ANALISIS VOLATILITAS HARGA BITCOIN TERHADAP SENTIMEN BERITA DI MEDIA SOSIAL

• SYAWALLUDDIN
• RANGGA SIDIQ ENDRASMOYO
• 2025

---

Abstract

This study investigates the relationship between social media sentiment and Bitcoin price volatility using advanced natural language processing techniques. We collected X data from April 10-29, 2025, analyzing cryptocurrency-related tweets alongside Bitcoin price movements obtained through the CoinGecko API. Five sentiment analysis methodologies were comparatively evaluated: VADER, TextBlob, BERTweet, RoBERTa Base, and RoBERTa Large. Bitcoin price volatility was measured using log returns to capture market fluctuations accurately. Correlation analysis revealed significant differences in methodological effectiveness. Traditional lexicon-based approaches (VADER and TextBlob) demonstrated weak correlations with volatility (r = -0.2232 and r = -0.0710 respectively). Transformer-based models showed superior performance, with RoBERTa Large achieving the strongest correlation (r = 0.4569, p = 0.0428), representing the only statistically significant relationship. The positive correlation indicates that increased social media sentiment corresponds to higher Bitcoin price volatility rather than directional price movements. These findings demonstrate that sophisticated deep learning models can effectively capture sentiment-driven market dynamics, providing valuable insights for cryptocurrency investors, trading platforms, and market analysts seeking to understand social media influence on digital asset markets.

 

Keywords: Bitcoin; X Sentiment; Volatility; Pearson Correlation; Deep Learning

 

Abstrak

Penelitian ini menginvestigasi hubungan antara sentimen media sosial dan volatilitas harga Bitcoin menggunakan teknik natural language processing yang canggih. Kami mengumpulkan data X dari 10-29 April 2025, menganalisis tweet terkait cryptocurrency bersamaan dengan pergerakan harga Bitcoin yang diperoleh melalui API CoinGecko. Lima metodologi analisis sentimen dievaluasi secara komparatif: VADER, TextBlob, BERTweet, RoBERTa Base, dan RoBERTa Large. Volatilitas harga Bitcoin diukur menggunakan log returns untuk menangkap fluktuasi pasar secara akurat. Analisis korelasi mengungkapkan perbedaan signifikan dalam efektivitas metodologi. Pendekatan lexicon-based tradisional (VADER dan TextBlob) menunjukkan korelasi lemah dengan volatilitas (r = -0,2232 dan r = -0,0710). Model transformer menunjukkan performa superior, dengan RoBERTa Large mencapai korelasi terkuat (r = 0,4569, p = 0,0428), merepresentasikan satu-satunya hubungan yang signifikan secara statistik. Korelasi positif menunjukkan bahwa peningkatan sentimen media sosial berkorelasi dengan volatilitas harga Bitcoin yang lebih tinggi daripada pergerakan harga terarah. Temuan ini mendemonstrasikan bahwa model deep learning yang sophisticated dapat secara efektif menangkap dinamika pasar yang digerakkan sentimen, memberikan wawasan berharga bagi investor cryptocurrency, platform trading, dan analis pasar yang berusaha memahami pengaruh media sosial pada pasar aset digital.

 

Kata Kunci: Bitcoin; Sentimen X; Volatilitas; Korelasi Pearson; Deep Learning

https://repository.bsi.ac.id/repo/69130/ANALISIS-VOLATILITAS-HARGA-BITCOIN-TERHADAP--SENTIMEN-BERITA-DI-MEDIA-SOSIAL
Anda dapat membaca file tugas akhir ini di repository.