Types of Approaches, Applications and Challenges in the Development of Sentiment Analysis Systems

TL;DR

This paper reviews various approaches, applications, and challenges in sentiment analysis, highlighting its importance in extracting insights from large volumes of unstructured web data using NLP and machine learning techniques.

Contribution

It provides a comprehensive overview of sentiment analysis methods, their applications, and the challenges faced in developing effective systems.

Findings

Sentiment analysis enables understanding of public opinion from social media data.

Various approaches include lexicon-based, machine learning, and deep learning methods.

Challenges include handling sarcasm, context, and multilingual data.

Abstract

Today, the web has become a mandatory platform to express users' opinions, emotions and feelings about various events. Every person using his smartphone can give his opinion about the purchase of a product, the occurrence of an accident, the occurrence of a new disease, etc. in blogs and social networks such as (Twitter, WhatsApp, Telegram and Instagram) register. Therefore, millions of comments are recorded daily and it creates a huge volume of unstructured text data that can extract useful knowledge from this type of data by using natural language processing methods. Sentiment analysis is one of the important applications of natural language processing and machine learning, which allows us to analyze the sentiments of comments and other textual information recorded by web users. Therefore, the analysis of sentiments, approaches and challenges in this field will be explained in the following.