Arabic Text Classification using Feature-Reduction Techniques for Detecting Violence on Social Media

This paper presents a comprehensive evaluation of data pre-processing and word embedding techniques in the context of Arabic document classification in the domain of health-related communication on social media. We evaluate 26 text pre-processings applied to Arabic tweets within the process of training a classifier to identify health-related tweets. For this task we use the (traditional) machine learning classifiers KNN, SVM, Multinomial NB and Logistic Regression. Furthermore, we report experimental results with the deep learning architectures BLSTM and CNN for the same text classification problem. Since word embeddings are more typically used as the input layer in deep networks, in the deep learning experiments we evaluate several state-of-the-art pre-trained word embeddings with the same text pre-processing applied. To achieve these goals, we use two data sets: one for both training and testing, and another for testing the generality of our models only. Our results point to the conclusion that only four out of the 26 pre-processings improve the classification accuracy significantly. For the first data set of Arabic tweets, we found that Mazajak CBOW pre-trained word embeddings as the input to a BLSTM deep network led to the most accurate classifier with F1 score of 89.7%. For the second data set, Mazajak Skip-Gram pre-trained word embeddings as the input to BLSTM led to the most accurate model with F1 score of 75.2% and accuracy of 90.7% compared to F1 score of 90.8% achieved by Mazajak CBOW for the same architecture but with lower accuracy of 70.89%. Our results also show that the performance of the best of the traditional classifier we trained is comparable to the deep learning methods on the first dataset, but significantly worse on the second dataset.

show abstract

“…There are several methods of removal for Arabic stop words. Examples of studies that removed stop words are [ 19 , 35 , 93 ].…”

Section: First Experimentsmentioning

confidence: 99%

Investigating the impact of pre-processing techniques and pre-trained word embeddings in detecting Arabic health information on social media

2021

View full text Add to dashboard Cite

show abstract

“…Pedoman PICO sangat berguna dan memudahkan dalam merumuskan pertanyaan penelitian [20]. Tabel Dataset Peneliti Jumlah Twitter [33], [34], [35], [36], [23], [24], [37], [38], [39], [22], [40], [41], [42], [43], [44], [45], [46] 17 Berita berbahasa Arab [28], [47], [48], [49], [27], [25], [50], [51] 8…”

Section: Tahap Pembuatan Rencana Awalunclassified

“…Tabel 6. Analisis Metode Representasi Teks dalam Arabic Natural Language Processing Metode Untuk Representasi Teks Peneliti Jumlah TF-IDF [4], [9], [48], [30], [23], [24], [29], [53], [54], [7], [38], [55], [32], [56], [25], [31], [59], [1], [51], [60] 20 Word2Vec [34], [24], [49], [7], [57], [39], [41], [43], [45], [46] 10 AraVec [34], [35], [37], [40], [41], [42] 6 FastText [34], [47], [35], [57], [41], [42], [50], [46] 8 mBERT [27], [22], [41], [46] 4 AraBERT [36],…”

Section: Tahap Pembuatan Rencana Awalmentioning

confidence: 99%

“…Untuk lebih mempertimbangkan konteks kata dan makna kalimat dapat diatasi dengan dynamic atau contextual embedding yang mempelajari representasi kalimat secara universal [27]. Contextual embedding yang pertama kali diusulkan adalah Embeddings from Language Model (ELMO) [68] [33], [34], [47], [48], [30], [23], [24], [54], [38], [27], [56], [31], [57], [39], [1], [42], [51], [46], [9] 20…”

Section: Tahap Pembuatan Rencana Awalunclassified

See 1 more Smart Citation

Analisis Metode Representasi Teks Untuk Deteksi Interelasi Kitab Hadis: Systematic Literature Review

Ariyanto

fatichah²,

Arifin³

2021

RESTI

View full text Add to dashboard Cite

Hadith is the second source of reference for Islamic law after the Qur'an, which explains the sentences in the Qur'an which are still global by referring to the provisions of the Prophet Muhammad SAW. Classification of text documents can also be used to overcome the problem of interrelation between the Qur'an and hadith. The problem of interrelation between books of hadith needs to be done because some hadiths in certain hadith books have the same meaning as other hadith books. This study aims to analyze the development of text representation and classification methods suitable to overcome similarity meaning problems in detecting interrelationships between hadith books. The research method used is Systematic Literature Review (SLR) sourced from Google Scholar, Science Direct, and IEEE. There are 42 pieces of literature that have been studied successfully. The results showed that contextual embedding as the newest text representation method considered word context and sentence meaning better than static embedding. As a classification method, the ensemble method has better performance in classifying text documents than using only a single classifier model. Thus, future research can consider using a combination of contextual embedding and ensemble methods to detect interrelationships between books of hadith.

show abstract

“…In [54] devised a TC model to detect violence in Arabic tweets using different feature reduction methods. For classification they used KNN, Bayesian boosting, and bagging SVM.…”

Section: Related Workmentioning

confidence: 99%

Impact of Stemming and Word Embedding on Deep Learning-Based Arabic Text Categorization

Almuzaini

Azmi

2020

IEEE Access

View full text Add to dashboard Cite

Document classification is a classical problem in information retrieval, and plays an important role in a variety of applications. Automatic document classification can be defined as content-based assignment of one or more predefined categories to documents. Many algorithms have been proposed and implemented to solve this problem in general, however, classifying Arabic documents is lagging behind similar works in other languages. In this paper, we present seven deep learning-based algorithms to classify the Arabic documents. These are: Convolutional Neural Network (CNN), CNN-LSTM (LSTM = Long Short-Term Memory), CNN-GRU (GRU = Gated Recurrent Units), BiLSTM (Bidirectional LSTM), BiGRU, Att-LSTM (Attention-based LSTM), and Att-GRU. And for word representation, we applied the word embedding technique (Word2Vec). We tested our approach on two large datasets-with six and eight categories-using ten-fold cross-validation. Our objective was to study how the classification is affected by the stemming strategies and word embedding. First, we looked into the effects of different stemming algorithms on the document classification with different deep learning models. We experimented with eleven different stemming algorithms, broadly falling into: root-based and stem-based, and no stemming. We performed ANOVA test on the classification results using the different stemmers, which helps assure if the results are significant. The results of our study indicate that stem-based algorithms perform slightly better compared to root-based algorithms. Among the deep learning models, the Attention mechanism and the Bidirectional learning gave outstanding performance with Arabic text categorization. Our best performance is F -score = 97.96%, achieved using the Att-GRU model with stem-based algorithm. Next, we looked into different controlling parameters for word embedding. For Word2Vec, both skip-gram and bag-of-words (CBOW) perform well with either stemming strategies. However, when using a stem-based algorithm, skipgram achieves good results with a vector of smaller dimension, while CBOW requires a larger dimension vector to achieve a similar performance.

show abstract

Arabic Text Classification using Feature-Reduction Techniques for Detecting Violence on Social Media

Cited by 8 publications

References 22 publications

Investigating the impact of pre-processing techniques and pre-trained word embeddings in detecting Arabic health information on social media

Investigating the impact of pre-processing techniques and pre-trained word embeddings in detecting Arabic health information on social media

Analisis Metode Representasi Teks Untuk Deteksi Interelasi Kitab Hadis: Systematic Literature Review

Impact of Stemming and Word Embedding on Deep Learning-Based Arabic Text Categorization

Contact Info

Product

Resources

About