Dataset Cagub Jakarta 2024

Published: 5 August 2025| Version 1 | DOI: 10.17632/kfg55pby62.1
Contributor:
ricy ardiansyah ricyl

Description

Raw data was downloaded using Python programming with the Twitter API. The data came from Twitter platforms discussing the 2024 Jakarta gubernatorial candidates. A total of 12,099 data points were collected, with the following details for each candidate: • Pramono Anung: December 2024 - January 2025 • Ridwan Kamil: December 2024 - January 2025 • Dharma Pongrekun: December 2024 - January 2025 The data used was collected before the 2024 Jakarta gubernatorial candidates were determined, but the topic of the Jakarta gubernatorial election was already widely discussed on Twitter. The data obtained will be useful for further research as a comparison in determining the results of the Jakarta gubernatorial election, when compared to data from the candidate determination and campaign period, as well as data after the election (actual results).

Files

Steps to reproduce

The data was obtained using the Google Colab programming tool in the Python programming language. A laptop requires a stable internet connection to download the data. The data used is data on the 2024 Jakarta gubernatorial candidates. The keywords used to collect the data were "candidate name," such as Pramono Anung 2024, Ridwan Kamil 2024, and Dharma Pongrekun 2024. Data collection took place in December 2024, with 4,000 entries for each candidate. The resulting data is in CSV format. To obtain positive and negative sentiment labels for each Tweet, we used Transformers machine learning.

Institutions

  • Universitas Ahmad Dahlan

Categories

Data Mining, Machine Learning, Big Data, Political Campaigning, Sentiment Analysis

Licence