Mulki, HalaHaddad, HatemGridach, MouradBabaoglu, İsmail2021-12-132021-12-132019978-1-950737-32-1https://hdl.handle.net/20.500.13091/101357th Annual Meeting of the Association-for-Computational-Linguistics (ACL) / 4th Arabic Natural Language Processing Workshop (WANLP) -- JUL 28-AUG 02, 2019 -- Florence, ITALYArabic sentiment analysis models have employed compositional embedding features to represent the Arabic dialectal content. These embeddings are usually composed via ordered, syntax-aware composition functions and learned within deep neural frameworks. With the free word order and the varying syntax nature across the different Arabic dialects, a sentiment analysis system developed for one dialect might not be efficient for the others. Here we present syntax-ignorant n-gram embeddings to be used in sentiment analysis of several Arabic dialects. The proposed embeddings were composed and learned using an unordered composition function and a shallow neural model. Five datasets of different dialects were used to evaluate the produced embeddings in the sentiment analysis task. The obtained results revealed that, our syntax-ignorant embeddings could outperform word2vec model and doc2vec both variant models in addition to hand-crafted system baselines, while a competent performance was noticed towards baseline systems that adopted more complicated neural architectures.eninfo:eu-repo/semantics/closedAccessConference Object2-s2.0-85096607823