A Framework for Sentiment Analysis of Telugu Tweets

G Balakrishna Priya, ,M Usha Rani

doi:10.35940/ijeat.f1602.089620

Abstract

Now a day Social Media like Facebook, twitter and Instagram is major Sources for people to share their emotions based on the current situations in society. By knowing the interesting patterns in it, a government/appropriate person for that situation can take good and useful decisions. Sentiment analysis is a method where people can extract the useful information from the text like the emotions (happy, sad, and neutral) of people. Much research work was been underdoing in the area of sentiment analysis. Among that work the Machine learning and Deep learning approaches plays a maximum role. Existing works on sentiment analysis is going in the English language. In this paper, proposed a novel framework that specifically designed to do sentiment analysis of the text data, that available in the telugu language. The proposed framework was integrated with the word embedding model Word2Vec, language translator and deep learning approaches like Recurrent Neural Network and Navie base algorithms to collect and analyse the sentiment in tweeter data that present in telugu language. The results shows effective in terms of accuracy, precision and specificity.

Highlights

Sentiment analysis is a method to identify the polarity in the text document
With the development of technologies like web, the huge textual data is available in the internet, which consists of the historical, news, science and political from the major social media websites like twitter and face book [1]
The framework consists of a steps Tweets, Word embed tool, Language Translator and deep learning algorithms

Summary

INTRODUCTION

Sentiment analysis is a method to identify the polarity in the text document. The polarity may be a negative, positive and neutral. To determine the thoughts of a person opinion mining or sentiment analysis is used This can be done in sentence level, document level and future levels in terms of positive, negative and Neutral [2]. Market Analyst will develop the products by analysing the reviews of the product given by the Customer, that which helps to know the strategy of the market To do this the Natural language processing, machine learning and deep learning approaches can be used [4]. Tweets are collected from the twitter by using the API keys of the twitter account and obtained the results in terms of the Accuracy, precision, F-Score and Recall with the polarities like negative, positive and neutral [4]. Experiment analysis was done for the word embed tool Word2vec in the bangala language [10]

PROPOSED FRAMEWORK

RESULTS AND DISCUSSIONS

CONCLUSION AND FUTURE WORK