CN108710654A - A kind of public sentiment data method for visualizing and equipment - Google Patents
A kind of public sentiment data method for visualizing and equipment Download PDFInfo
- Publication number
- CN108710654A CN108710654A CN201810441355.2A CN201810441355A CN108710654A CN 108710654 A CN108710654 A CN 108710654A CN 201810441355 A CN201810441355 A CN 201810441355A CN 108710654 A CN108710654 A CN 108710654A
- Authority
- CN
- China
- Prior art keywords
- public sentiment
- keyword
- sentiment data
- data
- emotional category
- 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.)
- Granted
Links
Abstract
This application provides a kind of public sentiment data method for visualizing and equipment, the program is after acquiring public sentiment data, first determine the emotional category and temporal information of every public sentiment data, then according to the emotional category and temporal information of the public sentiment data, determine the quantity for the public sentiment data for belonging to target emotional category in each preset time period, and obtain the keyword for the public sentiment data for belonging to target emotional category in each preset time period, and then according to the quantity for the public sentiment data for belonging to target emotional category in each preset time period, generate the visualized graphs about each preset time period, and corresponding keyword is added in the visualized graphs.Due to being intuitively demonstrated by the Sentiment orientation of public sentiment data in preset time period, quantity and the keyword being related in visualized graphs, user is by checking that visualized graphs can comprehensively and efficiently understand the public opinion situation in preset time period.
Description
Technical field
This application involves information technology field more particularly to a kind of public sentiment data method for visualizing and equipment.
Background technology
Under the internet big data epoch, emerge one after another from the various new media forms such as media, for social event and news
The various comments of report, article content are very different, and the good and bad jumbled together, more has unique force malicious calumniation to start a rumour, deliberately
Deceptive information is issued, or is added fuel to the flames to unreal report, attempts to mislead public opinion by quick and various transmission on Internet way, by
This can lead to the generation of large-scale public sentiment event, bring about great losses to state and society.Due to new on current internet
The public sentiment datas publication channels such as news report, event message, comment are more, and information content is huge, and there are no one kind to allow user can
Comprehensively and efficiently understand the mode of current public sentiment tendency.
Apply for content
The purpose of the application is to provide a kind of public sentiment data visualization scheme, can allow user comprehensively and efficiently
Current public sentiment tendency is solved, and then reaches the monitoring to public sentiment.
To achieve the above object, this application provides a kind of public sentiment data method for visualizing, this method includes：
Acquire public sentiment data；
Determine the emotional category and temporal information of every public sentiment data；
According to the emotional category and temporal information of the public sentiment data, determines and belong to target emotion in each preset time period
The quantity of the public sentiment data of classification, and obtain the key for the public sentiment data for belonging to target emotional category in each preset time period
Word；
According to the quantity for the public sentiment data for belonging to target emotional category in each preset time period, generate about each default
The visualized graphs of period, and corresponding keyword is added in the visualized graphs.
Another aspect based on the application also provides a kind of public sentiment data visualization device, wherein the equipment includes：
Data acquisition device, for acquiring public sentiment data；
Data processing equipment, emotional category and temporal information for determining every public sentiment data, and according to the carriage
The emotional category and temporal information of feelings data, determine the number for the public sentiment data for belonging to target emotional category in each preset time period
Amount, and obtain the keyword for the public sentiment data for belonging to target emotional category in each preset time period；
Data coding device, for the number according to the public sentiment data for belonging to target emotional category in each preset time period
Amount generates the visualized graphs about each preset time period, and adds corresponding keyword in the visualized graphs.
In addition, present invention also provides a kind of public sentiment data visualization device, which includes：
Processor；And
One or more machine readable medias of machine readable instructions are stored with, when the processor execution machine can
When reading instruction so that the equipment executes public sentiment data method for visualizing above-mentioned.
In scheme provided by the present application, after acquiring public sentiment data, first determine every public sentiment data emotional category and
Temporal information determines then according to the emotional category and temporal information of the public sentiment data and belongs to target feelings in preset time period
Feel the quantity of the public sentiment data of classification, and obtains the key for the public sentiment data for belonging to target emotional category in the preset time period
Word, and then according to the quantity for the public sentiment data for belonging to target emotional category in preset time period, generate about the preset time
The visualized graphs of section, and corresponding keyword is added in the visualized graphs.Due to intuitive earth's surface in visualized graphs
The Sentiment orientation of public sentiment data in preset time period, quantity and the keyword being related to are showed, therefore user is visual by checking
The public opinion situation in preset time period can comprehensively and efficiently be understood by changing figure.
Description of the drawings
By reading a detailed description of non-restrictive embodiments in the light of the attached drawings below, the application's is other
Feature, objects and advantages will become more apparent upon：
Fig. 1 is a kind of process chart of public sentiment data method for visualizing provided by the embodiments of the present application；
Fig. 2 is a kind of schematic diagram of visual layout involved in the embodiment of the present application；
Fig. 3 be the embodiment of the present application use schemes generation public sentiment data visualized graphs provided by the embodiments of the present application when
Overall flow figure；
Fig. 4 shows the detailed process of data processing step in a kind of embodiment of the application；
Fig. 5 shows the detailed process of data encoding step in a kind of embodiment of the application；
Fig. 6 is a kind of structural schematic diagram of public sentiment data visualization device provided by the embodiments of the present application；
Fig. 7 is the structural schematic diagram of another public sentiment data visualization device provided by the embodiments of the present application；
Same or analogous reference numeral represents same or analogous component in attached drawing.
Specific implementation mode
The application is described in further detail below in conjunction with the accompanying drawings.
In a typical configuration of this application, terminal, the equipment of service network include one or more processors
(CPU), input/output interface, network interface and memory.
Memory may include computer-readable medium in volatile memory, random access memory (RAM) and/or
The forms such as Nonvolatile memory, such as read-only memory (ROM) or flash memory (flash RAM).Memory is computer-readable medium
Example.
Computer-readable medium includes permanent and non-permanent, removable and non-removable media, can be by any side
Method or technology realize information storage.Information can be computer-readable instruction, data structure, program device or other number
According to.The example of the storage medium of computer includes, but are not limited to phase transition internal memory (PRAM), static RAM
(SRAM), dynamic random access memory (DRAM), other kinds of random access memory (RAM), read-only memory
(ROM), electrically erasable programmable read-only memory (EEPROM), fast flash memory bank or other memory techniques, CD-ROM (CD-
ROM), digital versatile disc (DVD) or other optical storages, magnetic tape cassette, magnetic tape disk storage or other magnetic storages
Equipment or any other non-transmission medium can be used for storage and can be accessed by a computing device information.
The embodiment of the present application provides a kind of public sentiment data method for visualizing, and this method can be according to collecting in a period of time
Public sentiment data generate visualized graphs, and intuitively show in the visualized graphs feelings of public sentiment data in preset time period
Sense tendency, quantity and the keyword being related to so that user is by checking that it is a certain that visualized graphs can comprehensively and efficiently understand
Public opinion situation in period.In actual scene, the executive agent of this method can include but is not limited to network host, single
Network server, multiple network server collection or the set of computers etc. based on cloud computing.Here, cloud is by being based on cloud computing
A large amount of hosts or network server of (Cloud Computing) are constituted, wherein and cloud computing is one kind of Distributed Calculation, by
One virtual machine of the computer collection composition of a group loose couplings.
Fig. 1 shows a kind of process flow of public sentiment data method for visualizing provided by the embodiments of the present application, including following
Processing step：
S101 acquires public sentiment data.The application implement in, the public sentiment data refer to about the data of public opinion situation,
All kinds of media such as news report, forum, blog, microblogging, community comments can be derived from, the public can be reflected for society
The attitude and Sentiment orientation that generation, development and the variation of meeting event are held.Under Internet scene, crawlers may be used
(web crawler) obtains all kinds of public sentiment datas according to default rule from internet, such as periodically from all kinds of portal websites
Obtain all kinds of news and the comment for the news.
S102 determines the emotional category and temporal information of every public sentiment data, for dividing these public sentiment datas
Class is gathered the public sentiment data of the same emotional category in special time period as one.
In the emotional category for determining public sentiment data, it can identify according to the content of every public sentiment data and mark every
The emotional category of public sentiment data.Wherein, emotional category can be set according to the demand of actual classification, such as the application is implemented
Emotional category is set as two classifications, i.e. positive emotion and negative emotion in example, it can also be according to reality in actual scene
Demand further segments positive emotion and negative emotion, to obtain more emotional categories.In the embodiment of the present application
In, if this collected public sentiment data has 1 to N items, according to emotion is positive and negative classified after, wherein 1 is to be classified as to M items
Positive emotion, M+1 to N marks are classified as negative emotion.
The emotional category of public sentiment data can be determined based on the content of public sentiment data, such as the content of a certain news is report
Event that the road somewhere common people are not hesitate to do what is right simultaneously makes an affirmation to the behavior, then the emotional category of this news can be classified as just
Face emotion.In actual scene, machine learning algorithm may be used and carry out automatic identification, use labeled emotional category first
Training set is trained the disaggregated model of machine learning, completes after training, which can be to newly inputting
The emotional category of public sentiment data is identified.Wherein, the specific algorithm of machine learning can be carried out according to the demand of actual scene
Selection, such as logistic regression, decision tree, naive Bayesian scheduling algorithm.
When determining the temporal information of every public sentiment data, the issuing time can be determined as the public sentiment data
Temporal information, for example, a certain public sentiment data issuing time be 2018-4-22,20:22:22, then it can determine its temporal information
For the issuing time.But in some special circumstances, for example, website do not open corresponding interface or not to issuing time into
Row record, then can not get issuing time, can determine the public sentiment by according to the time for acquiring the public sentiment data at this time
The temporal information of data.Such as updating faster website, crawlers are set as obtaining it every 10s the primary website
Public sentiment data, the time for getting public sentiment data every time is set as the temporal information of the public sentiment data.As a result, in the application
Some embodiments in, if in public sentiment data include issuing time, the issuing time is determined as the public sentiment data
Temporal information；If not including issuing time in public sentiment data, by according to the time for acquiring the public sentiment data, the carriage is determined
The temporal information of feelings data.
Step S103 is determined in each preset time period and is belonged to according to the emotional category and temporal information of the public sentiment data
In the quantity of the public sentiment data of target emotional category, and obtain the public sentiment number for belonging to target emotional category in each preset time period
According to keyword.
The chronomere that preset time period is generated as visualized graphs, such as preset time period are 1 hour, then this Shen
Please embodiment scheme when being handled using 1 hour as statistics time interval, it is specific within 1 hour to count
The quantity of the public sentiment data of emotional category.For example, the public sentiment data of acquisition may includes the data in nearest 5 hours, this
When according to 1 hour time interval be divided into 5 preset time periods, count in each preset time period the quantity of public sentiment data and
Keyword.Target emotional category refers to the emotional category for needing to embody in visualized graphs, can include all emotional categories,
Selected part user the emotional category paid close attention to can also be needed in all emotional categories, such as in the embodiment of the present application, mark feelings
It can be positive emotion and negative emotion to feel classification.With preset time period 00:00:01-01:00:For 00, if collected carriage
The temporal information of feelings data has 200 within the preset time period, wherein and emotional category has 130 for positive emotion,
Emotional category has 70 for negative emotion, it is possible thereby to determine preset time period 00:00:01-01:00:Belong to target in 00
The quantity of the public sentiment data of emotional category is：Positive emotion 130, negative emotion 70.
For collected public sentiment data, keyword extraction algorithm extraction keyword may be used.The embodiment of the present application into
Any suitable algorithm that scene is handled in public sentiment data, such as TF- may be used in used algorithm when row keyword extraction
IDF, KEA scheduling algorithm.Can be that the keyword adds flag information for the keyword extracted, with distinguish content it is identical but
Come from the keyword of the public sentiment data of different preset time periods.For example, for public sentiment data 1, can extract to obtain keyword 1
With keyword 2, record when can with keyword add flag information, such as incidentally timestamp or it is other can be used in distinguish close
The information of the affiliated preset time period of keyword.In a kind of embodiment of the application, under type form such as may be used and record：It is crucial
Word _ period _ emotional category, such as keyword 1_ periods 1_ front, the period 2_ fronts keyword 1_.Wherein, the period
Preset time period as belonging to 1 corresponding public sentiment data of keyword, and emotional category is then 1 corresponding public sentiment data of keyword
Emotional category.
Step S104 is generated and is closed according to the quantity for the public sentiment data for belonging to target emotional category in each preset time period
In the visualized graphs of each preset time period, and corresponding keyword is added in the visualized graphs.
It, can be first according to belonging in each preset time period when generating visualized graphs about each preset time period
The quantity of the public sentiment data of target emotional category determines the graphic attribute of the visualized graphs about each preset time period, should
Graphic attribute can be with the relevant parameter of the visual image of visualized graphs, it is specifically true according to the graphic style actually used
It is fixed, such as can be any one of the areas of visualized graphs, height, width, diameter, curvature or multinomial combination.
After determining graphic attribute, it can be generated in the display area of target emotional category described visual according to the graphic attribute
Change figure.For example, when visualized graphs are block diagram, graphic attribute can be the height of block diagram, and visualized graphs are folding
When line chart, graphic attribute can be the area etc. for the closed figure that line chart is surrounded.
In some embodiments of the present application, the public sentiment data of target emotional category is belonged to according to each preset time period
Quantity can first determine visual layout, wherein described before generating visualized graphs about each preset time period
Visual layout includes at least the form of the display area and visualized graphs of target emotional category.For example, Fig. 2 shows this Shens
A kind of visual layout that please be in embodiment, using the pattern of mirrored arrangement, i.e., using the time as horizontal axis, as dividing two kinds of emotions
The baseline of classification display area, will be divided into the display area of two kinds of emotional categories up and down, be the exhibition of positive emotion above baseline
Show region, is the display area of negative emotion below baseline, the public sentiment data of target emotional category is belonged in preset time period
Quantity as the longitudinal axis, the form of visualized graphs is line chart.
In some embodiments of the present application, when adding corresponding keyword in the visualized graphs, can first it count
The word frequency for belonging to the keyword of the public sentiment data of target emotional category in each preset time period, then according to the keyword
Word frequency adds corresponding keyword in the form of word cloud in the visualized graphs.By using the form of word cloud so that close
Display size of the keyword in visualized graphs is related to the word frequency that it occurs, for example, the high keyword of word frequency occur shows ruler
It is very little larger, and it is then relatively small the low keyword display size of word frequency occur.
In the embodiment of the present application, the form record of " keyword _ period _ emotional category " may be used after extraction keyword
The statistical information of the keyword.According to the statistical information, the word frequency of keyword in each period, example can be further counted
Such as, for keyword 1, statistical information has the record 60 about keyword 1 altogether, wherein " keyword 1_ periods 1_ front "
Record have 10, the record of " keyword 1_ periods 2_ front " has 20, and the note in " keyword 1_ periods 4_ front "
Record has 30.When building word cloud, the size of display size is related to the word frequency that keyword occurs, it is possible thereby to proportionally really
Display size of the keyword in each preset time period is determined, for example, for keyword 1 above-mentioned, in preset time period 1
Occur 10 times, occur in preset time period 2 20 times, occurs in preset time period 4 30 times, thus generating word cloud
When, display size is minimum in preset time period 1, takes second place in preset time period 2, and the display size in preset time period 4
It is maximum.
It is further possible to determine the word frequency of other keywords in the same way, and then it is based on all keywords
Word frequency uniformly determine the sizes of different keyword display sizes in different preset time periods in word cloud.
Further, since visualized graphs correspond to preset time period, it can be related with this attribute of time to its display location,
Therefore when adding keyword, the display location of keyword can also be associated with the time, and user can be from added with key
More information are obtained in the visualized graphs of word, such as by the keyword on sometime corresponding position, determining should
The topic that moment public sentiment is primarily upon.It, can also be according to institute when adding corresponding keyword in the visualized graphs as a result,
The temporal information for stating keyword determines location information of the keyword in the visualized graphs, then according to institute's rheme
Confidence ceases, and corresponding keyword is added in the corresponding position in the visualized graphs, wherein the time of the keyword believes
Breath is the temporal information of the public sentiment data belonging to the keyword.
Further, can also be that the visualized graphs and the keyword add in some embodiments of the present application
Color, and color emotional category corresponding to the visualized graphs is related, it is possible thereby to allow user from color
On overall condition of the more intuitive impression per the public sentiment data of a kind of emotional category.In actual scene, the selection of color can
To be set according to the use habit of user, such as two emotional categories in the embodiment of the present application, can use red, yellow
Etc. warm colours color indicia positive emotion, mark negative emotion using the color of the cool colours such as indigo plant, blueness.
When Fig. 3, Fig. 4 and Fig. 5 are shown using schemes generation public sentiment data visualized graphs provided by the embodiments of the present application
Process flow, including following processing step：
Step S1, data acquisition.
Step S2, data processing.
Wherein, step S2 includes the content of 3 parts, as shown in Figure 4.First, public sentiment data acquisition come is according to feelings
Feel positive and negative progress mark classification processing, it is assumed that data content has 1 to arrive N items, returns content-data 1 to M marks according to emotion is positive and negative
Class is positive emotion data, and M+1 to N marks are classified as negative emotion data.Secondly, a time interval is set, as pre-
If the period, such as 1 hour, then the quantity statistics of public sentiment data are carried out in the period one by one.Finally, in each preset time
In section, according to the positive and negative classification of emotional category, the word frequency of the keyword occurred in the preset time period is counted.
Step S3, data encoding.
Wherein, the content of following 3 parts step S3, as shown in Figure 5.First, the visualization for data displaying is determined
The visual layout of figure.Using mirrored arrangement as layout pattern, i.e., it is the longitudinal axis by the quantity of horizontal axis, public sentiment data of the time,
The quantity of public sentiment data is used as baseline for 0, is the display area of positive emotion above baseline, is negative emotion below baseline
Display area.
Secondly, by emotional category and the period determined, the quantity of public sentiment data is encoded, in the positive minus zone of emotion
Domain is encoded according to the quantity of statistics with broken line diagram form by the period respectively.Coding form can be line chart, can also
It is the form that other energy such as curve graph and baseline constitute closed area, the size that line chart or curve graph be constituted with baseline
It indicates that quantity, positive and negative can be encoded using different colours of emotional category are distinguished to show, red coding can be used for example
Negative emotion uses blue-coded positive emotion.
Finally, keyword is encoded, according to emotional category, within each period, to the keyword handled well and
Word frequency data carry out word cloud coding, and keyword data, wherein the word frequency number of the size coding keyword of word are shown with word cloud form
According to emotional category and its temporal information determine the spatial position belonging to it, and foundation public sentiment is positive and negative can be used and respectively affiliated carriage
The color of the tone encoded key word of feelings emotion same color is to show emotional category.
Step S4, visualization output.To handle and encode the data of completion as procedure described above, using computer or other
Means are showed in the form of visualized graphs, you can are obtained a set of be directed to and coupled public sentiment data emotion variation tendency number
According to the visual presentation scheme of, the multi-dimensional time sequence data of quantity, public sentiment keyword and word frequency data, can be helped using the program
It helps and grasps hot spot public sentiment, the overall growth dynamic of event, the public and netizen to its main comment, view, viewpoint and emotion
Tendency, and then reach the monitoring and management to internet public feelings, it can also be used as the basis that public sentiment event analysis is studied and judged.
Based on same inventive concept, a kind of public sentiment data visualization device is additionally provided in the embodiment of the present application, it is described to set
Standby corresponding method is the public sentiment data method for visualizing in previous embodiment, and its principle for solving the problems, such as and this method phase
Seemingly.
A kind of public sentiment data visualization device provided by the embodiments of the present application can be according to the public sentiment collected in a period of time
Data generate visualized graphs, and the emotion for intuitively showing in the visualized graphs public sentiment data in preset time period is inclined
To, quantity and the keyword being related to so that user is by checking that visualized graphs can comprehensively and efficiently understand sometime
Public opinion situation in section.In actual scene, the specific implementation of the equipment can include but is not limited to network host, single network
Server, multiple network server collection or the set of computers etc. based on cloud computing.Here, cloud is by being based on cloud computing (Cloud
Computing a large amount of hosts or network server) are constituted, wherein cloud computing is one kind of Distributed Calculation, loose by a group
One virtual machine of the computer collection composition of coupling.
Fig. 6 shows a kind of structure of public sentiment data visualization device provided by the embodiments of the present application, including data acquisition
Device 610, data processing equipment 620, data coding device 630.Wherein, the data acquisition device 610 is for acquiring public sentiment
Data.During the application is implemented, the public sentiment data refers to that can derive from news report, opinion about the data of public opinion situation
All kinds of media such as altar, blog, microblogging, community comments can reflect generation, development and change of the public for social event
Change held attitude and Sentiment orientation.Under Internet scene, crawlers (web crawler) may be used according to default
Rule obtain all kinds of public sentiment datas from internet, such as periodically from all kinds of portal websites obtain all kinds of news and for this it is new
The comment of news.
Data processing equipment 620 is used to determine the emotional category and temporal information of every public sentiment data, for these
Public sentiment data is classified, and is gathered the public sentiment data of the same emotional category in special time period as one.
In the emotional category for determining public sentiment data, the data processing equipment can be according in every public sentiment data
Hold, identifies and mark the emotional category of every public sentiment data.Wherein, emotional category can be set according to the demand of actual classification
It is fixed, such as emotional category is set as two classifications, i.e. positive emotion and negative emotion in the embodiment of the present application, in actual scene
In positive emotion and negative emotion can also further be segmented according to actual demand, to obtain more emotion classes
Not.In the embodiment of the present application, if this collected public sentiment data has 1 to N items, according to emotion is positive and negative classified after,
Wherein 1 to M items be classified as positive emotion, M+1 to N marks are classified as negative emotion.
The emotional category of public sentiment data can be determined based on the content of public sentiment data, such as the content of a certain news is report
Event that the road somewhere common people are not hesitate to do what is right simultaneously makes an affirmation to the behavior, then the emotional category of this news can be classified as just
Face emotion.In actual scene, machine learning algorithm may be used and carry out automatic identification, use labeled emotional category first
Training set is trained the disaggregated model of machine learning, completes after training, which can be to newly inputting
The emotional category of public sentiment data is identified.Wherein, the specific algorithm of machine learning can be carried out according to the demand of actual scene
Selection, such as logistic regression, decision tree, naive Bayesian scheduling algorithm.
When determining the temporal information of every public sentiment data, the data processing equipment can determine the issuing time
For the temporal information of the public sentiment data, such as the issuing time of a certain public sentiment data is 2018-4-22,20:22:22, then may be used
To determine its temporal information for the issuing time.But in some special circumstances, for example, website do not open corresponding interface or
Person does not record issuing time, then can not get issuing time, at this time can will be according to acquiring the public sentiment data
Time determines the temporal information of the public sentiment data.Such as updating faster website, crawlers are set as every 10s
The public sentiment data of the primary website is obtained to it, the time for getting public sentiment data every time is set as the time of the public sentiment data
Information.It is if in public sentiment data including issuing time, the issuing time is true as a result, in some embodiments of the present application
It is set to the temporal information of the public sentiment data；It, will be according to the acquisition public sentiment number if not including issuing time in public sentiment data
According to time, determine the temporal information of the public sentiment data.
Data processing equipment 620 is additionally operable to emotional category and temporal information according to the public sentiment data, determines each pre-
If belonging to the quantity of the public sentiment data of target emotional category in the period, and obtains and belong to target emotion in each preset time period
The keyword of the public sentiment data of classification.
The chronomere that preset time period is generated as visualized graphs, such as preset time period are 1 hour, then this Shen
Please embodiment scheme when being handled using 1 hour as statistics time interval, it is specific within 1 hour to count
The quantity of the public sentiment data of emotional category.For example, the public sentiment data of acquisition may includes the data in nearest 5 hours, this
When according to 1 hour time interval be divided into 5 preset time periods, count in each preset time period the quantity of public sentiment data and
Keyword.Target emotional category refers to the emotional category for needing to embody in visualized graphs, can include all emotional categories,
Selected part user the emotional category paid close attention to can also be needed in all emotional categories, such as in the embodiment of the present application, mark feelings
It can be positive emotion and negative emotion to feel classification.With preset time period 00:00:01-01:00:For 00, if collected carriage
The temporal information of feelings data has 200 within the preset time period, wherein and emotional category has 130 for positive emotion,
Emotional category has 70 for negative emotion, it is possible thereby to determine preset time period 00:00:01-01:00:Belong to target in 00
The quantity of the public sentiment data of emotional category is：Positive emotion 130, negative emotion 70.
For collected public sentiment data, keyword extraction algorithm extraction keyword may be used in data processing equipment.This
Any suitable calculation that scene is handled in public sentiment data may be used in used algorithm when application embodiment progress keyword extraction
Method, such as TF-IDF, KEA scheduling algorithm.Can be that the keyword adds flag information, to distinguish for the keyword extracted
Content is identical but comes from the keyword of different public sentiment datas.For example, for public sentiment data 1, can extract to obtain keyword 1
With keyword 2, record when can with keyword add flag information, such as incidentally timestamp or it is other can be used in distinguish close
The information of the affiliated preset time period of keyword.In a kind of embodiment of the application, under type form such as may be used and record：It is crucial
Word _ period _ emotional category, such as keyword 1_ periods 1_ front, the period 2_ fronts keyword 1_.Wherein, the period
Preset time period as belonging to 1 corresponding public sentiment data of keyword, and emotional category is then 1 corresponding public sentiment data of keyword
Emotional category.
Data coding device 630 is used for the number according to the public sentiment data for belonging to target emotional category in each preset time period
Amount generates the visualized graphs about each preset time period, and adds corresponding keyword in the visualized graphs.
When generating the visualized graphs about each preset time period, data coding device can be first according to each default
Belong to the quantity of the public sentiment data of target emotional category in period, determines the visualized graphs about each preset time period
Graphic attribute, the graphic attribute can be with the visual image of visualized graphs relevant parameter, according to according to actually using
Graphic style specifically determines, for example, can be any one of the areas of visualized graphs, height, width, diameter, curvature or
Multinomial combination.It, can be according to the graphic attribute, in the display area of target emotional category after determining graphic attribute
Generate the visualized graphs.For example, when visualized graphs are block diagram, graphic attribute can be the height of block diagram, can
When regarding figure is line chart, graphic attribute can be the area etc. for the closed figure that line chart is surrounded.
In some embodiments of the present application, the number of the public sentiment data of target emotional category is belonged to according to preset time period
Amount, before generating the visualized graphs about the preset time period, data coding device can first determine visual layout,
In, the visual layout includes at least the form of the display area and visualized graphs of target emotional category.For example, Fig. 2 shows
A kind of visual layout in the embodiment of the present application is gone out, using the pattern of mirrored arrangement, i.e., using the time as horizontal axis, as division
The baseline of two kinds of emotional category display areas will be divided into the display area of two kinds of emotional categories up and down, be positive above baseline
The display area of emotion is the display area of negative emotion below baseline, belongs to target emotional category in preset time period
For the quantity of public sentiment data as the longitudinal axis, the form of visualized graphs is line chart.
In some embodiments of the present application, when adding corresponding keyword in the visualized graphs, data processing dress
The word frequency for the keyword that can first count the public sentiment data for belonging to target emotional category in each preset time period is set, then data
Code device adds corresponding keyword in the form of word cloud according to the word frequency of the keyword in the visualized graphs.
By using the form of word cloud so that display size of the keyword in visualized graphs is related to the word frequency that it occurs, for example,
It is larger to there is the high keyword display size of word frequency, and it is then relatively small the low keyword display size of word frequency occur.
In the embodiment of the present application, the form record of " keyword _ period _ emotional category " may be used after extraction keyword
The statistical information of the keyword.According to the statistical information, the word frequency of keyword in each period, example can be further counted
Such as, for keyword 1, statistical information has the record 60 about keyword 1 altogether, wherein " keyword 1_ periods 1_ front "
Record have 10, the record of " keyword 1_ periods 2_ front " has 20, and the note in " keyword 1_ periods 4_ front "
Record has 30.When building word cloud, the size of display size is related to the word frequency that keyword occurs, it is possible thereby to proportionally really
Display size of the keyword in each preset time period is determined, for example, for keyword 1 above-mentioned, in preset time period 1
Occur 10 times, occur in preset time period 2 20 times, occurs in preset time period 4 30 times, thus generating word cloud
When, display size is minimum in preset time period 1, takes second place in preset time period 2, and the display size in preset time period 4
It is maximum.
It is further possible to determine the word frequency of other keywords in the same way, and then it is based on all keywords
Word frequency uniformly determine the sizes of different keyword display sizes in different preset time periods in word cloud.
Further, since visualized graphs correspond to preset time period, it can be related with this attribute of time to its display location,
Therefore when adding keyword, the display location of keyword can also be associated with the time, and user can be from added with key
More information are obtained in the visualized graphs of word, such as by the keyword on sometime corresponding position, determining should
The topic that moment public sentiment is primarily upon.When adding corresponding keyword in the visualized graphs as a result, data coding device
Location information of the keyword in the visualized graphs can also be determined according to the temporal information of the keyword, so
Afterwards according to the positional information, corresponding keyword is added in the corresponding position in the visualized graphs, wherein the pass
The temporal information of keyword is the temporal information of the public sentiment data belonging to the keyword.
Further, in some embodiments of the present application, data coding device can also be the visualized graphs and institute
State keyword addition color, and color emotional category corresponding to the visualized graphs is related, it is possible thereby to so that with
Family more can intuitively experience the overall condition of the public sentiment data per a kind of emotional category from color.In actual scene,
The selection of color can be set according to the use habit of user, such as two emotional categories in the embodiment of the present application,
The color indicia positive emotion that the warm colours such as red, yellow can be used, negative feelings are marked using the color of the cool colours such as indigo plant, blueness
Sense.
In addition, the part of the application can be applied to computer program product, such as computer program instructions, when its quilt
When computer executes, by the operation of the computer, it can call or provide according to the present processes and/or technical solution.
And the program instruction of the present processes is called, it is possibly stored in fixed or moveable recording medium, and/or pass through
Broadcast or the data flow in other signal loaded mediums and be transmitted, and/or be stored in the calculating run according to program instruction
In the working storage of machine equipment.Here, including an equipment as shown in Figure 7 according to one embodiment of the application, this sets
Standby includes the one or more machine readable medias 710 for being stored with machine readable instructions and the place for executing machine readable instructions
Manage device 720, wherein when the machine readable instructions are executed by the processor so that the equipment is executed based on aforementioned according to this
The method and/or technology scheme of multiple embodiments of application.
In addition, some embodiments of the present application additionally provide a kind of computer-readable medium, it is stored thereon with computer journey
Sequence instruct, the computer-readable instruction can be executed by processor multiple embodiments to realize aforementioned the application method and/
Or technical solution.
It should be noted that the application can be carried out in the assembly of software and/or software and hardware, for example, can adopt
With application-specific integrated circuit (ASIC), general purpose computer or any other realized similar to hardware device.In one embodiment
In, the software program of the application can be executed by processor to realize above step or function.Similarly, the software of the application
Program (including relevant data structure) can be stored in computer readable recording medium storing program for performing, for example, RAM memory, magnetic or
CD-ROM driver or floppy disc and similar devices.In addition, hardware can be used to realize in some steps or function of the application, for example,
Coordinate to execute the circuit of each step or function as with processor.
It is obvious to a person skilled in the art that the application is not limited to the details of above-mentioned exemplary embodiment, Er Qie
In the case of without departing substantially from spirit herein or essential characteristic, the application can be realized in other specific forms.Therefore, no matter
From the point of view of which point, the present embodiments are to be considered as illustrative and not restrictive, and scope of the present application is by appended power
Profit requires rather than above description limits, it is intended that all by what is fallen within the meaning and scope of the equivalent requirements of the claims
Variation is included in the application.Any reference signs in the claims should not be construed as limiting the involved claims.This
Outside, it is clear that one word of " comprising " is not excluded for other units or step, and odd number is not excluded for plural number.That is stated in device claim is multiple
Unit or device can also be realized by a unit or device by software or hardware.The first, the second equal words are used for table
Show title, and does not represent any particular order.
Claims (17)
1. a kind of public sentiment data method for visualizing, wherein this method includes：
Acquire public sentiment data；
Determine the emotional category and temporal information of every public sentiment data；
According to the emotional category and temporal information of the public sentiment data, determines and belong to target emotional category in each preset time period
Public sentiment data quantity, and obtain the keyword for the public sentiment data for belonging to target emotional category in each preset time period；
According to the quantity for the public sentiment data for belonging to target emotional category in each preset time period, generate about each preset time
The visualized graphs of section, and corresponding keyword is added in the visualized graphs.
2. according to the method described in claim 1, wherein it is determined that the emotional category of every public sentiment data, including：
According to the content of every public sentiment data, the emotional category of every public sentiment data is identified and marked, wherein the emotional category
Including positive emotion and negative emotion.
3. according to the method described in claim 1, wherein it is determined that the temporal information of every public sentiment data, including：
If including issuing time in public sentiment data, the issuing time is determined as to the temporal information of the public sentiment data；
If not including issuing time in public sentiment data, by according to the time for acquiring the public sentiment data, the public sentiment number is determined
According to temporal information.
4. according to the method described in claim 1, wherein, according to the public sentiment for belonging to target emotional category in each preset time period
The quantity of data generates the visualized graphs about each preset time period, including：
According to the quantity for the public sentiment data for belonging to target emotional category in each preset time period, determine about each preset time
The graphic attribute of the visualized graphs of section；
According to the graphic attribute, the visualized graphs are generated in the display area of target emotional category.
5. according to the method described in claim 4, wherein, according to the public sentiment for belonging to target emotional category in each preset time period
The quantity of data further includes before generating visualized graphs about each preset time period：
Determine visual layout, wherein the visual layout includes at least display area and the visualization of target emotional category
The form of figure.
6. according to the method described in claim 1, wherein, corresponding keyword is added in the visualized graphs, including：
Count the word frequency of the keyword for the public sentiment data for belonging to target emotional category in each preset time period；
According to the word frequency of the keyword, corresponding keyword is added in the visualized graphs in the form of word cloud, wherein
The display size of the keyword is related to the word frequency of the keyword.
7. according to the method described in claim 1, wherein, corresponding keyword is added in the visualized graphs, including：
According to the temporal information of the keyword, location information of the keyword in the visualized graphs is determined, wherein
The temporal information of the keyword is the temporal information of the public sentiment data belonging to the keyword；
According to the positional information, corresponding keyword is added in the corresponding position in the visualized graphs.
8. according to the method described in claim 1, wherein, this method further includes：
Color is added for the visualized graphs and the keyword, wherein the color is corresponding with the visualized graphs
Emotional category is related.
9. a kind of public sentiment data visualization device, wherein the equipment includes：
Data acquisition device, for acquiring public sentiment data；
Data processing equipment, emotional category and temporal information for determining every public sentiment data, and according to the public sentiment number
According to emotional category and temporal information, determine the quantity for the public sentiment data for belonging to target emotional category in each preset time period,
And obtain the keyword for the public sentiment data for belonging to target emotional category in each preset time period；
Data coding device, it is raw for the quantity according to the public sentiment data for belonging to target emotional category in each preset time period
At the visualized graphs about each preset time period, and corresponding keyword is added in the visualized graphs.
10. equipment according to claim 9, wherein the data processing equipment, for according in every public sentiment data
Hold, identifies and mark the emotional category of every public sentiment data, wherein the emotional category includes positive emotion and negative emotion.
11. equipment according to claim 9, wherein the data processing equipment, for including publication in public sentiment data
When the time, the issuing time is determined as to the temporal information of the public sentiment data；And publication is not included in public sentiment data
When the time, by according to the time for acquiring the public sentiment data, the temporal information of the public sentiment data is determined.
12. equipment according to claim 9, wherein the data coding device, for according in each preset time period
Belong to the quantity of the public sentiment data of target emotional category, determines the figure category of the visualized graphs about each preset time period
Property, and according to the graphic attribute, the visualized graphs are generated in the display area of target emotional category.
13. equipment according to claim 12, wherein the data coding device is additionally operable to when according to each default
Between belong in section target emotional category public sentiment data quantity, generate about each preset time period visualized graphs it
Before, determine visual layout, wherein the visual layout includes at least the display area of target emotional category and visualization is schemed
The form of shape.
14. equipment according to claim 9, wherein the data processing equipment is additionally operable to count each preset time period
Inside belong to the word frequency of the keyword of the public sentiment data of target emotional category；
The data coding device, for the word frequency according to the keyword, in the form of word cloud in the visualized graphs
Add corresponding keyword, wherein the display size of the keyword is related to the word frequency of the keyword.
15. equipment according to claim 9, wherein the data coding device, for the time according to the keyword
Information determines location information of the keyword in the visualized graphs, and according to the positional information, it is described can
Add corresponding keyword in corresponding position depending on changing in figure, wherein the temporal information of the keyword is the keyword institute
The temporal information of the public sentiment data of category.
16. equipment according to claim 9, wherein the data coding device, be additionally operable to as the visualized graphs and
The keyword adds color, wherein color emotional category corresponding to the visualized graphs is related.
17. a kind of public sentiment data visualization device, wherein the equipment includes：
Processor；And
One or more machine readable medias of machine readable instructions are stored with, when the processor executes the machine readable finger
When enabling so that the equipment executes such as method described in any item of the claim 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810441355.2A CN108710654B (en) | 2018-05-10 | 2018-05-10 | Public opinion data visualization method and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810441355.2A CN108710654B (en) | 2018-05-10 | 2018-05-10 | Public opinion data visualization method and equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108710654A true CN108710654A (en) | 2018-10-26 |
| CN108710654B CN108710654B (en) | 2021-03-26 |
Family
ID=63868824
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810441355.2A Active CN108710654B (en) | 2018-05-10 | 2018-05-10 | Public opinion data visualization method and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108710654B (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109448728A (en) * | 2018-10-29 | 2019-03-08 | 苏州工业职业技术学院 | Merge the multi-party conversation method for visualizing and system of emotion recognition |
| CN109447050A (en) * | 2018-12-29 | 2019-03-08 | 上海乂学教育科技有限公司 | A kind of Online class user emotion visualization system |
| CN109977278A (en) * | 2019-02-21 | 2019-07-05 | 中国电子科技集团公司第二十八研究所 | Visual presentation system, method, equipment and the storage medium of public sentiment data |
| CN110674300A (en) * | 2019-09-30 | 2020-01-10 | 京东城市(北京)数字科技有限公司 | Method and apparatus for generating information |
| CN111435374A (en) * | 2019-01-11 | 2020-07-21 | 百度在线网络技术（北京）有限公司 | Display device and method for searching statistical data |
| CN112417253A (en) * | 2020-12-28 | 2021-02-26 | 时间知道(北京)文化科技有限公司 | Multi-dimensional public opinion monitoring system and method |
Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101231641A (en) * | 2007-01-22 | 2008-07-30 | 北大方正集团有限公司 | Method and system for automatic analysis of hotspot subject propagation process in the internet |
| US20080215571A1 (en) * | 2007-03-01 | 2008-09-04 | Microsoft Corporation | Product review search |
| CN101408883A (en) * | 2008-11-24 | 2009-04-15 | 电子科技大学 | Method for collecting network public feelings viewpoint |
| CN101751458A (en) * | 2009-12-31 | 2010-06-23 | 暨南大学 | Network public sentiment monitoring system and method |
| US20100223581A1 (en) * | 2009-02-27 | 2010-09-02 | Microsoft Corporation | Visualization of participant relationships and sentiment for electronic messaging |
| CN101894102A (en) * | 2010-07-16 | 2010-11-24 | 浙江工商大学 | Method and device for analyzing emotion tendentiousness of subjective text |
| CN102023967A (en) * | 2010-11-11 | 2011-04-20 | 清华大学 | Text emotion classifying method in stock field |
| CN102546771A (en) * | 2011-12-27 | 2012-07-04 | 西安博构电子信息科技有限公司 | Cloud mining network public opinion monitoring system based on characteristic model |
| CN103077207A (en) * | 2012-12-28 | 2013-05-01 | 深圳先进技术研究院 | Method and system for analyzing microblog happiness index |
| CN103841216A (en) * | 2014-04-01 | 2014-06-04 | 深圳市科盾科技有限公司 | Network public opinion monitoring system based on cloud platform |
| CN104408157A (en) * | 2014-12-05 | 2015-03-11 | 四川诚品电子商务有限公司 | Funnel type data gathering, analyzing and pushing system and method for online public opinion |
| CN105512166A (en) * | 2015-10-30 | 2016-04-20 | 青岛智能产业技术研究院 | Traffic parallel method with mapping between microblog public sentiments and city road conditions |
| CN106649875A (en) * | 2017-01-04 | 2017-05-10 | 成都四方伟业软件股份有限公司 | Visualization system of public opinion big data |
| CN107016107A (en) * | 2017-04-12 | 2017-08-04 | 四川九鼎瑞信软件开发有限公司 | The analysis of public opinion method and system |
| CN107491548A (en) * | 2017-08-28 | 2017-12-19 | 武汉烽火普天信息技术有限公司 | A kind of network public-opinion text message recommends and method for visualizing |
-
2018
- 2018-05-10 CN CN201810441355.2A patent/CN108710654B/en active Active
Patent Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101231641A (en) * | 2007-01-22 | 2008-07-30 | 北大方正集团有限公司 | Method and system for automatic analysis of hotspot subject propagation process in the internet |
| US20080215571A1 (en) * | 2007-03-01 | 2008-09-04 | Microsoft Corporation | Product review search |
| CN101408883A (en) * | 2008-11-24 | 2009-04-15 | 电子科技大学 | Method for collecting network public feelings viewpoint |
| US20100223581A1 (en) * | 2009-02-27 | 2010-09-02 | Microsoft Corporation | Visualization of participant relationships and sentiment for electronic messaging |
| CN101751458A (en) * | 2009-12-31 | 2010-06-23 | 暨南大学 | Network public sentiment monitoring system and method |
| CN101894102A (en) * | 2010-07-16 | 2010-11-24 | 浙江工商大学 | Method and device for analyzing emotion tendentiousness of subjective text |
| CN102023967A (en) * | 2010-11-11 | 2011-04-20 | 清华大学 | Text emotion classifying method in stock field |
| CN102546771A (en) * | 2011-12-27 | 2012-07-04 | 西安博构电子信息科技有限公司 | Cloud mining network public opinion monitoring system based on characteristic model |
| CN103077207A (en) * | 2012-12-28 | 2013-05-01 | 深圳先进技术研究院 | Method and system for analyzing microblog happiness index |
| CN103841216A (en) * | 2014-04-01 | 2014-06-04 | 深圳市科盾科技有限公司 | Network public opinion monitoring system based on cloud platform |
| CN104408157A (en) * | 2014-12-05 | 2015-03-11 | 四川诚品电子商务有限公司 | Funnel type data gathering, analyzing and pushing system and method for online public opinion |
| CN105512166A (en) * | 2015-10-30 | 2016-04-20 | 青岛智能产业技术研究院 | Traffic parallel method with mapping between microblog public sentiments and city road conditions |
| CN106649875A (en) * | 2017-01-04 | 2017-05-10 | 成都四方伟业软件股份有限公司 | Visualization system of public opinion big data |
| CN107016107A (en) * | 2017-04-12 | 2017-08-04 | 四川九鼎瑞信软件开发有限公司 | The analysis of public opinion method and system |
| CN107491548A (en) * | 2017-08-28 | 2017-12-19 | 武汉烽火普天信息技术有限公司 | A kind of network public-opinion text message recommends and method for visualizing |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109448728A (en) * | 2018-10-29 | 2019-03-08 | 苏州工业职业技术学院 | Merge the multi-party conversation method for visualizing and system of emotion recognition |
| CN109447050A (en) * | 2018-12-29 | 2019-03-08 | 上海乂学教育科技有限公司 | A kind of Online class user emotion visualization system |
| CN109447050B (en) * | 2018-12-29 | 2020-08-04 | 上海乂学教育科技有限公司 | Online classroom user emotion visualization system |
| CN111435374A (en) * | 2019-01-11 | 2020-07-21 | 百度在线网络技术（北京）有限公司 | Display device and method for searching statistical data |
| CN111435374B (en) * | 2019-01-11 | 2023-04-25 | 百度在线网络技术（北京）有限公司 | Display device and method for searching statistical data |
| CN109977278A (en) * | 2019-02-21 | 2019-07-05 | 中国电子科技集团公司第二十八研究所 | Visual presentation system, method, equipment and the storage medium of public sentiment data |
| CN110674300A (en) * | 2019-09-30 | 2020-01-10 | 京东城市(北京)数字科技有限公司 | Method and apparatus for generating information |
| CN112417253A (en) * | 2020-12-28 | 2021-02-26 | 时间知道(北京)文化科技有限公司 | Multi-dimensional public opinion monitoring system and method |
| CN112417253B (en) * | 2020-12-28 | 2021-10-15 | 时间知道(北京)文化科技有限公司 | Multi-dimensional public opinion monitoring system and method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108710654B (en) | 2021-03-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108710654A (en) | A kind of public sentiment data method for visualizing and equipment | |
| US9367603B2 (en) | Systems and methods for behavioral segmentation of users in a social data network | |
| AU2010330720B2 (en) | System and method for attentive clustering and related analytics and visualizations | |
| CN102760172B (en) | Network searching method and network searching system | |
| KR101974695B1 (en) | Method and apparatus for displaying recommendation result | |
| KR20160083017A (en) | Systems and methods for identifying influencers and their communities in a social data network | |
| Shen et al. | Nameclarifier: A visual analytics system for author name disambiguation | |
| US10269033B2 (en) | Expanded overlay state for campaign performance data snapshot cards | |
| US20140195950A1 (en) | Gui for viewing and manipulating connected tag clouds | |
| US10304079B2 (en) | Organization of campaign performance data snapshot cards in card feeds and card boards | |
| US10360579B2 (en) | Campaign performance data snapshot cards | |
| US20130138638A1 (en) | Temporal visualization of query results | |
| CN111937027A (en) | Information processing apparatus, information processing method, and information processing program | |
| CN103412958A (en) | Display method and device for searching result | |
| US20170039244A1 (en) | Simplification of sankey diagram | |
| WO2014123929A1 (en) | System and method for classifying a contagious phenomenon propagating on a network | |
| Mahalle et al. | Foundations of data science for engineering problem solving | |
| CN116414854A (en) | Data asset query method, device, computer equipment and storage medium | |
| JP5787924B2 (en) | Cluster forming apparatus, cluster forming method, and cluster forming program | |
| JP5497925B2 (en) | Content management apparatus, content management method and program | |
| CA2941604A1 (en) | System and method for temporal identification of latent communities using electronic content | |
| Müller et al. | A framework for evaluation and exploration of clustering algorithms in subspaces of high dimensional databases | |
| Lui et al. | KANDINSKY: abstract art-inspired visualization of social discussions | |
| VAN HERCK | Visualising Gender Balance | |
| TW202407575A (en) | An editing system used for recommending articles |
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 |