Sentiment Analysis on Moroccan Dialect based on ML and Social Media Content Detection

Abstract

As technology continues to evolve, humans tend to follow suit, and currently social media has taken place as the defacto method of communication. As it tends to happen with verbal communication, people express their opinions in written form and through an analysis of their words, one can extract what an individual wants from a product, a topic, or an event. By looking at the emotions expressed in such content, governments, businesses, and people can learn a lot that can help them improve their strategies. Therefore, in this study, we will use different algorithms to improve the Moroccan sentiment classification. The first step is to gather and prepare Moroccan Dialectal Arabic Twitter comments. Then, a lot of different combinations of extraction (n-grams) and weighting schemes (BOW/ TF-IDF) and word embedding for feature construction are applied to get the best classification models. We used Naive Bayes, Random Forests, Support Vector Machines, and Logistic regression and LSTM to classify the data we prepared. Our machine learning approach, which incorporates sentiment analysis, was designed to analyze Twitter comments written in Modern Standard Arabic or Moroccan Dialectal Arabic. As a final benchmark of our paper, we were simply a sliver shy away from the 70% mark in our accuracy by relying on the SVM algorithm. Although not a game-changing result, this was enough to encourage us to continue developing our model further.

Sentiment Analysis from Texts Written in Standard Arabic and Moroccan Dialect Based on Deep Learning Approaches

“…Recent studies look to expand sentiment analysis to cover the breadth of Moroccan linguistic diversity, tackling both Arabic and Latin scripted dialects [9]. Methodologies include different algorithms, such as Naive Bayes and Random Forests, for classifying sentiment in social media content, with one study showing the utility of multiple classifiers in analyzing Twitter comments [10]. In the context of Arabic social media text processing, there are specific challenges due to the diglossia nature of the language, use of roman script, and code-switching [11].…”

“…Errami et al [10] addressed the sentiment analysis of Moroccan dialect using machine learning techniques and social media content. They curated a dataset of Moroccan dialect tweets and applied a range of preprocessing steps before employing various machine learning models, including SVM, NB, and RF to classify the tweets across sentiment classes.…”

Comparative Analysis of Classification Methods in Sentiment Analysis: The Impact of Feature Selection and Ensemble Techniques Optimization

“…On the other hand, sentiment analysis faces the challenge of complexity in interpreting large and diverse text data (Krishna, 2023;Suhaimin, 2023). In this context, classification is at the heart of sentiment analysis, as it allows the sorting of opinions into different categories (positive, negative, neutral), offering a clearer and more structured view of public sentiment (Errami, 2023;Hung, 2023;Lasri, 2023;G. Li, 2023).…”