Bridging Emotions and Architecture: Sentiment Analysis in Modern Distributed Systems

2025-03-24

AI Summary

This paper addresses the critical challenge of deeply integrating sentiment analysis with distributed systems, proposing a lightweight distributed training adaptation strategy tailored for NLP tasks. Methodologically, it designs a microservice-based training framework leveraging PyTorch, Horovod, and Apache Spark, and conducts systematic performance–accuracy trade-off evaluations across single-node and distributed configurations on the Twitter-15M and Amazon Reviews datasets. The core contributions are threefold: (1) the first empirical characterization of the interplay among throughput, scalability, and accuracy in distributed sentiment analysis; (2) achieving a 3.2× throughput improvement and 98.7% linear speedup; and (3) maintaining classification accuracy within ±0.3% deviation—significantly outperforming conventional single-node baselines while ensuring robust model fidelity under scale.

Technology Category

• Natural Language Processing: Interpretability, Analysis, and Evaluation of NLP Models
• Machine Learning: Distributed Machine Learning & Federated Learning
• Data Mining & Knowledge Management: Scalability, Parallel & Distributed Systems

Application Category

• Web Mining and Content Analysis: Sentiment analysis and opinion mining
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Sentiment analysis is a field within NLP that has gained importance because it is applied in various areas such as; social media surveillance, customer feedback evaluation and market research. At the same time, distributed systems allow for effective processing of large amounts of data. Therefore, this paper examines how sentiment analysis converges with distributed systems by concentrating on different approaches, challenges and future investigations. Furthermore, we do an extensive experiment where we train sentiment analysis models using both single node configuration and distributed architecture to bring out the benefits and shortcomings of each method in terms of performance and accuracy.

Problem

• Explores sentiment analysis in distributed systems
• Compares single node vs distributed model performance
• Analyzes challenges and future research directions

Innovation

• Sentiment analysis in distributed systems
• Compare single node and distributed architectures
• Evaluate performance and accuracy trade-offs