Unique ID: 2015060
| Division: | Integration, Analysis, and Research |
|---|---|
| Issue Date: | February 13th 2019 |
| Last modified: | February 22nd 2019 |
Cost: FREE
Use of data from social networks to obtain statistical and geographical information
Use of data from social networks to obtain statistical and geographical information
Exploration of different topics to review the feasibility of using information from Twitter to produce statistical and geographical information
Project Objective:
Exploration, Scientific / research
Project Outcomes:
Indicators on subjective well-being. Mobility maps of people among cities and across borders. Maps showing directions and flows of domestic tourism.
Project Sources
| Type Of Institution: | National statistical office |
|---|---|
| Big Data Source: | Social media data |
| Region: | Latin America & the Caribbean |
| Country Area: | Mexico |
| Id Country Regional: | country |
Partnerships
| Other Partners: | Research or academic institute |
|---|
Accessing Data
| Data Access Rights: | Broader access rights |
|---|
Data Coverage
| Data Coverage: | Only a portion of all data |
|---|---|
| Coverage Geo Pop: | Whole country / high % of market |
| Cost Implication: | Free |
| Coverage Period: | 2014/2015 |
Project Details
| Frequency Comments: | Data with geospatial reference (longitude and latitude) |
|---|
Data Quality
| Quality Aspects Evaluated: | Privacy and Security, Completeness, Usability, Time Factors, Accessibility, Relevance, Validity, Accuracy, including selectivity, Coherence, including linkability to other sources |
|---|---|
| Quality Framework Comments: | No, because big data is a different paradigm. |
| Quality Assessment Comments: | Completeness: we defined and obtained our own data of universe; Accuracy: check against tourism data is good; for subjective well-being data are confronted with those from surveys and we have a consistency of 80% ; Coherence: consistency across time. |
Methodology
| Methods Used: | Supervised learning, Decision Trees, Data visualization methods, Machine learning (Random forest, etc.) |
|---|
Technologies
| Technologies: | Relational database, NoSQL database, Data visualization tools, Hadoop Clusters, Cloud services |
|---|
Other
| Income Level: | Upper-middle-income |
|---|---|
| Iso: | MX |
| Timeframe To Produce Indicator: | NA |
| Frequency Comments: | Data with geospatial reference (longitude and latitude) |
Write Your Own Review