IS434 Social Analytics and Applications
Project Report
Team Members:
JOEL YAP WEN-LIANG
LIM JIE MIN
SHAN HUIJIE
ZHANG ZHENGNAN
,Introduction 3
Business Client 3
Business problem 3
Data Analysis 4
4.1 Chinese context 4
4.1.1 Data Collection 4
4.1.1.1 Platform Used and Data Crawling Strategy 4
4.1.1.2. Data Description 4
4.1.2 Data Cleaning and Transformation 5
4.1.3 Limitations 5
4.1.3.1 Limitation of data source 5
4.1.3.1 Limitation of data analysis strategy 6
4.1.4 Technologies, Tools and Methods 6
4.1.5 Analysis & Results 6
4.1.5.1 Degree and Topic of concerns over time 6
4.1.5.2 Sentiments of significant incidents 13
4.1.5.3 Summary of opinions on incidents 14
4.1.5.4 Changes in sentiments over time by analysing significant incidents 16
4.2 English context 18
4.2.1 Data Collection 18
4.2.2 Data Cleaning and Transformation 18
4.2.3 Limitations 18
4.2.4 Technologies, Tools and Methods 19
4.2.4.1 Python Packages 19
4.2.4.2 Word Map 19
4.2.4.3 Sentiment Analysis 21
4.2.4.4 Topic Modelling 22
4.2.4.5 Tableau Visualization 23
4.2.5 Analysis & Results 24
Conclusion 24
Team Contribution 25
Acknowledgements 25
References 26
, COVID-19 and People’s Sentiments
1.Introduction
In Wuhan, China, a pneumonia of unknown cause was reported on 31 December 2019.
Then more people began to be infected, with surprisingly high mortality rates.The culprit was
discovered - a new virus, officially termed COVID-19. On 30 January 2020, the outbreak was
declared a Public Health Emergency of International Concern. By 11 March 2020, the World
Health Organization declared COVID-19 a pandemic, with alarming levels of spread around
the world.
2.Business Client
Our client is Singapore China Cultural Center. China Cultural Center (CCC) is an official
cultural institution overseas which is established by the chinese government. CCC
Singapore aims to introduce Chinese culture to Singapore, and to enhance the
understanding and friendship between the two peoples. It offers a variety of cultural
activities, including lectures and training programs, performances, exhibitions and consulting
sessions.
Since COVID-19 started from China, SCCC is interested to find out what insights can be
obtained from social media sites in both China and Singapore.
3.Business problem
We are investigating the following four dimensions of people’s perceptions surrounding the
COVID-19 outbreak in China and Singapore - groups of people who are concerned (who
care), reasons of concerns (why people care) and discussion topics about COVID-19 (what
are people talking about) with a timeline (when people are concerned).
Project Report
Team Members:
JOEL YAP WEN-LIANG
LIM JIE MIN
SHAN HUIJIE
ZHANG ZHENGNAN
,Introduction 3
Business Client 3
Business problem 3
Data Analysis 4
4.1 Chinese context 4
4.1.1 Data Collection 4
4.1.1.1 Platform Used and Data Crawling Strategy 4
4.1.1.2. Data Description 4
4.1.2 Data Cleaning and Transformation 5
4.1.3 Limitations 5
4.1.3.1 Limitation of data source 5
4.1.3.1 Limitation of data analysis strategy 6
4.1.4 Technologies, Tools and Methods 6
4.1.5 Analysis & Results 6
4.1.5.1 Degree and Topic of concerns over time 6
4.1.5.2 Sentiments of significant incidents 13
4.1.5.3 Summary of opinions on incidents 14
4.1.5.4 Changes in sentiments over time by analysing significant incidents 16
4.2 English context 18
4.2.1 Data Collection 18
4.2.2 Data Cleaning and Transformation 18
4.2.3 Limitations 18
4.2.4 Technologies, Tools and Methods 19
4.2.4.1 Python Packages 19
4.2.4.2 Word Map 19
4.2.4.3 Sentiment Analysis 21
4.2.4.4 Topic Modelling 22
4.2.4.5 Tableau Visualization 23
4.2.5 Analysis & Results 24
Conclusion 24
Team Contribution 25
Acknowledgements 25
References 26
, COVID-19 and People’s Sentiments
1.Introduction
In Wuhan, China, a pneumonia of unknown cause was reported on 31 December 2019.
Then more people began to be infected, with surprisingly high mortality rates.The culprit was
discovered - a new virus, officially termed COVID-19. On 30 January 2020, the outbreak was
declared a Public Health Emergency of International Concern. By 11 March 2020, the World
Health Organization declared COVID-19 a pandemic, with alarming levels of spread around
the world.
2.Business Client
Our client is Singapore China Cultural Center. China Cultural Center (CCC) is an official
cultural institution overseas which is established by the chinese government. CCC
Singapore aims to introduce Chinese culture to Singapore, and to enhance the
understanding and friendship between the two peoples. It offers a variety of cultural
activities, including lectures and training programs, performances, exhibitions and consulting
sessions.
Since COVID-19 started from China, SCCC is interested to find out what insights can be
obtained from social media sites in both China and Singapore.
3.Business problem
We are investigating the following four dimensions of people’s perceptions surrounding the
COVID-19 outbreak in China and Singapore - groups of people who are concerned (who
care), reasons of concerns (why people care) and discussion topics about COVID-19 (what
are people talking about) with a timeline (when people are concerned).
