Feature-level Rating System for Telugu Amazon Customer Reviews using Hybrid XGB-RF Classifier
Author(s): Dr Palli Suryachandra
Authors Affiliations:
Lecturer in Computer Science, Government Degree College
Pattikonda, Andhra Pradesh
Email:chandravj111@gmail.com
DOIs:10.2015/IJIRMF/202508020 | Paper ID: IJIRMF202508020Sentiment Analysis (SA) is the opinion extraction that studies the attitude, sentiments, opinions and emotion of people. The huge number of active users will provide information about their opinions in E-Commerce websites which gives the effective review about products. Various sentiment analysis approaches were presented to classify the sentiments as positive, negative, and neutral. However, the existing methods are not effective and ignore the subtle sentiment classification among various text. But, the supervised learning methods was achieved some satisfactory performance on dimensional sentiment analysis, although they needed multiple labels to train the system, that are cost effective and consumes time for annotation of data. In order to overcome such an issue, proposed an Hybrid XGB-RF (XG Boost-Random Forest) Classifier method for the sentimental analysis of the Amazon telugu reviews. The proposed, Hybrid XGB-RF classifier is used to classify the product reviews and ratings are generated. When the ratings are generated the reviews are categorized as Terrible (1star), Poor (2stars), Average (3stars), Very Good (4stars) and Excellent (5stars).The proposed Feature Level Rating with Hybrid XGB-RF obtained accuracy of 97.22 % better when compared to the existing SentiPhraseNet model that obtained 78% of accuracy.
Dr.Palli Suryachandra (2025); Feature-level Rating System for Telugu Amazon Customer Reviews using Hybrid XGB-RF Classifier, International Journal for Innovative Research in Multidisciplinary Field, ISSN(O): 2455-0620, Vol-11, Issue-8, Pp.160-168. Available on – https://www.ijirmf.com/
[1] Reddy, G.R.R., 2020. Enhancing Sentiment Prediction and Bias Detection for Telugu Language across Multiple Domains using ML and Deep Learning (Doctoral dissertation, International Institute of Information Technology Hyderabad).
[2] Yang, C., Zhang, H., Jiang, B. and Li, K., “Aspect-based sentiment analysis with alternating coattention networks”. Information Processing & Management, 56(3), pp.463-478., 2019
[3] Ali, F., Kwak, D., Khan, P., El-Sappagh, S., Ali, A., Ullah, S., Kim, K.H. and Kwak, K.S., Transportation sentiment analysis using word embedding and ontology-based topic modeling. Knowledge-Based Systems, 174, pp.27-42.,2019.
[4] Diamantini, C., Mircoli, A., Potena, D. and Storti, E., 2019. Social information discovery enhanced by sentiment analysis techniques. Future Generation Computer Systems, 95, pp.816-828.
[5] Rehman, A.U., Malik, A.K., Raza, B. and Ali, W., 2019. A hybrid CNN-LSTM model for improving accuracy of movie reviews sentiment analysis. Multimedia Tools and Applications, 78(18), pp.26597-26613.
[6] Jagdale, R.S., Shirsat, V.S. and Deshmukh, S.N., 2019. Sentiment analysis on product reviews using machine learning techniques. In Cognitive Informatics and Soft Computing (pp. 639-647). Springer, Singapore.
[7] Kumar, S.S., Kumar, M.A., Soman, K.P. and Poornachandran, P., 2020. Dynamic mode-based feature with random mapping for sentiment analysis. In Intelligent systems, technologies and applications (pp. 1-15). Springer, Singapore.
[8] Hasan, A., Moin, S., Karim, A. and Shamshirband, S., 2018. Machine learning-based sentiment analysis for twitter accounts. Mathematical and Computational Applications, 23(1), p.11.
[9] Liang, Z., Du, J. and Li, C., 2020. Abstractive Social Media Text Summarization using Selective Reinforced Seq2Seq Attention Model. Neurocomputing.
[10] Wu, C., Wu, F., Wu, S., Yuan, Z., Liu, J. and Huang, Y., 2019. Semi-supervised dimensional sentiment analysis with variational autoencoder. Knowledge-Based Systems, 165, pp.30-39.
[11]Jonnalagadda, P., Hari, K.P., Batha, S. and Boyina, H., 2019. A rule based sentiment analysis in Telugu. International Journal of Advance Research, Ideas and Innovations in Technology.
[12] Regatte, Y.R., Gangula, R.R.R. and Mamidi, R., 2020, May. Dataset Creation and Evaluation of Aspect Based Sentiment Analysis in Telugu, a Low Resource Language. In Proceedings of The 12th Language Resources and Evaluation Conference (pp. 5017-5024).
[13] Kumar, R.G. and Shriram, R., Sentiment Analysis using Bi-directional Recurrent Neural Network for Telugu Movies.
[14]Bharti, S.K., Naidu, R. and Babu, K.S., 2020. Hyperbolic Feature-based Sarcasm Detection in Telugu Conversation Sentences. Journal of Intelligent Systems, 30(1), pp.73-89.
[15] Garapati, A., Bora, N., Balla, H. and Sai, M., 2019. SentiPhraseNet: An extended SentiWordNet approach for Telugu sentiment analysis.