Applications and Challenges of Sentiment Analysis in Real-life Scenarios

TL;DR

This paper reviews the applications of sentiment analysis in real-world domains like health, social policy, e-commerce, and digital humanities, highlighting key challenges such as privacy and dataset bias.

Contribution

It provides a comprehensive overview of how sentiment analysis is applied across various fields and discusses the main challenges faced in real-life implementations.

Findings

Deep learning is widely used in sentiment analysis applications.

Privacy and dataset bias are major challenges across applications.

Real-world applications require addressing domain-specific issues.

Abstract

Sentiment analysis has benefited from the availability of lexicons and benchmark datasets created over decades of research. However, its applications to the real world are a driving force for research in SA. This chapter describes some of these applications and related challenges in real-life scenarios. In this chapter, we focus on five applications of SA: health, social policy, e-commerce, digital humanities and other areas of NLP. This chapter is intended to equip an NLP researcher with the `what', `why' and `how' of applications of SA: what is the application about, why it is important and challenging and how current research in SA deals with the application. We note that, while the use of deep learning techniques is a popular paradigm that spans these applications, challenges around privacy and selection bias of datasets is a recurring theme across several applications.