• Venkataraman Nerellapalli

Emojis can be expressed to show the emotional and sentimental feelings in terms of graphical symbols which can add weightage to the text statement. Emojis have been widely used in social media and chat conversation on both web as well as mobile applications. With usage of emojis, the textual communicating statements will be more expressive & effective. Therefore, it is important to mine the relationship between the text & emoji symbols. By using the advanced machine learning techniques, related emojis can be suggested automatically while understanding the real context of the statement. In this paper, I present a neural network methodology to predict appropriate emoji symbol for a given textual statement and the machine learning model is built by using word vector representations & deep learning frameworks. Model is created by using Global Vector (GloVe) embedding representation, combination of long short-term memory (LSTM) network and convolutional neural network (CNN) and softmax layers. Algorithm is able to generalize and associate words in the test set finds the proper emoji symbol even. The model becomes an accurate classifier mapping from sentences to emoji symbols, even if the words do not appear in the training set

Emojis, LSTM, Deep Learning, Neural Networks, Sentimental Analysis

"Sentimental Analysis – Emoji prediction ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 4, page no.247-249, April-2019, Available :http://www.jetir.org/papers/JETIRAZ06053.pdf

"Sentimental Analysis – Emoji prediction ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 4, page no. pp247-249, April-2019, Available at : http://www.jetir.org/papers/JETIRAZ06053.pdf