Retainable Short Term Memory Based Sentiment Analysis on Trending Data

Abstract

Sentiment analysis on large-scale social media data is important to bridge the gaps between social media contents and real world activities including political election prediction, individual and public emotional status monitoring and analysis, and so on. Although textual sentiment analysis has been well studied based on platforms such as Twitter and Instagram, the analysis of the role of extensive use of emoji in sentiment analysis remains light. In this paper, a novel scheme for Twitter sentiment analysis is proposed with extra attention on emoji. Initially bi-sense emoji embedding under positive and negative sentimental tweets individually, and then find the feature extraction of data using TF_IDF to train a sentiment classifier by attending on these bi-sense emoji embedding with an attention-based long short-term memory network (LSTM). Our experiments show that the bi-sense embedding is effective for extracting sentiment-aware embedding of emoji and outperforms the state-of-the-art models. This paper visualize the attentions to show that the bi-sense emoji embedding provides better guidance on the attention mechanism to obtain a more robust understanding of the semantics and sentiments classified the boosting LSTM algorithm based classified the Twitter data reviews .