| CN111382276A (en) * | 2018-12-29 | 2020-07-07 | 中国科学院信息工程研究所 | Event development venation map generation method |
| CN111444402A (en) * | 2019-10-29 | 2020-07-24 | 天津大学 | Analysis method for community detection based on index construction and social factor control network |
| WO2020155496A1 (en) * | 2019-01-31 | 2020-08-06 | 平安科技（深圳）有限公司 | Public opinion tracking method and device for combined video-text data, and computer apparatus |
| CN112765485A (en) * | 2021-01-18 | 2021-05-07 | 深圳市网联安瑞网络科技有限公司 | Network social event prediction method, system, terminal, computer device and medium |
| CN113449116A (en) * | 2021-06-22 | 2021-09-28 | 青岛海信网络科技股份有限公司 | Map construction and early warning method, device and medium |
| CN113486754A (en) * | 2021-06-29 | 2021-10-08 | 中国科学院自动化研究所 | Event evolution prediction method and system based on video |
| CN113761337A (en) * | 2020-12-31 | 2021-12-07 | 国家计算机网络与信息安全管理中心 | Event prediction method and device based on implicit elements and explicit relations of events |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020099744A1 (en) * | 2001-01-25 | 2002-07-25 | International Business Machines Corporation | Method and apparatus providing capitalization recovery for text |
| CN101299241A (en) * | 2008-01-14 | 2008-11-05 | 浙江大学 | Method for detecting multi-mode video semantic conception based on tensor representation |
| CN102411638A (en) * | 2011-12-30 | 2012-04-11 | 中国科学院自动化研究所 | Method for generating multimedia summary of news search result |
-
2013
- 2013-05-24 CN CN2013101971291A patent/CN103455705A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020099744A1 (en) * | 2001-01-25 | 2002-07-25 | International Business Machines Corporation | Method and apparatus providing capitalization recovery for text |
| CN101299241A (en) * | 2008-01-14 | 2008-11-05 | 浙江大学 | Method for detecting multi-mode video semantic conception based on tensor representation |
| CN102411638A (en) * | 2011-12-30 | 2012-04-11 | 中国科学院自动化研究所 | Method for generating multimedia summary of news search result |
Non-Patent Citations (2)
| Title |
|---|
| 赵旭剑: "中文新闻话题动态演化及其关键技术研究", 《中国博士学位论文全文数据库》 * |
| 齐海凤: "网络舆情热点发现与事件跟踪技术研究", 《中国优秀硕士学位论文全文数据库》 * |
Cited By (34)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103699663A (en) * | 2013-12-27 | 2014-04-02 | 中国科学院自动化研究所 | Hot event mining method based on large-scale knowledge base |
| CN103699663B (en) * | 2013-12-27 | 2017-02-08 | 中国科学院自动化研究所 | Hot event mining method based on large-scale knowledge base |
| CN103699761B (en) * | 2014-01-13 | 2015-08-05 | 中国人民解放军国防科学技术大学 | Based on general artificial social product battle state display method and the device of data stream |
| CN103699761A (en) * | 2014-01-13 | 2014-04-02 | 中国人民解放军国防科学技术大学 | Method and device for displaying general artificial social situation based on data flow mapping |
| CN103955505A (en) * | 2014-04-24 | 2014-07-30 | 中国科学院信息工程研究所 | Micro-blog-based real-time event monitoring method and system |
| US9742719B2 (en) | 2014-06-02 | 2017-08-22 | International Business Machines Corporation | Method for real-time viral event prediction from social data |
| CN105630845A (en) * | 2014-11-19 | 2016-06-01 | 北京航天长峰科技工业集团有限公司 | Specific network information based analysis research and judgment method |
| CN105354280A (en) * | 2015-10-30 | 2016-02-24 | 中国科学院自动化研究所 | Social event tracking and evolving method based on social media platform |
| CN105808722A (en) * | 2016-03-08 | 2016-07-27 | 苏州大学 | Information discrimination method and system |
| CN105808722B (en) * | 2016-03-08 | 2020-07-24 | 苏州大学 | Information discrimination method and system |
| CN106126558B (en) * | 2016-06-16 | 2019-09-20 | 东软集团股份有限公司 | A kind of public sentiment monitoring method and device |
| CN106126558A (en) * | 2016-06-16 | 2016-11-16 | 东软集团股份有限公司 | A kind of public sentiment monitoring method and device |
| CN106295565A (en) * | 2016-08-10 | 2017-01-04 | 中用环保科技有限公司 | Monitor event identifications based on big data and in real time method of crime prediction |
| CN107590733A (en) * | 2017-08-08 | 2018-01-16 | 杭州灵皓科技有限公司 | Platform methods of risk assessment is borrowed based on the net of geographical economy and social networks |
| CN107958322A (en) * | 2017-10-09 | 2018-04-24 | 中国电子科技集团公司第二十八研究所 | A kind of urban network spatial synthesis governing system |
| CN107958322B (en) * | 2017-10-09 | 2021-08-10 | 中国电子科技集团公司第二十八研究所 | Urban network space comprehensive treatment system |
| CN110019812A (en) * | 2018-02-27 | 2019-07-16 | 中国科学院计算技术研究所 | A kind of user is from production content detection algorithm and system |
| CN110019812B (en) * | 2018-02-27 | 2021-08-20 | 中国科学院计算技术研究所 | User self-production content detection method and system |
| CN108846043A (en) * | 2018-05-30 | 2018-11-20 | 深圳市锐安信息安全技术有限公司 | Network trace mining analysis method and system based on internet big data |
| CN109635995A (en) * | 2018-10-25 | 2019-04-16 | 中国电子科技集团公司电子科学研究院 | A kind of social security events anomaly method and device based on multidimensional data |
| CN111382276A (en) * | 2018-12-29 | 2020-07-07 | 中国科学院信息工程研究所 | Event development venation map generation method |
| CN111382276B (en) * | 2018-12-29 | 2023-06-20 | 中国科学院信息工程研究所 | Event development context graph generation method |
| WO2020155496A1 (en) * | 2019-01-31 | 2020-08-06 | 平安科技（深圳）有限公司 | Public opinion tracking method and device for combined video-text data, and computer apparatus |
| CN110855467A (en) * | 2019-08-19 | 2020-02-28 | 中国电子科技集团公司第三十研究所 | Network comprehensive situation prediction method based on computer vision technology |
| CN110855467B (en) * | 2019-08-19 | 2022-02-08 | 中国电子科技集团公司第三十研究所 | Network comprehensive situation prediction method based on computer vision technology |
| CN111444402A (en) * | 2019-10-29 | 2020-07-24 | 天津大学 | Analysis method for community detection based on index construction and social factor control network |
| CN110825839A (en) * | 2019-11-07 | 2020-02-21 | 成都国腾实业集团有限公司 | Incidence relation analysis method for targets in text information |
| CN113761337A (en) * | 2020-12-31 | 2021-12-07 | 国家计算机网络与信息安全管理中心 | Event prediction method and device based on implicit elements and explicit relations of events |
| CN113761337B (en) * | 2020-12-31 | 2023-10-27 | 国家计算机网络与信息安全管理中心 | Event prediction method and device based on implicit event element and explicit connection |
| CN112765485A (en) * | 2021-01-18 | 2021-05-07 | 深圳市网联安瑞网络科技有限公司 | Network social event prediction method, system, terminal, computer device and medium |
| CN113449116A (en) * | 2021-06-22 | 2021-09-28 | 青岛海信网络科技股份有限公司 | Map construction and early warning method, device and medium |
| CN113449116B (en) * | 2021-06-22 | 2022-12-20 | 青岛海信网络科技股份有限公司 | Map construction and early warning method, device and medium |
| CN113486754A (en) * | 2021-06-29 | 2021-10-08 | 中国科学院自动化研究所 | Event evolution prediction method and system based on video |
| CN113486754B (en) * | 2021-06-29 | 2024-01-09 | 中国科学院自动化研究所 | Event evolution prediction method and system based on video |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103455705A (en) | Analysis and prediction system for cooperative correlative tracking and global situation of network social events | |
| EP3819792A2 (en) | Method, apparatus, device, and storage medium for intention recommendation | |
| Bozarth et al. | Toward a better performance evaluation framework for fake news classification | |
| CN106598944B (en) | A kind of civil aviaton's security public sentiment sentiment analysis method | |
| Jackoway et al. | Identification of live news events using Twitter | |
| US9229977B2 (en) | Real-time and adaptive data mining | |
| Liu et al. | Event detection and evolution in multi-lingual social streams | |
| Sun et al. | Ddgcn: Dual dynamic graph convolutional networks for rumor detection on social media | |
| Alsaedi et al. | Arabic event detection in social media | |
| CN103268350A (en) | Internet public opinion information monitoring system and monitoring method | |
| CN103246644B (en) | Method and device for processing Internet public opinion information | |
| CN103544255A (en) | Text semantic relativity based network public opinion information analysis method | |
| CN108399241A (en) | A kind of emerging much-talked-about topic detecting system based on multiclass feature fusion | |
| CN105630884A (en) | Geographic position discovery method for microblog hot event | |
| Huang et al. | Early detection of emergency events from social media: A new text clustering approach | |
| CN103177076A (en) | Public sentiment monitoring system and method based on fixed point websites | |
| CN104899335A (en) | Method for performing sentiment classification on network public sentiment of information | |
| Alsaedi et al. | A combined classification-clustering framework for identifying disruptive events | |
| CN104346382B (en) | Use the text analysis system and method for language inquiry | |
| CN104268230A (en) | Method for detecting objective points of Chinese micro-blogs based on heterogeneous graph random walk | |
| CN106294333A (en) | A kind of microblogging burst topic detection method and device | |
| Zhao et al. | Towards events detection from microblog messages | |
| Zhou et al. | Classification of microblogs for support emergency responses: Case study Yushu earthquake in China | |
| Afyouni et al. | Spatio-temporal event discovery in the big social data era | |
| Zavarella et al. | An Ontology-Based Approach to Social Media Mining for Crisis Management. |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into 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: 20131218 |