Nugroho, Athaya Reyhan (2025) Analisis Pengaruh Sentimen Masyarakat Terhadap Prediksi Persentase Keuntungan Saham Dengan Pendekatan Deep Learning. Other thesis, Institut Teknologi Sepuluh Nopember.
![]() |
Text
5027211067-Undegraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 April 2027. Download (3MB) | Request a copy |
Abstract
Pasar modal sebagai sarana investasi jangka panjang memiliki performa yang dipengaruhi berbagai macam faktor, salah satunya yaitu sentimen masyarakat. Penelitian ini fokus pada satu saham yang mengalami kenaikan harga tinggi meskipun memiliki valuasi yang mahal. Studi ini fokus pada analisis pengaruh sentimen masyarakat terhadap kenaikan persentase keuntungan saham tersebut dengan pendekatan deep learning. Untuk melakukan evaluasi terhadap sentimen masyarakat, akan dilakukan analisis sentimen dari data yang didapat di kolom media sosial dan aplikasi sekuritas. Analisis sentimen akan dilakukan dengan menggunakan model BERT. Kemudian, hasil dari analisis sentimen akan diintegrasikan dengan model prediksi persentase keuntungan saham yang menggunakan LSTM. Tujuan dari penelitian ini adalah untuk mengetahui seberapa besar pengaruh sentimen masyarakat terhadap kenaikan harga saham. Pada penelitian ini digunakan metrik MSE dan RMSE untuk menggambarkan besar error dari hasil prediksi model, dan nilai R2 untuk mempermudah interpretasi dari performa model. Dari hasil penelitian didapatkan bahwa model LSTM yang diintegrasikan dengan label sentimen memiliki performa yang lebih baik dengan nilai RMSE 0,402, MSE 0,634, dan R2 sebesar 0,523. Sedangkan model yang tidak diintegrasikan label sentimen memiliki nilai RMSE 0,447, MSE 0,669, dan R2 sebesar 0,523.
===================================================================================================================================
The capital market as a means of long-term investment is often influenced by various factors, one of which is public sentiment. This study focuses on a particular stock that has experienced significant price increases despite its high valuation. The research aims to analyze the impact of public sentiment on this stock's return percetage rise using a deep learning approach. To evaluate public sentiment, sentiment analysis will be conducted using data from social media comments and securities applications. The sentiment analysis will be performed using the BERT model. The results of the sentiment analysis will then be integrated with a stock price prediction model using LSTM. The objective of this research is to determine the extent to which public sentiment affects the rise in stock prices. In this study, MSE and RMSE metrics were used to represent the magnitude of errors in the model's predictions, while the R² value was utilized to facilitate the interpretation of the model's performance. The results of the study indicate that the LSTM model integrated with sentiment score outperforms the non-integrated model, achieving an RMSE of 0.402, MSE of 0.634, and an R² of 0.523. In contrast, the model without sentiment label integration recorded an RMSE of 0.447, MSE of 0.669, and an R² of 0.523.
Item Type: | Thesis (Other) |
---|---|
Uncontrolled Keywords: | deep learning, LSTM, BERT, analisis sentimen, time-series forecasting, deep learning, sentiment analysis |
Subjects: | T Technology > T Technology (General) T Technology > T Technology (General) > T174 Technological forecasting T Technology > T Technology (General) > T57.5 Data Processing |
Divisions: | Faculty of Intelligent Electrical and Informatics Technology (ELECTICS) > Information Technology > 59201-(S1) Undergraduate Thesis |
Depositing User: | Athaya Reyhan Nugroho |
Date Deposited: | 24 Jan 2025 06:47 |
Last Modified: | 24 Jan 2025 06:56 |
URI: | http://repository.its.ac.id/id/eprint/116848 |
Actions (login required)
![]() |
View Item |