Data and code accompanying the paper Politics and Virality in the Time of Twitter

Overview

Politics and Virality in the Time of Twitter

Data and code accompanying the paper Politics and Virality in the Time of Twitter.

In specific:

  • the code used for the training of our models (./code/finetune_models.py and ./code/finetune_multi_cv.py)
  • a Jupyter Notebook containing the major parts of our analysis (./code/analysis.ipynb)
  • the model that was selected and used for the sentiment analysis.
  • the manually annotated data used for training are shared (./data/annotation/).
  • the ids of tweets that were used in our analyis and control experiments (./data/main/ & ./data/control)
  • names, parties and handles of the MPs that were tracked (./data/mps_list.csv).

Annotated Data (./data/annotation/)

  • One folder for each language (English, Spanish, Greek).
  • In each directory there are three files:
    1. *_900.csv contains the 900 tweets that annotators labelled individually (300 tweets each annotator).
    2. *_tiebreak_100.csv contains the initial 100 tweets all annotators labelled. 'annotator_3' indicates the annotator that was used as a tiebreaker.
    3. *_combined.csv contains all tweets labelled for the language.

Model

While we plan to upload all the models trained for our experiments to huggingface.co, currently only the main model used in our analysis can be currently be find at: https://drive.google.com/file/d/1_Ngmh-uHGWEbKHFpKmQ1DhVf6LtDTglx/view?usp=sharing

The model, 'xlm-roberta-sentiment-multilingual', is based on the implementation of 'cardiffnlp/twitter-xlm-roberta-base-sentiment' while being further finetuned on the annotated dataset.

Example usage

from transformers import AutoModelForSequenceClassification, pipeline
model = AutoModelForSequenceClassification.from_pretrained('./xlm-roberta-sentiment-multilingual/')
sentiment_analysis_task = pipeline("sentiment-analysis", model=model, tokenizer="cardiffnlp/twitter-xlm-roberta-base-sentiment")

sentiment_analysis_task('Today is a good day')
Out: [{'label': 'Positive', 'score': 0.978614866733551}]

Reference paper

For more details, please check the reference paper. If you use the data contained in this repository for your research, please cite the paper using the following bib entry:

@inproceedings{antypas2022politics,
  title={{Politics and Virality in the Time of Twitter: A Large-Scale Cross-Party Sentiment Analysis in Greece, Spain and United Kingdom}},
  author={Antypas, Dimosthenis and Preece, Alun and Camacho-Collados, Jose},
  booktitle={arXiv preprint arXiv:2202.00396},
  year={2022}
}
Owner
Cardiff NLP
Research Group in Natural Language Processing at Cardiff University
Cardiff NLP
The repo for mlbtradetrees.com. Analyze any trade in baseball history!

The repo for mlbtradetrees.com. Analyze any trade in baseball history!

7 Nov 20, 2022
NumPy aware dynamic Python compiler using LLVM

Numba A Just-In-Time Compiler for Numerical Functions in Python Numba is an open source, NumPy-aware optimizing compiler for Python sponsored by Anaco

Numba 8.2k Jan 07, 2023
Statistical Rethinking: A Bayesian Course Using CmdStanPy and Plotnine

Statistical Rethinking: A Bayesian Course Using CmdStanPy and Plotnine Intro This repo contains the python/stan version of the Statistical Rethinking

Andrés Suárez 3 Nov 08, 2022
Performance analysis of predictive (alpha) stock factors

Alphalens Alphalens is a Python Library for performance analysis of predictive (alpha) stock factors. Alphalens works great with the Zipline open sour

Quantopian, Inc. 2.5k Jan 09, 2023
Spectacular AI SDK fuses data from cameras and IMU sensors and outputs an accurate 6-degree-of-freedom pose of a device.

Spectacular AI SDK examples Spectacular AI SDK fuses data from cameras and IMU sensors (accelerometer and gyroscope) and outputs an accurate 6-degree-

Spectacular AI 94 Jan 04, 2023
Autopsy Module to analyze Registry Hives based on bookmarks provided by EricZimmerman for his tool RegistryExplorer

Autopsy Module to analyze Registry Hives based on bookmarks provided by EricZimmerman for his tool RegistryExplorer

Mohammed Hassan 13 Mar 31, 2022
Accurately separate the TLD from the registered domain and subdomains of a URL, using the Public Suffix List.

tldextract Python Module tldextract accurately separates the gTLD or ccTLD (generic or country code top-level domain) from the registered domain and s

John Kurkowski 1.6k Jan 03, 2023
💬 Python scripts to parse Messenger, Hangouts, WhatsApp and Telegram chat logs into DataFrames.

Chatistics Python 3 scripts to convert chat logs from various messaging platforms into Pandas DataFrames. Can also generate histograms and word clouds

Florian 893 Jan 02, 2023
Falcon: Interactive Visual Analysis for Big Data

Falcon: Interactive Visual Analysis for Big Data Crossfilter millions of records without latencies. This project is work in progress and not documente

Vega 803 Dec 27, 2022
Maximum Covariance Analysis in Python

xMCA | Maximum Covariance Analysis in Python The aim of this package is to provide a flexible tool for the climate science community to perform Maximu

Niclas Rieger 39 Jan 03, 2023
a tool that compiles a csv of all h1 program stats

h1stats - h1 Program Stats Scraper This python3 script will call out to HackerOne's graphql API and scrape all currently active programs for informati

Evan 40 Oct 27, 2022
Transform-Invariant Non-Negative Matrix Factorization

Transform-Invariant Non-Negative Matrix Factorization A comprehensive Python package for Non-Negative Matrix Factorization (NMF) with a focus on learn

EMD Group 6 Jul 01, 2022
DaDRA (day-druh) is a Python library for Data-Driven Reachability Analysis.

DaDRA (day-druh) is a Python library for Data-Driven Reachability Analysis. The main goal of the package is to accelerate the process of computing estimates of forward reachable sets for nonlinear dy

2 Nov 08, 2021
Clean and reusable data-sciency notebooks.

KPACUBO KPACUBO is a set Jupyter notebooks focused on the best practices in both software development and data science, namely, code reuse, explicit d

Matvey Morozov 1 Jan 28, 2022
Larch: Applications and Python Library for Data Analysis of X-ray Absorption Spectroscopy (XAS, XANES, XAFS, EXAFS), X-ray Fluorescence (XRF) Spectroscopy and Imaging

Larch: Data Analysis Tools for X-ray Spectroscopy and More Documentation: http://xraypy.github.io/xraylarch Code: http://github.com/xraypy/xraylarch L

xraypy 95 Dec 13, 2022
A set of functions and analysis classes for solvation structure analysis

SolvationAnalysis The macroscopic behavior of a liquid is determined by its microscopic structure. For ionic systems, like batteries and many enzymes,

MDAnalysis 19 Nov 24, 2022
nrgpy is the Python package for processing NRG Data Files

nrgpy nrgpy is the Python package for processing NRG Data Files Website and source: https://github.com/nrgpy/nrgpy Documentation: https://nrgpy.github

NRG Tech Services 23 Dec 08, 2022
Feature engineering and machine learning: together at last

Feature engineering and machine learning: together at last! Lambdo is a workflow engine which significantly simplifies data analysis by unifying featu

Alexandr Savinov 14 Sep 15, 2022
Incubator for useful bioinformatics code, primarily in Python and R

Collection of useful code related to biological analysis. Much of this is discussed with examples at Blue collar bioinformatics. All code, images and

Brad Chapman 560 Jan 03, 2023
Fitting thermodynamic models with pycalphad

ESPEI ESPEI, or Extensible Self-optimizing Phase Equilibria Infrastructure, is a tool for thermodynamic database development within the CALPHAD method

Phases Research Lab 42 Sep 12, 2022