Title: Text sentiment analysis from students' comments using various machine learning and deep learning techniques: a comparative analysis

Authors: M. Ameen Chhajro; Kirshan Kumar Luhana; Asif Ali Wagan; Irfan Ali Kandhro

Addresses: Department of Software Engineering, Sindh Madressatul Islam University, Sindh, Pakistan ' Department of Computer Science, University of Sindh, Sindh, Pakistan ' Department of Computer Science, Sindh Madressatul Islam University, Sindh, Pakistan ' Department of Computer Science, Sindh Madressatul Islam University, Sindh, Pakistan

Abstract: The method of analysing text and sentiments from the data is commonly known as sentiment analysis. In this paper, the text-based dataset of students' comments has been considered. This automated model of text sentiment analysis has been trained on various machine learning techniques like random forest, MultinomialNB, and linear SVC. In this paper, we proposed a text sentiment analysis model for evaluating the performance matrix and accuracy of distinct machine learning and deep learning approaches. In this regard, the deep learning techniques that have been incorporated in this research are recurrent neural network (RNN), long short-term memory (LSTM), and gated recurrent unit (GRU), and we compared these techniques with the state-of-the-art algorithms of machine learning, respectively. The experimental result of the proposed model shows that the model architecture was designed and created to easily analyse the sentiments from students' comments in the form of happy, angry, sad, and relaxed. The proposed model of the sentiment analysis approach has been more focused on business firms' customer reviews and comment analysis for future decisions and the development of their businesses.

Keywords: sentiment classification; machine learning; deep learning; recurrent neural network; RNN; long short-term memory; LSTM; gated recurrent unit; GRU.

DOI: 10.1504/IJDATS.2023.136679

International Journal of Data Analysis Techniques and Strategies, 2023 Vol.15 No.4, pp.323 - 338

Received: 31 Oct 2022
Accepted: 06 Sep 2023
Published online: 15 Feb 2024 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article