Machine Learning for Sentimental Analysis of Gun Control on Twitter

This presentation discusses the use of machine learning for sentimental analysis of gun control on Twitter. It covers data collection, pre-processing, classification, summary, and visualization of the results. The study shows the need for stricter gun control measures to avoid future incidents like the Sandy Hook school shooting.

Gun Control

Introduction
 Violence related to gun has become a complex matter and it is accountable for a massive
populace of the violent incidents.
 In December 2012 a heavily armed young man having mental illness found right of entry to his
mother’s lawfully possessed guns and gunshot his way into the protected apartment of the Sandy
Hook Elementary School (SHES) in Connecticut, USA.
 The young man had killed approximately 26 people consisting of six adults and twenty kids and
lastly shot himself.
 The mass shooting at Sandy Hook Elementary School led to a heated debate and legislation
regarding gun control across the entire United States.

Cont’
 The incident of mass shooting was primarily based on gun ownership and gun
control with people giving different views advocating for tougher gun control.
 However, the tougher gun control views has been in clash with the America
Constitutional second amendment advocating for the right to hold firearms.

Machine Learning for Sentimental
Analysis
 To realise this, the research paper make use of machine learning sentiment analysis.
 Machine learning illustrate more than 300, 000 tweets made by people in the
United Sates.
 A machine learning system is trained to deduct sentiment information from tweets
that is a tweet which is formulated neutrally, negatively or positively.
 The machine learning is trained to analyse the stance recognition that is when an
individual is against, in favour of or neutral towards a given subject matter and in
this case gun control in the U.S

Why Twitter
 The researcher use Twitter in data collection because it has various advantages
which makes it a significant tool for sentimental analysis.
 Twitter is a free online social media platform that allow users to share messages
freely what is commonly referred to as tweets
 Every tweet is restricted to a specific number of characters.
 Microblogging service Twitter is capable of collecting tweets from individuals
with dissimilar cultural, social and economic settings.

Cont’
 The database of twitter keep on growing each day thus Twitter is an infinite data
resource.
 Twitter is the most ideal microblogging service for gathering and analysing data.
 For the purpose of gun control sentimental analysis and stance recognition Twitter
is the most appropriate for sentiment analysis.

Research questions
1. In the case of this research the researcher will use the following
questions:
2. What is the yearly trend on tweets about gun control?
3. At what frequency does the word “gun control” appear in the tweet over
time?
4. What is the comparison of tweets for pro-gun and anti-gun with and
without emoticons and polarity?

Hypothesis
 H0: The tweet sentiment analysis packages such as TextBlog, nltk, and Scikit
Learn are effective approaches for polarity and subjective analysis.

Methodology
 The procedure for analysing public sentiments about gun control involves various processes by
incorporating machine learning through the following approach:
 data collection
 pre-processes
 Classification
 summaries and
 data visualization.

Data collection
 The raw tweet data is in JSON format is bought from GNIP which is an authorized
third party that resells historical tweets determined by predetermined standards.
 GNIP filter data according to the period, key words as well as the user’s
geographical location.
 In comparison with other alternatives like tradition built web flatterers and
programming the Twitter Streaming API.
 This method is suitable in the sense that it saves time and also offer data in a
consistent structure despite the fact that the tweets have to be purchased.

Pre-processing
 The researcher utilize a file comprising a list of JSON files as well as their local
settings which was found from the GNIP reseller.
 Every JSON file is arranged for a period of ten minutes which covers a huge
amount of data about the gun control tweets.
 The JSON files are analysed to mine the most significant data for the study which
is later on converted into the comma-separated values (CSV) format.

Classification
 At the machine learning phase, the feelings of every tweet is extracted.
 The preparation set of data consists of 5000 tweets which are designated from the
clipped data whereas the outstanding tweets which are remaining for grouping.
 The views of every tweet is physically labelled using three categories that is
neutral, pro-gun, and anti-gun to gain a gold standard set of data.

Summary
 The summary use different calculation to calculate the Pro-Gun Public Sentiment
Scores (PGSS) for comparison.
 The investigator account for geographic and time frame described by g and t
respectively.
 The baseline is denoted in the following manner:
PGSS = positive tweets count (g,t)/ Negative tweets count (g,t)

Cont’
 The PGSS baseline measures the amount of pro-gun tweets against anti-gun
tweets from a set of tweets coming from given state within the specified time
frame.
 All the GPSS scores are normalised between zero and one for purposes of
visualisation.

Visualization
 A web app is created under the gun control context for purposes of data
visualization.
 The researcher will use geographic maps generated using Goggle Charts API and
Motion charts using the googleVis package.
 The applied techniques will present the results ranging from the state, and county
level in addition to daily analysis.
 The geographic map visualizes a sequence of PGPSS outcome. The line graph
exemplify the number of categorised tweets over a specified period.

Modelling
 The researcher used several predictive models using the training set of data found
from machine learning methods such as
 Random Forest (RF)
 Support Vector Machine (SVM)
 Maximum Entropy (ME)
 Boosting and Neutral Network (NN).
 All these machine learning techniques are inbuilt with RTextTools.

Results
 The study’s significant tweets were found from GNIP through supplication of
various filter regulations.
 The standards included key words and phrases like gun, gun violence and firearm
and hashtags like #Gun Control with a range of filters like the source of the tweet,
used and language.
 Pre-processing vital information like dates, tweets as well as geographical
locations were extracted.

Cont’
 A golden training set of data was physically of 5000 tweets was chosen and categorized based on
the following sentiment to the event:
 Neutral: This classification comprised irrelevant information which does no convey pro-gun or
anti-gun sentiment.
 Anti-gun: This are tweets which were in favour of gun control and it was an expression of the
sympathy and atrocity.
 For instance, “We need stricter gun control regulations.”
 Pro-gun: These tweets that were in favour of the freedom to possess guns that is these are
individuals who are against gun control.
 For instance, “The only way to stop a bad person with a gun, is a good person with a gun” and
“gun control cannot help”.

Machine Learning Approaches used to
Analyse Twitter Gun Control
Sentiments

Discussion
 The incident of Sandy Hook school genocide was a distressing as well as tragic incident.
 As a result, the event led to a heated debate about the gun ownership as well as mental health.
 The access to gun by individual who have mental problems is a clear indication of the
recklessness shown by people in possession of firearms.
 The incident exemplify that people in possession of guns do not take a right precautions to
safeguarding these arms but keep at the disposal of any person even kids who do not know how
the ammunition ought to be used

Conclusion
 Sentimental analysis of social media is a significant path of study in the field of natural
language processing.
 The researcher employed Twitter sentiment because it is less number of characters which
make it a more suitable approach for easy analysis of the results.
 The research has shown that is probable to analyse data from social media with the help of
machine learning in a dependable and replicable manner.
 There is need to come up stricter gun control measures to ensure that gun owners keep
their guns safely to avoid future incidents like that experienced at Sandy Hook school.