An Adaptable Scheme to Enhance the Sentiment Classification of Telugu Language

Abstract

Nowadays, the big data is ruling the entire digital world with its applications and facilities. Thus to run the online services in better way some of the machine learning model is utilized, also the machine learning strategy is became a trending field in big data; hence the success of online services or business is based upon the customer reviews. Almost the review contains neutral, positive, and negative sentiment value; this specification is done using natural Language Processing (NLP). Manual classification of sentiment value is a difficult task so that the Natural Language Processing (NLP) scheme is used which is processed using a machine learning strategy. Moreover, the part of Speech Specification for different language is difficult. To overcome this issue, the current research developed a CatBoost machine learning model with Less Error Pruning (LEP)-Shortest Description Length (SDL) and Ant Lion Optimization (MOALO) approach to classify the sentiment values in Telugu reviews. The purpose of using LEP-SDL is to remove unwanted characters and make the classification process easier. Several error removing models are available for machine learning process but those models are ineffective when it comes under to remove the error in Telugu Language, so that LEP-SDL model is developed here. Moreover, the fitness function of ALO is used in the catboost classification module improves the accuracy of sentiment classification. In addition, the proposed approach is implemented using python; the efficiency of the proposed model is compared with recent existing works and achieved better results by attaining high accuracy and precision rate of sentiment classification. The obtained results were justified that the proposed model is applicable for online services or businesses to classify the sentiment rates of each customer.