CN108628994A - A kind of public sentiment data processing system - Google Patents
A kind of public sentiment data processing system Download PDFInfo
- Publication number
- CN108628994A CN108628994A CN201810403516.9A CN201810403516A CN108628994A CN 108628994 A CN108628994 A CN 108628994A CN 201810403516 A CN201810403516 A CN 201810403516A CN 108628994 A CN108628994 A CN 108628994A
- Authority
- CN
- China
- Prior art keywords
- data
- public sentiment
- module
- processing system
- unit
- 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
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a kind of public sentiment data processing system, including acquiring unit, data set unit, data model unit, visualizations；Acquiring unit, for obtaining public sentiment data；Data set unit, for the public sentiment data got according to data criteria for classification, to be built into basic data collection；Data model unit establishes different types of data model using above-mentioned basic data collection；Visualization, for above-mentioned data model to be carried out data visualization processing.A kind of public sentiment data processing system of the present invention, public sentiment data can comprehensively be obtained, compensate for the artificial deficiency for obtaining public sentiment data, due to establishing different types of data model according to basic data collection, it ensure that public sentiment data after treatment levels off to for true public sentiment data, the appearance for avoiding false public sentiment data obtains will of the people data, the social will of the people of grasp and correct guide public opinion to government and provides important data support.
Description
Technical field
The present invention relates to the processing of public sentiment data, more specifically a kind of public sentiment data processing system.
Background technology
" public sentiment " refers to surrounding generation, development and the variation of intermediary social event in certain social space, as
The common people of main body are to as the social governor of object, enterprise, individual and other various organizations and its politics, society, morals etc.
The social attitude that the orientation of aspect generates and holds.It is the more masses about the letter expressed by various phenomenons in society, problem
The summation of thought, attitude, opinion and mood etc. performance.
Currently, the method for obtaining public sentiment data is mainly to obtain the public sentiment that user issues in internet by artificial mode
Information, then by Keyword-method-arit hmetic, into the filtering and screening of row information, then again by artificial mode into row information
Confirm.But with the development of internet, there are a large amount of data in internet, using traditional artificial gathered data mode, shows
So it is difficult to be competent at.Also have through keyword, sensitive word etc., internet mass information is captured automatically, realizes the net of user
Network public sentiment monitors and the information requirements such as Special Topics in Journalism tracking, but does not identify false public sentiment or benefit clusters in internet
The public feelings information deliberately manufactured.
Invention content
It is an object of the invention to overcome the deficiencies of the prior art and provide a kind of public sentiment data processing systems.
To achieve the above object, the present invention uses following technical scheme：A kind of public sentiment data processing system, including obtain single
Member, data set unit, data model unit, visualization；
The acquiring unit, for obtaining public sentiment data；
The data set unit, for the public sentiment data got according to data criteria for classification, to be built into basic data
Collection；
The data model unit establishes different types of data model using above-mentioned basic data collection；
The visualization, for above-mentioned data model to be carried out data visualization processing.
Its further technical solution is：The acquiring unit includes：
Information acquisition module, for collecting the public sentiment source information in internet；
Cleaning module, for being filtered to public sentiment source information, removing processing；
Data warehouse module, for storing treated public sentiment source information；
Data interface module, for transmitting stored public sentiment source information.
Its further technical solution is：The data set unit includes：
Data reception module, for receiving the public sentiment source information stored in data interface module；
Preprocessing module pre-processes the public sentiment source information received, forms complete orderly data set.
Its further technical solution is：Described classifies to receiving data according to different criteria for classifications, classification
Standard includes network behavior standard, behavioral standard, user content preference criteria and customer transaction standard in service.
Its further technical solution is：The data model unit includes：
Subject Clustering module is extracted multiple keywords for being concentrated from basic data, and is clustered out from these keywords
One or more special events；
Event excavates module, for carrying out multiple dimension parsings to a certain object event, obtains the event of the object event
Feature database.
Its further technical solution is：Described extracts multiple keywords for being concentrated from basic data, and is closed from these
One or more special events is clustered out in keyword, the keyword of extraction includes stability maintenance theme, environmental protection, food security.
Its further technical solution is：The Subject Clustering module includes：
Matching module, for carrying out work order matching to the keyword in subject events；
Filtering module, the sample text filtering for being formed after being matched to work order；
Module is checked, for being proofreaded to filtered sample text；
Training module obtains sample set for being trained to sample file by machine learning mode；
Cluster Analysis module forms thematic data collection for being excavated by doing the text subject based on LDA to sample set；
Iteration module, for being iterated optimization processing to obtained thematic data collection.
Its further technical solution is：Described is used to carry out multiple dimension parsings to a certain object event, obtains the mesh
The affair character library of mark event, dimension therein include event body, theme feature, emotional characteristics, time of origin feature, occur
Position feature accepts department.
Its further technical solution is：The visualization includes：
Modeling module, the geometric graphic element for obtained data to be mapped to object；
Rendering module, for depicting geometric graphic element as figure；
Display module, for by showing that equipment shows relational graph.
Its further technical solution is：Further include Service Processing Unit, for being carried out to the data information in data model
Analysis, tracking and prediction.
Compared with the prior art, the invention has the advantages that：A kind of public sentiment data processing system of the present invention, passes through acquisition
Unit, data set unit, data model unit, visualization, after the public sentiment data of acquisition is classified according to criteria for classification,
Formation base data set, then different types of data model is established on basic data collection, and finally will treated public sentiment number
According to intuitively showing.Public sentiment data can be comprehensively obtained, the artificial deficiency for obtaining public sentiment data is compensated for, due to basis
Basic data collection and establish different types of data model, the public sentiment data that ensure that after treatment levels off to for true
Public sentiment data, avoid the appearance of false public sentiment data, will of the people data obtained to government, grasp the social will of the people and correct guiding
Public opinion provides important data and supports.
Above description is only the general introduction of technical solution of the present invention, can in order to better understand technical measure
It is implemented in accordance with the contents of the specification, and in order to make above and other objects of the present invention, feature and advantage brighter
Aobvious understandable, special below to lift preferred embodiment, detailed description are as follows.
Description of the drawings
Fig. 1 is a kind of structure chart of public sentiment data processing system specific embodiment of the present invention；
Fig. 2 is the structure chart of acquiring unit in a kind of public sentiment data processing system specific embodiment of the present invention；
Fig. 3 is the structure chart of data set unit in a kind of public sentiment data processing system specific embodiment of the present invention；
Fig. 4 is the structure chart of data model unit in a kind of public sentiment data processing system specific embodiment of the present invention；
Fig. 5 is the structure chart of Subject Clustering module in a kind of public sentiment data processing system specific embodiment of the present invention；
Fig. 6 is the structure chart of visualization in a kind of public sentiment data processing system specific embodiment of the present invention.
Specific implementation mode
In order to more fully understand the present invention technology contents, with reference to specific embodiment to technical scheme of the present invention into
One step introduction and explanation, but not limited to this.
Referring to Fig. 1, the present invention provides a kind of public sentiment data processing system, which includes acquiring unit 1, data set
Unit 2, data model unit 3, visualization 4；
Acquiring unit 1, for obtaining public sentiment data；
Data set unit 2, for the public sentiment data got according to data criteria for classification, to be built into basic data collection；
Data model unit 3 establishes different types of data model using above-mentioned basic data collection；
Visualization 4, for above-mentioned data model to be carried out data visualization processing.
Referring to Fig. 2, acquiring unit 1 includes：
Information acquisition module 11, for collecting the public sentiment source information in internet；
Cleaning module 12, for being filtered to public sentiment source information, removing processing；
Data warehouse module 13, for storing treated public sentiment source information；
Data interface module 14, for transmitting stored public sentiment source information.
Specifically, including mainly major portal for the public sentiment source information of internet collected by information acquisition module 11
It stands data, the data of government's hot line data and public platform, the mode of acquisition includes Meta Search Engine technology, utilizes universal search engine
The self-defined sources URL and sample frequency, search crawl specific public sentiment source information on internet.The effect of cleaning module 12 is will to receive
The public sentiment source information of collection is filtered, clearly handles, since public sentiment source information has plenty of junk information, it is therefore desirable to filter, have
Data be wrong, it is also desirable to do clear processing.Data warehouse module 13 is for storing filtering, clear public sentiment source letter
Breath.
Referring to Fig. 3, data set unit 2 includes：
Data reception module 21, for receiving the public sentiment source information stored in data interface module 14；
Preprocessing module 22 pre-processes the public sentiment source information received, forms complete orderly data set.Such as
The either simplex data set of composition.
Specifically, classifying according to different criteria for classifications to receiving data, criteria for classification includes network behavior mark
Behavioral standard, user content preference criteria and customer transaction standard in accurate, service.Wherein, network behavior standard includes enlivening people
Number, accesses duration, activity ratio, external contact, social data at page browsing amount.Behavioral standard includes browse path, page in service
The face residence time accesses depth, unique page number of visits.User content preference criteria includes browsing/collection content, in comment
Appearance, interaction content, lifestyle preference, Brang Preference.Customer transaction standard includes contribution rate, visitor's unit price, related rate, turns one's head
Rate, turnover rate.Certainly the data being collected into will not be 100% accurate, all have uncertainty, this just needs the rank below
Section establishes data model further to be judged.For example it is collected into the man that certain user fills out on one column of gender at present, but it is logical
It crosses its Behavior preference and can determine whether that its gender is female, it is therefore desirable to which data module is judged and corrected come further.
Referring to Fig. 4, data model unit 3 includes：
Subject Clustering module 31 is extracted multiple keywords for being concentrated from basic data, and is clustered from these keywords
Go out one or more special events；
Event excavates module 32, for carrying out multiple dimension parsings to a certain object event, obtains the thing of the object event
Part feature database.
Subject Clustering module 31 is to extract multiple keywords for being concentrated from basic data, and clustered from these keywords
Go out one or more special events, the keyword of extraction includes stability maintenance theme, environmental protection, food security.Wherein, food is pacified
The keyword for including entirely has：Food/safety, toxic/food, food and drink/health, food/detection, transgenosis, malicious milk powder, health care
Product, food/pollution, pesticide/vegetables/fruit eat agricultural product, food poisoning.
Further, referring to Fig. 5, Subject Clustering module 31 includes：
Matching module 311, for carrying out work order matching to the keyword in subject events；
Filtering module 312, the sample text filtering for being formed after being matched to work order；
Module 313 is checked, for being proofreaded to filtered sample text；
Training module 314 obtains sample set for being trained to sample file by machine learning mode；
Cluster Analysis module 315 forms thematic data for being excavated by doing the text subject based on LDA to sample set
Collection；
Iteration module 316, for being iterated optimization processing to obtained thematic data collection.
Specifically, Subject Clustering is that many related subjects are clustered out from many keywords first, while also can be according to master
Topic keyword label carries out matching related work order, and accurately whether filtration fraction sample text seen by manually proofreading, pass through machine
Mode of learning, training sample set do the text subject method for digging based on LDA to full dose data set and carry out clustering, formed
Thematic data collection, iteration optimization.Precipitate thematic data collection simultaneously, deeply excavate corresponding theme, it is corresponding comprising annual tendency,
Area's distribution, classical case, intelligent department's distribution etc..
It is for carrying out multiple dimension parsings to a certain object event, obtaining the thing of the object event that event, which excavates module 32,
Part feature database, dimension therein include event body, theme feature, emotional characteristics, time of origin feature, occur position feature,
Accept department.Wherein event body includes that demand people draws a portrait and be resorted people's portrait；Theme feature includes hot word, emotional characteristics packet
Polarity and emotional category are included, polarity is divided into as affirmative or negates, and it is anxious that emotional category can be divided into happiness, anger, grief and joy；Time of origin is special
Sign includes festivals or holidays, working day, morning, the late into the night, morning, the morning, noon, afternoon, evening；It includes that section is false that position feature, which occurs,
Day；The department of accepting includes the administration for industry and commerce, traffic department, environmental protection administration etc..
In other embodiments, data model unit 3 further includes hot word discovery module, and sensor excavates module, opining mining
Module, analysis module of drawing a portrait.
Referring to Fig. 6, visualization 4 includes：
Modeling module 41, the geometric graphic element for obtained data to be mapped to object；
Rendering module 42, for depicting geometric graphic element as figure；
Display module 43, for by showing that equipment shows relational graph.
Visualization is that the intuitive projection of accurate public sentiment data that will be finally obtained comes out, unit related personnel
Check.
In certain embodiments, system further includes Service Processing Unit, for being carried out to the data information in data model
Analysis, tracking and prediction.
For public sentiment data obtained above, public sentiment data can be analyzed according to relevant business rule, analysis master
To include three directions, be ex ante analysis, analysis in progress and ex-post analysis respectively.
Ex ante analysis main purpose is the problem of prediction may occur, in order to initiate processing meaning to corresponding functional department
See, avert risks management and control in advance, and proactive problem occurs.For example, environmental pollution forward prediction, ten big commodity right-safeguarding predictions, hot spot
Prediction.
Analysis in progress is mainly tracking generation problem in thing, understands disposition or track of events details in real time, and to phase
Functional department is answered to initiate handling suggestion, related functional department's follow-up processing promotes service quality, reduces loss.For example, sensitive thing
Part, hot spot occurrences in human life, zone issue is attended a banquet in real time.
Convergence sex chromosome mosaicism is mainly analyzed in ex-post analysis, goes out specialist paper or final report for each special topic, is led for higher level
Lead decision support.For example, hot line treatment effeciency is analyzed, traffic answers efficiency analysis, the analysis of TOPS items, Analysis of Satisfaction.
In summary：A kind of public sentiment data processing system of the present invention, passes through acquiring unit 1, data set unit 2, data mould
Type unit 3, visualization 4, after the public sentiment data of acquisition is classified according to criteria for classification, formation base data set, then
Different types of data model is established on basic data collection, and finally public sentiment data is intuitively shown by treated.Energy
Enough comprehensive acquisition public sentiment datas, compensate for the artificial deficiency for obtaining public sentiment data, due to being established according to basic data collection
Different types of data model ensure that public sentiment data after treatment levels off to for true public sentiment data, avoid
The appearance of false public sentiment data, will of the people data are obtained to government, grasp the social will of the people and it is correct guide public opinion provide it is important
Data are supported.
It is above-mentioned only with embodiment come the technology contents that further illustrate the present invention, in order to which reader is easier to understand, but not
It represents embodiments of the present invention and is only limitted to this, any technology done according to the present invention extends or recreation, by the present invention's
Protection.Protection scope of the present invention is subject to claims.
Claims (10)
1. a kind of public sentiment data processing system, which is characterized in that including acquiring unit, data set unit, data model unit can
Depending on changing unit；
The acquiring unit, for obtaining public sentiment data；
The data set unit, for the public sentiment data got according to data criteria for classification, to be built into basic data collection；
The data model unit establishes different types of data model using above-mentioned basic data collection；
The visualization, for above-mentioned data model to be carried out data visualization processing.
2. a kind of public sentiment data processing system according to claim 1, which is characterized in that the acquiring unit includes：
Information acquisition module, for collecting the public sentiment source information in internet；
Cleaning module, for being filtered to public sentiment source information, removing processing；
Data warehouse module, for storing treated public sentiment source information；
Data interface module, for transmitting stored public sentiment source information.
3. a kind of public sentiment data processing system according to claim 2, which is characterized in that the data set unit includes：
Data reception module, for receiving the public sentiment source information stored in data interface module；
Preprocessing module pre-processes the public sentiment source information received, forms complete orderly data set.
4. a kind of public sentiment data processing system according to claim 1, which is characterized in that it is described to receive data by
Classify according to different criteria for classifications, criteria for classification includes network behavior standard, behavioral standard, user content preference in service
Standard and customer transaction standard.
5. a kind of public sentiment data processing system according to claim 1, which is characterized in that the data model unit packet
It includes：
Subject Clustering module extracts multiple keywords for being concentrated from basic data, and clusters out one from these keywords
Or multiple special events；
Event excavates module, for carrying out multiple dimension parsings to a certain object event, obtains the affair character of the object event
Library.
6. a kind of public sentiment data processing system according to claim 5, which is characterized in that described is used for from basic data
It concentrates and extracts multiple keywords, and cluster out one or more special events from these keywords, the keyword packet of extraction
Include stability maintenance theme, environmental protection, food security.
7. a kind of public sentiment data processing system according to claim 5, which is characterized in that the Subject Clustering module packet
It includes：
Matching module, for carrying out work order matching to the keyword in subject events；
Filtering module, the sample text filtering for being formed after being matched to work order；
Module is checked, for being proofreaded to filtered sample text；
Training module obtains sample set for being trained to sample file by machine learning mode；
Cluster Analysis module forms thematic data collection for being excavated by doing the text subject based on LDA to sample set；
Iteration module, for being iterated optimization processing to obtained thematic data collection.
8. a kind of public sentiment data processing system according to claim 5, which is characterized in that described is used for a certain target
Event carries out multiple dimension parsings, obtains the affair character library of the object event, and dimension therein includes event body, theme spy
Sign, time of origin feature, occurs position feature, accepts department emotional characteristics.
9. a kind of public sentiment data processing system according to claim 1, which is characterized in that the visualization includes：
Modeling module, the geometric graphic element for obtained data to be mapped to object；
Rendering module, for depicting geometric graphic element as figure；
Display module, for by showing that equipment shows relational graph.
10. a kind of public sentiment data processing system according to claim 1, which is characterized in that further include Service Processing Unit,
For the data information in data model to be analyzed, tracked and is predicted.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810403516.9A CN108628994A (en) | 2018-04-28 | 2018-04-28 | A kind of public sentiment data processing system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810403516.9A CN108628994A (en) | 2018-04-28 | 2018-04-28 | A kind of public sentiment data processing system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108628994A true CN108628994A (en) | 2018-10-09 |
Family
ID=63695118
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810403516.9A Pending CN108628994A (en) | 2018-04-28 | 2018-04-28 | A kind of public sentiment data processing system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108628994A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109711613A (en) * | 2018-12-24 | 2019-05-03 | 武汉烽火众智数字技术有限责任公司 | A kind of method for early warning and system based on personnel's relational model and event correlation model |
| CN109992661A (en) * | 2019-03-05 | 2019-07-09 | 广发证券股份有限公司 | A kind of intelligent public sentiment monitoring method and system towards securities industry |
| CN110516038A (en) * | 2019-07-30 | 2019-11-29 | 北京易华录信息技术股份有限公司 | A kind of alert data query method and device |
| CN110838080A (en) * | 2019-11-06 | 2020-02-25 | 上海秒针网络科技有限公司 | Report transmission method and device, storage medium, and electronic device |
| CN111382213A (en) * | 2020-04-02 | 2020-07-07 | 无锡蓝色云湾信息技术有限公司 | Data analysis system combining internet of things and cloud computing technology |
| CN111523856A (en) * | 2020-04-16 | 2020-08-11 | 山东贝赛信息科技有限公司 | Public opinion comprehensive supervision system |
| CN112287186A (en) * | 2020-12-24 | 2021-01-29 | 北京数字政通科技股份有限公司 | Intelligent classification method and system for city management |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103544255A (en) * | 2013-10-15 | 2014-01-29 | 常州大学 | Text semantic relativity based network public opinion information analysis method |
| WO2014123893A1 (en) * | 2013-02-08 | 2014-08-14 | Thomson Licensing | Privacy against interference attack for large data |
| CN104504150A (en) * | 2015-01-09 | 2015-04-08 | 成都布林特信息技术有限公司 | News public opinion monitoring system |
| CN104933093A (en) * | 2015-05-19 | 2015-09-23 | 武汉泰迪智慧科技有限公司 | Regional public opinion monitoring and decision-making auxiliary system and method based on big data |
| CN106326496A (en) * | 2016-09-30 | 2017-01-11 | 广州特道信息科技有限公司 | Cloud platform-based news reading system |
| CN106557558A (en) * | 2016-11-09 | 2017-04-05 | 中国工商银行股份有限公司 | A kind of data analysing method and device |
-
2018
- 2018-04-28 CN CN201810403516.9A patent/CN108628994A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2014123893A1 (en) * | 2013-02-08 | 2014-08-14 | Thomson Licensing | Privacy against interference attack for large data |
| CN103544255A (en) * | 2013-10-15 | 2014-01-29 | 常州大学 | Text semantic relativity based network public opinion information analysis method |
| CN104504150A (en) * | 2015-01-09 | 2015-04-08 | 成都布林特信息技术有限公司 | News public opinion monitoring system |
| CN104933093A (en) * | 2015-05-19 | 2015-09-23 | 武汉泰迪智慧科技有限公司 | Regional public opinion monitoring and decision-making auxiliary system and method based on big data |
| CN106326496A (en) * | 2016-09-30 | 2017-01-11 | 广州特道信息科技有限公司 | Cloud platform-based news reading system |
| CN106557558A (en) * | 2016-11-09 | 2017-04-05 | 中国工商银行股份有限公司 | A kind of data analysing method and device |
Non-Patent Citations (1)
| Title |
|---|
| 梁超君: ""大数据背景下G政府舆情分析应用研究"", 《中国优秀硕士学位论文全文数据库 社会科学I辑》 * |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109711613A (en) * | 2018-12-24 | 2019-05-03 | 武汉烽火众智数字技术有限责任公司 | A kind of method for early warning and system based on personnel's relational model and event correlation model |
| CN109992661A (en) * | 2019-03-05 | 2019-07-09 | 广发证券股份有限公司 | A kind of intelligent public sentiment monitoring method and system towards securities industry |
| CN110516038A (en) * | 2019-07-30 | 2019-11-29 | 北京易华录信息技术股份有限公司 | A kind of alert data query method and device |
| CN110838080A (en) * | 2019-11-06 | 2020-02-25 | 上海秒针网络科技有限公司 | Report transmission method and device, storage medium, and electronic device |
| CN111382213A (en) * | 2020-04-02 | 2020-07-07 | 无锡蓝色云湾信息技术有限公司 | Data analysis system combining internet of things and cloud computing technology |
| CN111523856A (en) * | 2020-04-16 | 2020-08-11 | 山东贝赛信息科技有限公司 | Public opinion comprehensive supervision system |
| CN112287186A (en) * | 2020-12-24 | 2021-01-29 | 北京数字政通科技股份有限公司 | Intelligent classification method and system for city management |
| CN112287186B (en) * | 2020-12-24 | 2021-03-26 | 北京数字政通科技股份有限公司 | Intelligent classification method and system for city management |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108628994A (en) | A kind of public sentiment data processing system | |
| Barbado et al. | A framework for fake review detection in online consumer electronics retailers | |
| CN110705288A (en) | Big data-based public opinion analysis system | |
| CN103226578A (en) | Method for identifying websites and finely classifying web pages in medical field | |
| CN113010572A (en) | Public digital life scene rule model prediction early warning method based on deep Bayesian network | |
| CN107292744A (en) | Investment Trend analysis method and its system based on machine learning | |
| Ghankutkar et al. | Modelling machine learning for analysing crime news | |
| CN109992704A (en) | A kind of enterprise's public sentiment monitoring system and method based on shot and long term Memory Neural Networks | |
| CN111666499A (en) | Public opinion monitoring cloud service platform based on big data | |
| CN111447575A (en) | Short message pushing method, device, equipment and storage medium | |
| Szymkowiak et al. | Applying market basket analysis to official statistical data | |
| CN110717089A (en) | User behavior analysis system and method based on weblog | |
| Al-Hagery | Extracting hidden patterns from dates' product data using a machine learning technique | |
| Alazmi et al. | Data mining and visualization of large databases | |
| CN110147482A (en) | Method and apparatus for obtaining burst hot spot theme | |
| Ataman et al. | Determination of Social Media Users' Perceptions About “Black Friday” Activity via Sentiment Analysis | |
| CN106777124B (en) | Semantic knowledge method, apparatus and system | |
| Awad et al. | Analyzing customer reviews on social media via applying association rule | |
| Rupa et al. | Multi-modal deep learning based fusion approach to detect illicit retail networks from social media | |
| Ashayeri et al. | Unraveling energy justice in NYC urban buildings through social media sentiment analysis and transformer deep learning | |
| Gorvankolla et al. | Application of Text Mining in Effective Document Analysis: Advantages, Challenges, Techniques and Tools | |
| Sengupta | Applications of data mining in library & information centres: an overview | |
| Egri et al. | Classifying and Analysing Human–Wildlife Conflicts in India using News Articles | |
| CN105512296A (en) | Webpage difference based webpage analysis method and system | |
| Matsunaga et al. | Data mining applications and techniques: A systematic review |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181009 |
|
| RJ01 | Rejection of invention patent application after publication |