Leveraging Sparse and Dense Feature Combinations for Sentiment Classification

TL;DR

This paper introduces a simple yet effective neural network model that combines sparse and dense features for sentiment classification, outperforming many complex models and matching state-of-the-art results.

Contribution

The authors propose a novel combination of sparse and dense features in a neural network for sentiment analysis, emphasizing simplicity and robustness.

Findings

Model outperforms many deep learning approaches

Achieves comparable results to complex architectures

Code is publicly available

Abstract

Neural networks are one of the most popular approaches for many natural language processing tasks such as sentiment analysis. They often outperform traditional machine learning models and achieve the state-of-art results on most tasks. However, many existing deep learning models are complex, difficult to train and provide a limited improvement over simpler methods. We propose a simple, robust and powerful model for sentiment classification. This model outperforms many deep learning models and achieves comparable results to other deep learning models with complex architectures on sentiment analysis datasets. We publish the code online.