Classifying sentiment in arabic social networks: Na&amp;#x00EF;ve search versus Na&amp;#x00EF;ve bayes

Itani, Maher; Hamandi, Lama; Zantout, Rached; Elkabani, Islam

doi:10.1109/ictea.2012.6462864

Cited by 27 publications

(22 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Authors also highlight the areas where progress is still limited concerning tools development such as translators, tokenisers?, POS taggers, stemmer, vocalisers?, and word disambiguation resolvers. Table 1 Although our source of data is similar to those mentioned in [14, 24, 46 -49], our annotation is similar to that of [11] but adds a 'spam' class. This gives the five classes: negative, positive, spam, dual, and neutral.…”

Section: The Arabic Languagementioning

confidence: 66%

“…Results analysed in [11] show that ~25% of the corpus size is enough to classify the corpus if a lexicon-based classifier is used which means that the remaining 75% is insignificant to a lexicon based classifier as they are nonopinionated words and would not affect the classification.…”

Section: Corpora Charactersitcsmentioning

confidence: 99%

“…Authors in [9,10,11] attempt to partially fill this gap. Arabic resources become scarcer when we consider the sentiment classification of DA text such as that found in social media.…”

Section: Introductionmentioning

confidence: 99%

“…However, to test such classifiers, and in a supervised learning context, the classes of the text used to train and test the classifier is required. The class of each record is specified by 'human classifiers' -native speakers of the language who read the text and label or mark it according to a predetermined set of rules [11]. Such rules require that the human annotators draw upon their own, often tacit, native linguistic knowledge.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Corpora for sentiment analysis of Arabic text in social media

Itani

Roast

Al-Khayatt

2017

2017 8th International Conference on Information and Communication Systems (ICICS)

View full text Add to dashboard Cite

Section: The Arabic Languagementioning

confidence: 66%

Section: Corpora Charactersitcsmentioning

confidence: 99%

“…Authors in [9,10,11] attempt to partially fill this gap. Arabic resources become scarcer when we consider the sentiment classification of DA text such as that found in social media.…”

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Corpora for sentiment analysis of Arabic text in social media

Itani

Roast

Al-Khayatt

2017

2017 8th International Conference on Information and Communication Systems (ICICS)

View full text Add to dashboard Cite

“…In linguistic classification, the sentence is classified based linguistic properties. A naïve search is compared against naïve Bayes for classifying sentiments in Arabic social network [36]. In this research, an application of two different approaches is presented to classify Arabic Facebook posts.…”

Section: Arabic Setiment Classificationmentioning

confidence: 99%

An Evaluation of Sentiment Analysis and Classification Algorithms for Arabic Textual Data

Mostafa¹

2017

IJCA

View full text Add to dashboard Cite

Sentiment analysis is a recent advance in text mining applications for analyzing textual data according to orientation of human comments to determine whether they are positive, negative, or neutral. Different data mining techniques and algorithms such as support vector machine, naïve Bayes, decision tree, k-nearest neighbor and other techniques are used for analyzing textual data. These techniques are evaluated based on Arabic language due to its richness and diversity that can lead to difficulties in analyzing and mining large number of morphological and linguistic words that can lead to different meaning. This research provides sophisticated categorization of most or all recent articles according to the algorithms used in analyzing sentiment data. A comparison table for the proposed algorithms is presented that explains each algorithm and its use in mining and analysis of Arabic textual data and provides different evaluation for each sentiment analysis and classification algorithm according to different categories such as sentiment type, feature selection, sentiment polarity, domain oriented , data scope and data source, algorithm used in the sentiment analysis or classification, and the best algorithm result during the analysis and mining process. The experimental results explain that support vector machine algorithm presents high accuracy with approximately 77% when compared to other text mining algorithms. Different algorithms of sentiment analysis and classifications are evaluated based on their use in Arabic language which has not been evaluated before.

show abstract

Towards a New Lexicon-Based Features Vector for Sentiment Analysis: Application to Moroccan Arabic Tweets

Garouani

Kharroubi

2022

Lecture Notes in Networks and Systems

View full text Add to dashboard Cite

Classifying sentiment in arabic social networks: Naïve search versus Naïve bayes

Cited by 27 publications

References 4 publications

Corpora for sentiment analysis of Arabic text in social media

Corpora for sentiment analysis of Arabic text in social media

An Evaluation of Sentiment Analysis and Classification Algorithms for Arabic Textual Data

Towards a New Lexicon-Based Features Vector for Sentiment Analysis: Application to Moroccan Arabic Tweets

Contact Info

Product

Resources

About