Lexicon Integrated CNN Models with Attention for Sentiment Analysis

TL;DR

This paper presents a novel CNN-based sentiment analysis model that integrates lexicon embeddings and attention mechanisms, improving performance and interpretability over existing methods on benchmark datasets.

Contribution

It introduces a new CNN architecture combining lexicon embeddings and attention, enhancing sentiment analysis accuracy and efficiency.

Findings

Lexicon embeddings enable smaller word embeddings without sacrificing performance.

Attention mechanism reduces noise from irrelevant words.

Model achieves state-of-the-art or comparable results on benchmark datasets.

Abstract

With the advent of word embeddings, lexicons are no longer fully utilized for sentiment analysis although they still provide important features in the traditional setting. This paper introduces a novel approach to sentiment analysis that integrates lexicon embeddings and an attention mechanism into Convolutional Neural Networks. Our approach performs separate convolutions for word and lexicon embeddings and provides a global view of the document using attention. Our models are experimented on both the SemEval'16 Task 4 dataset and the Stanford Sentiment Treebank, and show comparative or better results against the existing state-of-the-art systems. Our analysis shows that lexicon embeddings allow to build high-performing models with much smaller word embeddings, and the attention mechanism effectively dims out noisy words for sentiment analysis.