Team 8 : Detecting the Approval Rating of Political Actors Tweets

 Computational Social Science

Detecting the

Approval Rating of

Political Actors Tweets

September 4, 20XX

Introduction

Surveys of political opinions and, more specifically, the approval of political players have the potential to be supplemented by social media platforms like Twitter. However, fresh questions about the validity and reliability of social-media-based estimations have arisen. Measuring public opinion accurately and without systematic errors is as vital for a functioning democracy as it is for scholars to understand society. Survey methodologists have developed techniques over several decades to precisely quantify public opinion. The major goal is to analyze the tweets, posts on famous political actors on twitter,facebook or any social media platform and rank them based on the approval rating.


Methods & Findings

  • We created a google form to conduct the survey to find out the opinion of people on most acknowledged political actors in our domain.

  • The main aim of this data collection was to find the 8-10 political actors who are liked by the majority of people.

  • Then analyze the tweets and work on their approval ratings.







Survey Snaps

Forms response chart. Question title: Which 3 are you top Indian political leaders according to you?. Number of responses: 52 responses.

Tweet Analysis

For this we used elevated access to the twitter api, we accumulated the tweets of political actors,as those accumulated tweets were in various indian languages so we used google translator API for the purpose


Analysis Methods

In our work we focus on the specific case of stance detection, closely related to TS, which is the task of inferring whether a document is written in favor or against the given target.


We use Linear SVM-based method (SVM-SD) trained on a stance-annotated tweet corpus with character and word n-grams.


We use a large collection of tweets containing keywords relevant to the political actor, weakly labeled based on the presence of certain keywords or hashtags.


SVM-SD is fine-tuned through five-fold cross validation and grid search


The model is trained with SemEval 2016 Stance Dataset.


The hyperparameter C was tuned to 100 and the training time was 1053 seconds.

Analysis Results


Relationship between increasing training data and performance
(Mean Macro F1)


Future Work

We would like to analyze the geographic diversity in the approval ratings.

We would also try to get better training datasets and train on different models for better results.

We will extrapolate this code to access posts from other social media websites as well.

Comments

Post a Comment

Popular posts from this blog

23: Understanding the discourses around CAA NRC

Image
About CAA - NRC The Citizenship (Amendment) Act, 2019 aims to facilitate grant of citizenship to migrants belonging to Hindu, Sikh, Buddhist, Jain, Parsi or Christian communities from Pakistan, Bangladesh and Afghanistan who entered into India on or before 31st December, 2014 (1). It was enacted by the Government of India on 12 December, 2019. This particular move by the government of India sparked nationwide protests against CAA and the National Register of Citizens (NRC). The NRC is the official record of all the legal citizens of India. The main reason for the protests was the exclusion of Muslims and other communities who fled from the same or neighboring countries along with refugees from Sri Lankan Tamils in India, Rohingyas from Myanmar, and Tibetan refugees (4).  Due to the widespread national and overseas unrest from this act, it became a very important event in Indian history. Therefore, this led to an extensive media coverage in India. Furthermore, detailed accounts of t...
Read more

Archaeological Data Analysis on Harappan Civilization

Image
  Introduction Deriving conclusions from historical datasets is one of the hardest problems historians have to solve. The problems include verifying information, deriving correlations, and defending conclusions. The complexity of the problem results in increased time for a solution.  Through this project, we have proposed an accurate and faster way of concluding new inferences from historical data. This methodology primarily has 4 parts 1. Collecting and preprocessing the dataset 2. Analysing data using modern machine learning techniques. 3. Validate results using existing Information 4. Derive conclusions To showcase the working of the proposed methodology we have designed an experiment, in which we have derived cultural and economical relationships between ancient cities of the Indus valley civilization. Project Description Experimentation Data Collection (https://github.com/sidgupta2205/CSS_Project/tree/descriptors/Data) In the first phase, we worked on research and knowled...
Read more

14 : Misinformation Spread in Social Networks

Image
  Misinformation Spread in Social Networks Problem Statement In the Information Age, social networking sites have become a notable agent for the spread of misinformation, fake news, and propaganda. Misinformation on social media spreads quickly in comparison to traditional media because of the lack of regulation and examination required before posting. These sites provide users with the capability to spread information quickly to other users without requiring the permission of a gatekeeper such as an editor who might otherwise require confirmation of the truth before allowing publication. A 2018 study of Twitter determined that, compared to accurate information, false information spread significantly faster, deeper, and more broadly.  In this study, we aim to better understand misinformation flows in social networks. Related Work The spread of misinformation has been an ongoing research topic for some time now but before understanding the spread of misinformation, we need a cl...
Read more