Wafa Faisal
Publications
Researches on Artificial intelligence AI & Natural Language Processing NLP
Similarities between Arabic Dialects: Investigating Geographical Proximity
NLP - Research paper
This paper sheds light on an unexplored topic: the effects of the geographical proximity of cities located in Arab countries on their dialectical similarity. This research provides an important advancements in Arabic dialect research because it indicates that a more granular approach to dialect classification is essential to understanding how to frame the problem of Arabic dialects identification. Link
COVID-19 vaccine rejection causes based on Twitter people's opinions analysis using Deep Learning
AI- Research paper - Master's thesis
Aim to understand of people’s perceptions of the COVID-19 vaccine to help the organizations and companies who manufacture the vaccine improve their marketing strategy based on the rejection causes. We conducted this study to use Sentiment Analysis to classify people’s opinions from extracted tweets about COVID-19 vaccines into positive, negative, or neutral opinions, using several machine learning classifiers like Logistic Regression,
Stochastic Gradient Descent , Support Vector Machine, K-Nearest Neighbors, Decision Tree, Random Forest, XGBoost and Multinomial Naïve Bayes , and several deep learning models like Recurrent Neural Network (RNN), Long Short Term Memory (LSTM), Gated Recurrent Unit (GRU), RNN-LSTM and RNN-GRU. Then, we analyzed the negative tweets to identify the causes for rejecting the vaccine using topic modeling with Latent Dirichlet Allocation technique. Finally, we classified these negative tweets according to the obtained rejection causes for all the vaccines using the same ML and DL models.
Twitter People’s Opinions Analysis During Covid-19 Quarantine Using Machine Learning and Deep Learning Models
AI - Research paper
Aim to understand and analyze the quarantine impact of coronavirus pandemic (COVID19) on our lives. In fact, we used multiclass Sentiment Analysis to classify people's opinions from extracted tweets about COVID-19 quarantine impact, using different machine learning classifiers such as Support Vector Machine, K-Nearest Neighbors, and Multinomial Naive Bayes and secondly various Deep Learning models such as Recurrent Neural Network and Long Short-Term Memory. Link
Sentiment Analysis of E-learning Tweets during the COVID-19 pandemic using Machine Learning and Deep Learning
AI - Poster competition 🏆✨
First place winner 🥇 in the Women in Data Science (WiDS) poster competition 2021
