This is a presentation at SCA2013, Karlsruhe, Germany. This shows the design (architecture, database, sketch, wireframe, prototype) of a simple web-based tool that supports asynchronous collaboration among researchers when conducting content analysis on qualitative social media data.
6. Motivation
Human generated textual data on social media are:
Qualitative Data
requires qualitative interpretation
Large-scale Data
requires large-scale data mining techniques
9. Goal
To build a tool that:
Acquire social media data.
Integrate qualitative content analysis and
data mining techniques to analyze textual
data on social media.
10. Goal
To build a tool that:
Acquire social media data.
Integrate qualitative content analysis and
data mining techniques to analyze textual
data on social media.
Support asynchronous collaboration
among researchers.
11. Existing Tools
Social Media Analytics & Monitoring Tools
Focus on marketing
Do not usually incorporate human input
13. SWAB (Social Web Analytics Buddy)
3
Computation
Server
5
1
Social Media
Content
Web UI
API or
Web Crawler
2
Data Server
4
Web Server
Researchers
14. SWAB (Social Web Analytics Buddy)
3
Computation
Server
5
1
Social Media
Content
Web UI
API or
Web Crawler
2
Data Server
4
Web Server
Researchers
15. SWAB (Social Web Analytics Buddy)
Twitter search API
3
Computation
Server
5
1
Social Media
Content
Web UI
API or
Web Crawler
2
Data Server
4
Web Server
Researchers
16. SWAB (Social Web Analytics Buddy)
MySQL
3
Computation
Server
5
1
Social Media
Content
Web UI
API or
Web Crawler
2
Data Server
4
Web Server
Researchers
17. SWAB (Social Web Analytics Buddy)
MySQL
3
Computation
Server
5
1
Social Media
Content
Web UI
API or
Web Crawler
2
Data Server
4
Web Server
Researchers
18. SWAB (Social Web Analytics Buddy)
MySQL
3
Computation
Server
5
1
Social Media
Content
Web UI
API or
Web Crawler
2
Data Server
4
Web Server
Researchers
19. SWAB (Social Web Analytics Buddy)
MySQL
Classification &
Detection Modeling
Inter-rater Agreement
Computation
3
Computation
Server
5
1
Social Media
Content
Web UI
API or
Web Crawler
2
Data Server
4
Web Server
Researchers
20. SWAB (Social Web Analytics Buddy)
MySQL
3
Computation
Server
5
1
Social Media
Content
Web UI
API or
Web Crawler
2
Data Server
4
Web Server
Researchers
21. SWAB (Social Web Analytics Buddy)
MySQL
3
Computation
Server
Sample tweets for
researchers to analyze
1 Send results
API or
5
Web UI
back to
Web Crawler
data server
Communicate with
Social Media
2 Data
computation server Server
Content
4
Web Server
Researchers
22. SWAB (Social Web Analytics Buddy)
MySQL
3
Computation
Server
5
1
Social Media
Content
Web UI
API or
Web Crawler
2
Data Server
4
Web Server
Researchers
34. Web UI Design
Wireframes: the “Result” tab
All researchers’ results are aggregated in the
background.
Collaboration happens asynchronously.
Reliability measures are computed.
35. Web UI Design
Wireframes: the “Result” tab
Classification models can be trained based on
the qualitative input.
36. Web UI Design
Wireframes: the “Model Application” tab
Apply the trained model to a new dataset
to detect similar data as in dataset1 from
dataset2.
37. Web UI Design
Wireframes: the “Model Application” tab
Choose how to explore the detected
data from the new dataset: view list of
tweets, user accounts, or geomap.
41. Future Work
Design features to better support data
exploration.
Explore NoSQL database to handle large
datasets.
42. Future Work
Design features to better support data
exploration.
Explore NoSQL database to handle large
datasets.
Implement more sophisticated data mining and
visualization features.