A machine learning-based approach for sentiment analysis on distance learning from Arabic Tweets

Abstract

Social media platforms such as Twitter, YouTube, Instagram and Facebook are leading sources of large datasets nowadays. Twitter’s data is one of the most reliable due to its privacy policy. Tweets have been used for sentiment analysis and to identify meaningful information within the dataset. Our study focused on the distance learning domain in Saudi Arabia by analyzing Arabic tweets about distance learning. This work proposes a model for analyzing people’s feedback using a Twitter dataset in the distance learning domain. The proposed model is based on the Apache Spark product to manage the large dataset. The proposed model uses the Twitter API to get the tweets as raw data. These tweets were stored in the Apache Spark server. A regex-based technique for preprocessing removed retweets, links, hashtags, English words and numbers, usernames, and emojis from the dataset. After that, a Logistic-based Regression model was trained on the pre-processed data. This Logistic Regression model, from the field of machine learning, was used to predict the sentiment inside the tweets. Finally, a Flask application was built for sentiment analysis of the Arabic tweets. The proposed model gives better results when compared to various applied techniques. The proposed model is evaluated on test data to calculate Accuracy, F1 Score, Precision, and Recall, obtaining scores of 91%, 90%, 90%, and 89%, respectively.

Self-Attention-Based Bi-LSTM Model for Sentiment Analysis on Tweets about Distance Learning in Higher Education

“…Three different studies were carried out using machine learning algorithms for analyzing Arabic tweets concerning distance learning in Saudi Arabia. First, Almalki [29] proposed a model that uses Twitter API for collecting 14000 tweets, a regex-based technique for data pre-processing, a logistic regression algorithm [30] for sentiment prediction, and Flask API for getting tweet sentiment. The logistic regression outperformed the others models.…”

Sentiment Analysis of Students’ Feedback on E-Learning Using a Hybrid Fuzzy Model

“…However, accessing and analyzing students' opinions has become simpler, as students nowadays express their feedback on various social media sites. Thus, many researchers exploit social media sites, such as Twitter, to collect feedback and opinions [4].…”

“…Regarding the Arabic sentiment analysis, there are recent studies related to the topic and type of dataset used in this study, i.e., e-learning and Twitter-based data. The authors in [4,10] performed sentiment analyses of general Arabic tweets about e-learning, while the researchers in [11,12] analyzed Twitter datasets about e-learning relating to Saudi Arabia. These studies only focused on using traditional machine learning techniques, such as the naive Bayes and random forest techniques, and traditional feature extraction methods, such as the N-Gram and TF-IDF methods.…”