Sentiment Analysis of Arabic Slang Comments on  Facebook

Soliman, Taysir Hassan A.; Elmasry, Mohamed; Hedar, Abdel-Rahman; Doss, M. M.

doi:10.24297/ijct.v12i5.2917

Cited by 39 publications

(20 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…"SVM is robust in high dimensional feature spaces, works very good if any feature is relevant, data is linearly separable and most text categorization problems are considered as linearly separable" [1,30]. It is very remarkable that SVM is superior to many other machine learning techniques [1,13,15,18,19,20,21].…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Investigation of the Feature Selection Problem for Sentiment Analysis in Arabic Language

Nasser¹,

Dincer²,

Sever³

2016

RCS

View full text Add to dashboard Cite

Sentiment analysis, which is also known as opinion mining, can be defined as the process of the automatic detection of the attitude of an author towards a certain subject in textual contents. In this study we design and implement a document-level supervised sentiment analysis system for Arabic context and investigate its performance. We use three different feature extraction methods in order to generate three different datasets (unigrams, bigrams and trigrams) from the Opinion Corpus for Arabic (OCA). In order to find the optimal number of features and to obtain the best time performance in sentiment analysis, we employ two feature ranking methods (Information Gain based and Chi-Square based) and calculate the score of each feature with respect to the class labels. This feature ranking step selects only the features that are relevant to the class labels and removes the irrelevant features that cause unnecessary processing. Hence, it helps to increase the classification performance and reduce the processing time. Finally, we evaluate the performance of three standard classifiers for polarity on the previously generated unigram and bigram based data sets, namely Support Vector Machines, K-Nearest Neighbor and Decision Tree, known by their effectiveness over these types of datasets. In our study SVM classifier has showed superior classification performance compared to the other two classifiers. Our experimentation results also prove the effectiveness of the two feature selection methods we use in order to reduce the feature space of the generated datasets and provide higher classification performance.

show abstract

Section: Discussionmentioning

confidence: 99%

“…In [20] a sentence level supervised SA approach was presented. The dataset was collected from Arabic news websites such as Al Jazeera, BBC Arabic, Al-Youm Al-Sabe'a and Al Arabiya, Constitution Facebook Page, and People's Opinion Facebook page.…”

Section: Related Workmentioning

confidence: 99%

Investigation of the Feature Selection Problem for Sentiment Analysis in Arabic Language

Nasser¹,

Dincer²,

Sever³

2016

RCS

View full text Add to dashboard Cite

show abstract

“…Soliman et al (11) proposed a semantic-based method along with SVM classifier for slang Arabic sentiment analysis. Since most of the social network contains informal Arabic words or slang idioms thus, the authors have used a specific lexicon for the slang Arabic terms.…”

Section: Keowreuantrmentioning

confidence: 99%

A Hybrid Method of Linguistic and Statistical Features for Arabic Sentiment Analysis

AL-Jumaili

2020

Baghdad Sci.J

View full text Add to dashboard Cite

Sentiment analysis refers to the task of identifying polarity of positive and negative for particular text that yield an opinion. Arabic language has been expanded dramatically in the last decade especially with the emergence of social websites (e.g. Twitter, Facebook, etc.). Several studies addressed sentiment analysis for Arabic language using various techniques. The most efficient techniques according to the literature were the machine learning due to their capabilities to build a training model. Yet, there is still issues facing the Arabic sentiment analysis using machine learning techniques. Such issues are related to employing robust features that have the ability to discriminate the polarity of sentiments. This paper proposes a hybrid method of linguistic and statistical features along with classification methods for Arabic sentiment analysis. Linguistic features contains stemming and POS tagging, while statistical contains the TF-IDF. A benchmark dataset of Arabic tweets have been used in the experiments. In addition, three classifiers have been utilized including SVM, KNN and ME. Results showed that SVM has outperformed the other classifiers by obtaining an f-score of 72.15%. This indicates the usefulness of using SVM with the proposed hybrid features.

show abstract

“…In general Arabic is divided into three types: Classical Arabic, Modern Arabic, and Colloquial Arabic. As the official language of 22 countries, there are 49 million Arab users of Facebook [7]. Arabic language is a high complex language, which embeds five critical challenges for Natural Language Processing (NLP) task,1) Arabic is not a case-sensitive language; it has no capital letters.…”

Section: Introductionmentioning

confidence: 99%

“…5) Arabic resources, such as corpora, gazetteers, and NLP tools, are not free [9]. Existing Facebook sentiment analysis focus on the English language but very few focuses on Arabic slang comments [7]. It is classified into many regional forms in the Middle East [10], which are Arabian Peninsula Arabic (Khaliji Arabic), Syro-Palestinian Arabic, Egyptian Arabic and Maghrebi Arabic.…”

Section: Introductionmentioning

confidence: 99%

Sentiment Analysis of Arabic Tweets in Sudanese Dialect

Abdelhameed¹,

Hernández²

2019

International Journal of New Technology and Research

View full text Add to dashboard Cite

Sentiment analysis is the field of science that deals with extracting opinions embedded in human oral or written speech. In this paper we focus on sentiment analysis of Arabic tweets written using either Modern Standard Arabic or Sudanese dialectical Arabic. We have created our own lexicon which contain 2500 words and we have applied three different classifiers on the dataset namely; Support Vector Machine (SVM), Naive Bayes (NB) and K-Nearest Neighbor (K-NN), to classify the tweets based on its polarity into positive or negative. We evaluate our work by four different measures which are Precision, Recall, Accuracy and F-measure. The results show that, SVM achieved the best Recall, Accuracy and F-measure and it equals 95.1%, 76.5% and 84.4% respectively. While NB achieved best Precision and it equals to 85.1%.

show abstract

Sentiment Analysis of Arabic Slang Comments on Facebook

Cited by 39 publications

References 12 publications

Investigation of the Feature Selection Problem for Sentiment Analysis in Arabic Language

Investigation of the Feature Selection Problem for Sentiment Analysis in Arabic Language

A Hybrid Method of Linguistic and Statistical Features for Arabic Sentiment Analysis

Sentiment Analysis of Arabic Tweets in Sudanese Dialect

Contact Info

Product

Resources

About