Hong Kong Protests
Presented by: Group 9
Abhijit Kulkarni
Roshni Agrawal
Akanksha Gohil
Prasad Joshi
Rajat Sharma
ABI – Sentimental Analysis
Hong Kong Protests
• It all started with extradition bill
• Initial protests were against this bill
• Fear of losing rights and freedoms as well as the "high degree of
autonomy" atmosphere enjoyed by HK citizens
• Causeway Bay Books and Xiao Jianhua disappearances
• Then people started protesting for immediate independence
from China
• China used twitter trolls to ridicule the protests
• Hong Kong is protesting since 31st March 2019
Objective of Analysis
• General sentiment of the tweets regarding the protest, in particular,
what are these tweets’ stances/opinions towards the central
government in China, Hong Kong administration and police force
• Popularity of hashtags
• Behavior of top users and users in general
Data Source
Twitter:
• Twitter generate a vast amount of data from people around the world on a daily basis on a
variety of topics and consequently represent a key source of information for anyone seeking
to study 21st century society.
• Twitter remains the most popular platform for academic research, as it still provides its data
via a number of Application Programming Interfaces (API).
• The popularity of using Twitter for social media research, both in academia and in industry,
remains high; no other platform has attracted as much attention from academics.
• Also, Hong Kong Protests being an international matter, opinions of people across the world
are taken into consideration while doing analysis of data acquired through twitter.
Data Description
Hashtags used:
#FightForHongKong
#HongKongProtest
Analysis Performed
• Descriptive Statistics in Excel, Tableau
• Word Cloud in Orange for different sentiments
• Sentiment Analysis using orange
• Concordance in orange
• Heat Map in Orange
Descriptive Statistics
Category Count
Total tweets 2000
Number of unique authors 1488
Maximum number of tweets 24 (By @applehahaa)
Maximum number of followers 217927 (of @threadreaderapp)
Maximum number of retweets 9955 (for @maychen)
Missing contents 0
Word Counts
Orange Workflow
Word CloudEntire Data Neutral
NegativePositive
Sentiment Analysis
Total tweets: 2000
Tweets with positive sentiments: 217
Tweets with negative sentiments: 1636
Tweets with neutral sentiments: 142
Average overall sentiment: -0.41476
Heat Map
Concordance
Interpretations
• Overall aggregate sentiment from the analysis is negative which
means negative comments are more.
• In this scenario, we can infer that people’s perception is mostly
against the passing of extradition bill. And the same is conveyed
through protests.
Thank you

Sentiment Analysis on Hong Kong Protest - Using Twitter data

  • 1.
    Hong Kong Protests Presentedby: Group 9 Abhijit Kulkarni Roshni Agrawal Akanksha Gohil Prasad Joshi Rajat Sharma ABI – Sentimental Analysis
  • 2.
    Hong Kong Protests •It all started with extradition bill • Initial protests were against this bill • Fear of losing rights and freedoms as well as the "high degree of autonomy" atmosphere enjoyed by HK citizens • Causeway Bay Books and Xiao Jianhua disappearances • Then people started protesting for immediate independence from China • China used twitter trolls to ridicule the protests • Hong Kong is protesting since 31st March 2019
  • 3.
    Objective of Analysis •General sentiment of the tweets regarding the protest, in particular, what are these tweets’ stances/opinions towards the central government in China, Hong Kong administration and police force • Popularity of hashtags • Behavior of top users and users in general
  • 4.
    Data Source Twitter: • Twittergenerate a vast amount of data from people around the world on a daily basis on a variety of topics and consequently represent a key source of information for anyone seeking to study 21st century society. • Twitter remains the most popular platform for academic research, as it still provides its data via a number of Application Programming Interfaces (API). • The popularity of using Twitter for social media research, both in academia and in industry, remains high; no other platform has attracted as much attention from academics. • Also, Hong Kong Protests being an international matter, opinions of people across the world are taken into consideration while doing analysis of data acquired through twitter.
  • 5.
  • 6.
    Analysis Performed • DescriptiveStatistics in Excel, Tableau • Word Cloud in Orange for different sentiments • Sentiment Analysis using orange • Concordance in orange • Heat Map in Orange
  • 7.
    Descriptive Statistics Category Count Totaltweets 2000 Number of unique authors 1488 Maximum number of tweets 24 (By @applehahaa) Maximum number of followers 217927 (of @threadreaderapp) Maximum number of retweets 9955 (for @maychen) Missing contents 0
  • 8.
  • 9.
  • 10.
    Word CloudEntire DataNeutral NegativePositive
  • 11.
    Sentiment Analysis Total tweets:2000 Tweets with positive sentiments: 217 Tweets with negative sentiments: 1636 Tweets with neutral sentiments: 142 Average overall sentiment: -0.41476
  • 12.
  • 13.
  • 14.
    Interpretations • Overall aggregatesentiment from the analysis is negative which means negative comments are more. • In this scenario, we can infer that people’s perception is mostly against the passing of extradition bill. And the same is conveyed through protests.
  • 15.