Dark Mode
Indonesian Election Candidate Sentiment Dataset
Data Science and Analytics
Tags and Keywords
Trusted By
"No reviews yet"
Free
About
This dataset presents a collection of Twitter data focused on Indonesia's 2024 presidential candidates, including profiles and policy discussions. The raw data was acquired using Python programming with the Twitter API, covering discourse around Ganjar Pranowo, Prabowo Subianto, and Anies Baswedan. This data was collected before the official determination of presidential candidates, yet the topic of the Indonesian presidential election was already widely discussed on the Twitter platform. It is a valuable resource for future research, offering a basis for comparison with election outcomes at various stages, such as during candidate determination, campaign periods, and ultimately, the actual election results.
Columns
- Unnamed: 0.1: An arbitrary index for each record within the dataset.
- Date Created: The precise date and time when the original tweet was posted.
- User ID: A unique identifier for the Twitter user who authored the tweet.
- Followers: The number of followers the Twitter user had at the time the tweet was created.
- Following: The number of accounts the Twitter user was following.
- Tweet Count: The total number of tweets published by the user up to that point.
- TweetLocation: Geographic location information associated with the user's profile or the tweet itself.
- Text: The raw textual content of the tweet.
- tweet_tokens: The tweet text broken down into individual word tokens.
- tweet_tokens_WSW: Tokenised tweet text where common stop words have been removed.
- tweet_normalized: A standardised version of the tweet text, often for consistent processing.
- tweet_tokens_stemmed: The word tokens from the tweet, reduced to their linguistic root forms.
- label: A sentiment classification assigned to the tweet, typically indicating a positive or negative tone.
Distribution
The dataset is typically structured in a tabular format, such as CSV files. It contains a total of approximately 30,000 data records. The dataset is organised into three main directories: original data, cleaned data, and labelled data, with three files residing in each of these directories. The overall size of the dataset (Version 1) is approximately 41.32 MB. Specific numbers for rows or records beyond the total count are not detailed.
Usage
This dataset is ideally suited for various applications, including:
- Sentiment analysis: Understanding public opinion and sentiment towards presidential candidates.
- Political campaigning: Informing strategies by analysing public discourse and reactions.
- Data mining: Discovering patterns and trends in social media discussions related to elections.
- Machine learning: Developing models for political forecasting, topic modelling, or public perception analysis.
- Academic research: Providing foundational data for studies on Indonesian politics and social media influence in elections.
Coverage
The dataset focuses on the Republic of Indonesia, specifically covering the social media discourse surrounding the 2024 presidential candidates.
- Ganjar Pranowo: Data spans from October 2022 to April 2023.
- Prabowo Subianto: Data was collected from December 2022 to April 2023.
- Anies Baswedan: Data is available from January to April 2023. The information captures the period before the official candidate selections for the election.
License
CC0: Public Domain
Who Can Use It
- Researchers and Academics: Those studying political science, computational social science, and electoral behaviour.
- Data Scientists and Machine Learning Practitioners: Individuals building and evaluating natural language processing (NLP) models, particularly for sentiment analysis.
- Political Analysts and Strategists: Professionals seeking insights into public perception and social media trends affecting political campaigns.
- Organisations involved in Big Data: Entities needing large-scale social media data for analysis or application development.
- Students and Educators: For educational purposes related to data analysis, machine learning, and Indonesian current affairs.
Dataset Name Suggestions
- Indonesia 2024 Presidential Election Twitter Data
- Indonesian Political Candidate Social Media Analysis
- 2024 Indonesia Presidential Aspirations on Twitter
- Indonesian Election Candidate Sentiment Dataset
- Twitter Discourse: Indonesia's 2024 Presidential Race
Attributes
Original Data Source: Indonesian Election Candidate Sentiment Dataset
QUALITY