Real-time Twitter Sentiment Analysis for Moroccan Universities using Machine Learning and Big Data Technologies

Abstract

In recent years, sentiment analysis (SA) has raised the interest of researchers in several domains, including higher education. It can be applied to measure the quality of the services supplied by the higher education institution and construct a university ranking mechanism from social media like Twitter. Hence, this study presents a novel system for Twitter sentiment prediction on Moroccan public universities in real-time. It consists of two phases: offline sentiment analysis phase and real-time prediction phase. In the offline phase, the collected French tweets about twelve Moroccan universities were classified according to their sentiment into ‘positive’, ‘negative’, or ‘neutral’ using six machine learning algorithms (random forest, multinomial Naive Bayes classifier, logistic regression, decision tree, linear support vector classifier, and extreme gradient boosting) with the term frequency-inverse document frequency (TF-IDF) and count vectorizer feature extraction techniques. The results reveal that random forest classifier coupled with TF-IDF has obtained the best test accuracy of 90%. This model was then applied on real-time tweets. The real-time prediction pipeline comprises Twitter streaming API for data collection, Apache Kafka for data ingestion, Apache Spark for real-time sentiment analysis, Elasticsearch for real-time data exploration, and Kibana for data visualization. The obtained results can be used by the Ministry of higher education, scientific research and innovation of Morocco for decision-making process.

Development and Comparison of Multiple Emotion Classification Models in Indonesia Text Using Machine Learning

“…A similar observation was made in the comparison of SVM and Naï ve Bayes on two different datasets including IMDB and Twitter, and the findings showed that SVM performed better with 83% accuracy on IMDB and 82% on Twitter [19]. Moreover, the sentiments of people towards Moroccan universities were assessed using RF, MNB, LR DT, SVM, and XGboost, as well as the results indicated that the highest accuracy at 98% [20]. Another sentiment analysis was also conducted on a marketplace dataset using naï ve Bayes and random forest and the highest accuracy was achieved by Naï ve Bayes at 87% [21].…”

Multilingual sentiment analysis during the pandemic using deep learning models

“…Support vector machines obtained the best results of machine learning methods with an accuracy of 0.986 and F1 value of 0.988. Lasri et al [10] applied six different machine learning methods (Random Forest, multinomial Naive Bayes classifier, Logistic Regression, Decision Tree, Linear Support Vector classifier, and Extreme Gradient Boosting) to classify tweets collected from Twitter about the University of Morocco into three labels (positive, negative, and neutral). The results showed that the accuracy of random forest classifier was up to 90%, and the classification performance was the best among the six machine learning methods.…”

Analysis of Student Performance Applying Data Mining Techniques in a Virtual Learning Environment

“…The prediction models were validated through a confusion matrix and metrics such as accuracy, recall, precision, F1-score, ROC curve, the area under the curve (AUC), and the Kappa coefficient. The definitions and formulas of each metric can be seen in detail in [35] [36]. The most relevant for this study are defined in the next section.…”