ISSS608 2017-18 T1 Assign MATILDA TAN YING XUAN

Overview	Data Preparation	Analysis and Results

Introduction

A mysterious illness with flu-like symptoms is spreading in Smartpolis, and the authorities have provided the following information for the deduction of the channel through which the illness is spread, and also whether emergency personnel needs to be deployed outside the affected areas.

Dataset 1 - Microblog entries (1023077 observations)
Variables available:

1) User ID

2) Time post was created

3) Location of user during post (Lat, Long values)

4) Content of post

Dataset 2 - Population Data (13 observations for the thirteen towns)
Variables available:

1) Town name

2) Location of town (Lat, Long values)

3) Population Density

4) Daytime population

Dataset 3 - Weather Data (21 entries for the 21 days in the timeperiod observed)
Variables available:

1) Date

2) Wind direction

3) Average Wind Speed

4) Weather

Tableau workbook

The link to the tableau workbook solution (in the story tab) is as follows:
https://public.tableau.com/views/VisualAnalyticsAssignment-VASTMC12011/Story?:embed=y&:display_count=yes&publish=yes

Resources and acknowledgements

Software used

JMP Pro 13

Tableau Desktop 10.3

Python (for text processing

Books used

Bird, S., Klein,E., Loper,E. (2009) Natural Language Processing with Python. Sebastapol, CA: O Reilly Media

Acknowledgements

thenounproject for the images

Prof Kam for guidance in visual analytics

MITB coursemates Rachel Tong and Fam Guo Teng for the enlightening discussions