Abstract:
Sentiment analysis, a key area in Natural Language Processing (NLP), involves categorizing text data based on its emotional tone-positive, negative, or neutral. With the growing reliance on online interactions, understanding sentiments expressed in text is vital for assessing user opinions, behaviours, and engagement. In peer-to-peer (P2P) networks, where content sharing and decentralized user interaction dominate, sentiment analysis can uncover critical insights into digital relationships and collaborative tendencies. This paper explores sentiment analysis within P2P platforms using the BERT (Bidirectional Encoder Representations from Transformers) algorithm, a state-of-the-art NLP model. Unlike traditional methods, BERT effectively captures contextual and nuanced sentiments, enabling more accurate classification. The methodology includes preprocessing data, extracting embeddings using BERT, and employing fine-tuned models for sentiment categorization. Dimensionality reduction and visualization techniques further reveal patterns, sentiment clusters, and alignment between emotional tones in user interactions. Results demonstrate that BERT-powered sentiment analysis identifies content trends, emotional polarities, and behavioural dynamics in decentralized environments. The research also addresses challenges such as handling diverse content and biases in sentiment interpretation. This study highlights the growing need for advanced sentiment analysis techniques to enhance content profiling, trend forecasting, and user understanding on decentralized platforms, offering valuable implications for businesses and researchers.