Sentiment Analysis and Topic Modeling of Twitter Conversations in Indonesia's 2024 Presidential Election
Hastuti, Harry Fajar Maulana, Eko Satria · Jurnal Pekommas · 2025
The 2024 Indonesian presidential election has garnered significant attention owing to the increasing influence of social media on public perceptions of political leaders and information exchange. This study aimed to analyse the online discourse surrounding three prominent Indonesian presidential candidates: Anies Baswedan, Prabowo Subianto, and Ganjar Pranowo. Utilising sentiment analysis, frequency analysis, and the Latent Dirichlet Allocation (LDA) algorithm, this study examines conversations on social media platforms, focusing on word frequency, sentiment, subjects, and entities that emerge in the discussions. The findings reveal that Prabowo Subianto is the most frequently mentioned candidate, followed by Anies Baswedan, and Ganjar Pranowo. Sentiment analysis indicated a predominantly neutral to slightly positive sentiment across conversations. The LDA topic analysis uncovered distinct campaign focuses for each candidate, with Anies emphasising local issues and debates, Prabowo concentrating on national discourse and defense policy, and Ganjar discussing national concerns, justice, and progress. Named Entity Recognition (NER) highlights the prominence of entities such as "Indonesia”, "Prabowo”, and "Pilpres2024" in online discussions. This study underscores the crucial role of social media in shaping public opinion and provides valuable insights into the online narratives of presidential candidates. These findings contribute to a deeper understanding of the dynamics of digital elections and offer guidance for political analysts and academics in navigating the evolving landscape of online political discourse in Indonesia.