SentiFuse: Deep Multi-model Fusion Framework for Robust Sentiment Extraction

TL;DR

SentiFuse introduces a versatile, model-agnostic framework that effectively combines multiple sentiment analysis models through various fusion strategies, significantly improving accuracy and robustness across diverse social media datasets.

Contribution

It presents a novel unified fusion framework supporting decision, feature, and adaptive fusion, enhancing sentiment analysis performance over individual models and simple ensembles.

Findings

Feature-level fusion improves F1 score by up to 4% over best individual models.

Adaptive fusion increases robustness in complex sentiment cases.

SentiFuse outperforms naive ensemble methods across three large-scale datasets.

Abstract

Sentiment analysis models exhibit complementary strengths, yet existing approaches lack a unified framework for effective integration. We present SentiFuse, a flexible and model-agnostic framework that integrates heterogeneous sentiment models through a standardization layer and multiple fusion strategies. Our approach supports decision-level fusion, feature-level fusion, and adaptive fusion, enabling systematic combination of diverse models. We conduct experiments on three large-scale social-media datasets: Crowdflower, GoEmotions, and Sentiment140. These experiments show that SentiFuse consistently outperforms individual models and naive ensembles. Feature-level fusion achieves the strongest overall effectiveness, yielding up to 4\% absolute improvement in F1 score over the best individual model and simple averaging, while adaptive fusion enhances robustness on challenging cases such as negation, mixed emotions, and complex sentiment expressions. These results demonstrate that systematically leveraging model complementarity yields more accurate and reliable sentiment analysis across diverse datasets and text types.