Sentiment classification is a widely used technique in natural language processing (NLP). Sentiment classification is referred to as the automated process to identify the opinions of the users from their text and label them as positive, negative, or neutral based on the user-s opinions in their text. Social media networking enables users to share opinions for specific or general content. The sentiment of the user is classified based on their reviews, chats, likes, and dislikes available on their social media.

  Due to the availability of datasets in social media being large, traditional methods for sentiment classification faces difficulty in handling data. The deep learning approach possesses the ability to handle huge datasets and unstructured data. Deep learning with contextual embedding provides the vector representation of the text to reflect its polarity in the specific context. Social media sentiment classification using deep contextual embedding enhances the polarity identification with superior performance.

  • In Natural Language Processing (NLP), sentiment classification is an intellectual notion of disentangling user feelings and emotions.

  • Sentiment analysis from social media imparts accustomed and inclusive information to understand the discernment of people and assist in decision making.

  • Utilizing contextual embedding enriched with deep learning for sentiment classification learns polarity semantic representation from large-scale social media data.

  • The multi-level sentiment enriched word embedding method is evolved to obtain sentiment-specific word representation to analyze word and tweet level polarity.

  • Lately, Deep intelligent contextual embedding has been developed that outperforms state of the art in sentiment classification by employing deep learning and hybrid models.