Exploratory Analysis for Big Social Data Using Deep Network
Exploratory analysis is an important way to gain understanding and find unknown relationships from various data sources, especially in the era of big data. Traditional paradigms of social science data analysis follow the steps of feature selection, modeling, and prediction. In this paper, we propose...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2019-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8643028/ |
| _version_ | 1818924291401449472 |
|---|---|
| author | Chao Wu Guolong Wang Jiangcheng Zhu Piyawat Lertvittayakumjorn Simon Hu Chilie Tan Hong Mi Yadan Xu Jun Xiao |
| author_facet | Chao Wu Guolong Wang Jiangcheng Zhu Piyawat Lertvittayakumjorn Simon Hu Chilie Tan Hong Mi Yadan Xu Jun Xiao |
| author_sort | Chao Wu |
| collection | DOAJ |
| description | Exploratory analysis is an important way to gain understanding and find unknown relationships from various data sources, especially in the era of big data. Traditional paradigms of social science data analysis follow the steps of feature selection, modeling, and prediction. In this paper, we propose a new paradigm that does not require feature selection so that data can speak for itself without manually picking out features. Besides, we propose using the deep network as a methodology to explore previously unknown relationships and capture complexity and non-linearity between target variables and a large number of input features for big social data. The new paradigm tends to be a relatively generic approach that can be widely used in different scenarios. In order to validate the feasibility of the paradigm, we use country-level indicators forecasting as a case study. The process includes: 1) data collection and preparation and 2) modeling and experiment. The data collection and preparation part builds a data warehouse and conducts the extract-transform-load process to eliminate data format inconsistency. The modeling and experiment part includes model setup and model structures change to achieve relatively high accuracy on prediction results at both model level and case level. We find some patterns about network capacity modification and the influence of time interval difference on the test results, whereas both of them deserve further research. |
| first_indexed | 2024-12-20T02:23:00Z |
| format | Article |
| id | doaj.art-27b879b996c04d138f301945d6c38d6d |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-20T02:23:00Z |
| publishDate | 2019-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-27b879b996c04d138f301945d6c38d6d2022-12-21T19:56:46ZengIEEEIEEE Access2169-35362019-01-017214462145310.1109/ACCESS.2019.28982388643028Exploratory Analysis for Big Social Data Using Deep NetworkChao Wu0Guolong Wang1https://orcid.org/0000-0003-4905-6040Jiangcheng Zhu2Piyawat Lertvittayakumjorn3Simon Hu4Chilie Tan5Hong Mi6Yadan Xu7Jun Xiao8School of Public Affairs, Zhejiang University, Hangzhou, ChinaSchool of Public Affairs, Zhejiang University, Hangzhou, ChinaCollege of Control Science and Technology, Zhejiang University, Hangzhou, ChinaData Science Institute, Imperial College London, London, U.K.ZJU-UIUC Institute, International Campus, Zhejiang University, Haining, ChinaTongdun Technology, Hangzhou, ChinaSchool of Public Affairs, Zhejiang University, Hangzhou, ChinaInternational Campus, Zhejiang University, Haining, ChinaCollege of Computer Science and Technology, Zhejiang University, Hangzhou, ChinaExploratory analysis is an important way to gain understanding and find unknown relationships from various data sources, especially in the era of big data. Traditional paradigms of social science data analysis follow the steps of feature selection, modeling, and prediction. In this paper, we propose a new paradigm that does not require feature selection so that data can speak for itself without manually picking out features. Besides, we propose using the deep network as a methodology to explore previously unknown relationships and capture complexity and non-linearity between target variables and a large number of input features for big social data. The new paradigm tends to be a relatively generic approach that can be widely used in different scenarios. In order to validate the feasibility of the paradigm, we use country-level indicators forecasting as a case study. The process includes: 1) data collection and preparation and 2) modeling and experiment. The data collection and preparation part builds a data warehouse and conducts the extract-transform-load process to eliminate data format inconsistency. The modeling and experiment part includes model setup and model structures change to achieve relatively high accuracy on prediction results at both model level and case level. We find some patterns about network capacity modification and the influence of time interval difference on the test results, whereas both of them deserve further research.https://ieeexplore.ieee.org/document/8643028/Data-drivennew paradigmsocial science |
| spellingShingle | Chao Wu Guolong Wang Jiangcheng Zhu Piyawat Lertvittayakumjorn Simon Hu Chilie Tan Hong Mi Yadan Xu Jun Xiao Exploratory Analysis for Big Social Data Using Deep Network IEEE Access Data-driven new paradigm social science |
| title | Exploratory Analysis for Big Social Data Using Deep Network |
| title_full | Exploratory Analysis for Big Social Data Using Deep Network |
| title_fullStr | Exploratory Analysis for Big Social Data Using Deep Network |
| title_full_unstemmed | Exploratory Analysis for Big Social Data Using Deep Network |
| title_short | Exploratory Analysis for Big Social Data Using Deep Network |
| title_sort | exploratory analysis for big social data using deep network |
| topic | Data-driven new paradigm social science |
| url | https://ieeexplore.ieee.org/document/8643028/ |
| work_keys_str_mv | AT chaowu exploratoryanalysisforbigsocialdatausingdeepnetwork AT guolongwang exploratoryanalysisforbigsocialdatausingdeepnetwork AT jiangchengzhu exploratoryanalysisforbigsocialdatausingdeepnetwork AT piyawatlertvittayakumjorn exploratoryanalysisforbigsocialdatausingdeepnetwork AT simonhu exploratoryanalysisforbigsocialdatausingdeepnetwork AT chilietan exploratoryanalysisforbigsocialdatausingdeepnetwork AT hongmi exploratoryanalysisforbigsocialdatausingdeepnetwork AT yadanxu exploratoryanalysisforbigsocialdatausingdeepnetwork AT junxiao exploratoryanalysisforbigsocialdatausingdeepnetwork |