Sentiment Analysis For Social Media Telugu Language Reviews
Author(s):
Padmaja Tallu, Dr. A. V. Krishna Prasad, Venkataramana Battula
Keywords:
Telugu Sentiment Analysis, Deep Learning, CNN,LSTM,Bidirectional -LSTM,BERT.
Abstract
The process of identifying positive, negative, or neutral sentiment in text is referred to as sentiment analysis. Businesses use this technology to assess brand reputation, gain a better understanding of customer concerns, and detect sentiment in social data. Sentiment analysis in low-resource languages and regional languages has recently emerged as an emerging area in natural language processing as industries encourage customers to express their opinions in regional languages. Telugu, also known as the "Italian of the East" is a Dravidian language spoken by over 82 million people worldwide. While sentiment analysis in English has become extremely common and relatively simple to perform due to the availability of a large volume of annotated data and tools, very little work is done in Telegu. This work primarily focuses on creating annotated data sets from various web sources and evaluating different Deep Learning models using pre-trained word embeddings trained on Telugu data, as well as evaluating state-of-the-art models such as BERT using the Transfer Learning concept. Different Machine Learning models with TFIDF Features were also evaluated on the same Telegu own corpus for comparison purposes. The combined CNN and BiLSTM model performed well, with 88 percent model accuracy.
Article Details
Unique Paper ID: 154432

Publication Volume & Issue: Volume 8, Issue 11

Page(s): 176 - 181
Article Preview & Download


Share This Article

Conference Alert

NCSST-2021

AICTE Sponsored National Conference on Smart Systems and Technologies

Last Date: 25th November 2021

SWEC- Management

LATEST INNOVATION’S AND FUTURE TRENDS IN MANAGEMENT

Last Date: 7th November 2021

Latest Publication

Go To Issue



Call For Paper

Volume 10 Issue 1

Last Date for paper submitting for March Issue is 25 June 2023

About Us

IJIRT.org enables door in research by providing high quality research articles in open access market.

Send us any query related to your research on editor@ijirt.org

Social Media

Google Verified Reviews

Contact Details

Telephone:6351679790
Email: editor@ijirt.org
Website: ijirt.org

Policies

Important Links

Browse Rsearch papers