A Perspective Study on Mining Techniques for Sentiment Analysis

Abstract

In the past 20 years, the landscape of social media has undergone substantial growth, emerging as a prominent platform that attracts a substantial and diverse audience. Within this digital realm, a wealth of opinionated content is disseminated, comprising various forms of data, including emails, user feedback, tweets, posts, pins, web content, and textual information such as product sentiments. The influx of this unstructured data across multiple domains has spurred the demand for data mining. Data mining, in turn, allows for the identification of valuable patterns within this vast and unstructured dataset. An area of considerable interest in the field of Natural Language Processing (NLP) is sentiment analysis, wherein the sentiments expressed in text are analyzed.

In this context, this study not only provides a concise overview of social networking platforms but also conducts an in-depth examination of the methodologies and tools employed in sentiment analysis. Furthermore, potential limitations are scrutinized, paving the way for opportunities to advance research in the future.