Authors - Anita Anand, Shivangi Surati Abstract - Artificial intelligence has transformed the predictive analysis of electoral processes by enabling a deeper understanding of candidates' preferences and behaviors through digital data. This study aimed to develop and compare deep learning models for sentiment analysis based on aspects of Ecuadorian electoral opinions. The Cross-Industry Standard Process for Machine Learning methodology was adopted. A dataset of Spanish-language comments collected from YouTube and Twitter, associated with presidential candidates, was constructed. Three classification architectures were implemented: BETO, BETO with Long Short-Term Memory (LSTM), and BETO with Bidirectional LSTM (BiLSTM). The results show that the hybrid architecture BETO with BiLSTM achieves the best performance, with an F1-score of 84.51% and precision of 85.09%, surpassing the other architectures and reaching levels comparable to international studies that employ BERT and hybrid models in political analysis. This model was integrated into an interactive dashboard that allows users to visualize the distribution of positive, neutral, and negative sentiment by candidate, making it a valuable tool for analyzing digital public opinion trends in Ecuador. Future work includes incorporating data balancing techniques, expanding the volume and time frame of comments, integrating demographic and geographic variables, and exploring more advanced models based on transformers and Large Language Models.
Open Zoom