Discovering Semantic and Sentiment Correlations using Short Informal Arabic Language Text

Abstract

Abstract-Semantic and Sentiment analysis have received a great deal of attention over the last few years due to the important role they play in many different fields, including marketing, education, and politics. Social media has given tremendous opportunities for researchers to collect huge amount of data as input for their semantic and sentiment analysis. Using twitter API, we collected around 4.5 million Arabic tweets and used them to propose a novel automatic unsupervised approach to capture patterns of words and sentences of similar contextual semantics and sentiment in informal Arabic language at word and sentence levels.

A Review on Arabic Sentiment Analysis: State-of-the-Art, Taxonomy and Open Research Challenges

“…In 2017 and 2016, a study was carried out in MSA, which used SVM classifiers [49], [46]. This study was carried out by Alotaibi and Anderson [49], wherein they used the word clustering feature for classifying the Arabic sentiments.…”

“…An accuracy of 96% was noted. In 2016, Alotaibi and Khan [46] carried out another study where they used the SVM classifiers with 5-fold cross-validation, linear regression and unigrams, for carrying out a supervised SA on the Arabic language, at the sentence and document level. All algorithms were used for the data set collected from earlier reviews.…”

“…Mountassir et al [136], [51], [46], [49] focused only on the problems related to the open research, which were based on the method applied for SA (POS, cluster and analysis level) for MSA. The authors used many features like SVM, NB with 5-fold cross-validation, unigrams, and linear algorithm.…”