View Profile Page
Azza Abugharsa
Linguistics Adjunct, Linguistics
- Email:
- abugharsaa@montclair.edu
- vCard:
- Download vCard
Profile
Dr. Abugharsa has a Ph.D. in TESL and Linguistics from Oklahoma State University in 2014. She has a Master's degree in Computational Linguistics from Montclair State University in 2022. In addition, She has publications in English and Arabic, and she is currently working on her third book. She focuses her research on developing deep learning models relevant to metaphor detection from Arabic poetry in addition to using machine learning models to generate new Arabic poems.
Specialization
Figurative language in NLP, machine learning, Arabic NLP
Second language teaching and theories
Usage-based theory
Onto-genetical language learning
Discourse analysis
Office Hours
Fall
- Monday
- 8:00 am - 9:00 am
- Mondays and Thursdays (Schmitt Hall, 241N)
Research Projects
Metaphor Detection in Poems in Misurata Arabic Sub-Dialect: An LSTM Model
The project focuses on metaphor detection in poems written in the Misurata Arabic sub-dialect spoken in Misurata. The model applied is built on the Long Short-Term Memory (LSTM) architecture. The results show that the model outperforms the output provided by the human annotators and scores a higher score of 79%. In addition, the model scores an 80.7% accuracy score in predicting metaphors from unseen blind data.
Sentiment Analysis in Poems in Misurata Sub-dialect
The tools used to detect sentiment from the Arabic poems dataset are Sklearn as well as the Mazajak sentiment tool. Logistic Regression, Random Forest, Naive Bayes (NB), and Support Vector Machines (SVM) classifiers are used with Sklearn, while the Convolutional Neural Network (CNN) is implemented with Mazajak. The results show that the traditional classifiers score a higher level of accuracy as compared to Mazajak which is built on an algorithm that includes deep learning techniques.
A Discourse Analysis of English-Arabic Cross-Culture Interactions between Arabic Speaking Mother and English Speaking Daughter
Conversational cooperation requires mutual comprehension of speakers’ intentions which underlie the linguistic level of utterances. By applying these findings to an ESL setting, it follows that ESL learning requires using the usage-based approach to reinforce communicative competence in addition to learning the grammar of the language