[Paper Review] Deep Learning for Sentiment Analysis : A Survey

Lei Zhang, Shuai Wang+1 more|arXiv (Cornell University)|Jan 24, 2018

Sentiment Analysis and Opinion Mining5 references50 citations

TL;DR

This paper surveys how deep learning methods are applied to sentiment analysis and summarizes architectures, datasets, and applications.

ABSTRACT

Deep learning has emerged as a powerful machine learning technique that learns multiple layers of representations or features of the data and produces state-of-the-art prediction results. Along with the success of deep learning in many other application domains, deep learning is also popularly used in sentiment analysis in recent years. This paper first gives an overview of deep learning and then provides a comprehensive survey of its current applications in sentiment analysis.

Motivation & Objective

• Provide an overview of deep learning and its impact on sentiment analysis.
• Offer a comprehensive survey of current applications of deep learning to sentiment analysis.
• Discuss common architectures, datasets, tasks, and evaluation practices in the field.

Proposed method

• Review and synthesize existing deep learning approaches used for sentiment analysis.
• Categorize architectures and models commonly used in sentiment tasks.
• Summarize datasets, tasks, and evaluation practices from the literature.

Experimental results

Research questions

• RQ1 What deep learning techniques have been applied to sentiment analysis and how are they categorized?
• RQ2 What datasets and benchmark tasks are commonly used in DL-based sentiment analysis, and what evaluation practices exist?
• RQ3 What are the main trends, challenges, and open issues in applying deep learning to sentiment analysis?

Key findings

• Provides a comprehensive survey of deep learning applications in sentiment analysis.
• Summarizes architectures, models, and components frequently used in sentiment tasks.
• Discusses datasets and evaluation practices common in the literature.
• High-level insights into current trends and potential research directions in DL-based sentiment analysis.