Tw-StAR at SemEval-2017 Task 4: Sentiment Classification of Arabic Tweets

Mulki, Hala; Haddad, Hatem; Gridach, Mourad; Babaoğlu, İsmail

doi:10.18653/v1/s17-2110

Cited by 18 publications

(15 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Much of the work on the classification of the regional dialects of Arabic has been mainly based on comparing a small number of dialects using a limited set of linguistic variables. Although Mulki, et al [29] suggested the use of recent clustering technologies and systems in the classification of social media language in Arabic, so far there is no holistic view of the regional dialects in Colloquial Arabic. This study seeks to address this gap in the literature through proposing a computational model for the classification of the regional dialects in Colloquial Arabic.…”

Section: Literature Reviewmentioning

confidence: 99%

Mapping Linguistic Variations in Colloquial Arabic through Twitter

Omar¹,

Ethleb²,

Elarabawy³

2020

IJACSA

View full text Add to dashboard Cite

The recent years have witnessed the development of different computational approaches to the study of linguistic variations and regional dialectology in different languages including English, German, Spanish and Chinese. These approaches have proved effective in dealing with large corpora and making reliable generalizations about the data. In Arabic, however, much of the work on regional dialectology is so far based on traditional methods; therefore, it is difficult to provide a comprehensive mapping of the dialectal variations of all the colloquial dialects of Arabic. As thus, this study is concerned with proposing a computational statistical model for mapping the linguistic variation and regional dialectology in Colloquial Arabic through Twitter based on the lexical choices of speakers. The aim is to explore the lexical patterns for generating regional dialect maps as derived from Twitter users. The study is based on a corpus of 1597348 geolocated Twitter posts. Using principal component analysis (PCA), data were classified into distinct classes and the lexical features of each class were identified. Results indicate that lexical choices of Twitter users can be usefully used for mapping the regional dialect variation in Colloquial Arabic.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Mapping Linguistic Variations in Colloquial Arabic through Twitter

Omar¹,

Ethleb²,

Elarabawy³

2020

IJACSA

View full text Add to dashboard Cite

show abstract

“…Other works examined the effectiveness of supervised and unsupervised and a combination of both. For example, [22] the proposed two models were for tasks A, B. The first supervised model using Naive Bayes with unigram, trigram, and bigram.…”

Section: Related Workmentioning

confidence: 99%

“…Two approaches were employed that tackled these tasks using deep neural networks [16], [17]. Conversely, six approaches [17]- [22] used traditional machine learning algorithm methods to classify the tweets (details will be provided in Section 2 ). The existing work on the deep learning method that used a wide CNN structure could not capture the semantic and sentiment feature for the Arabic dialects.…”

Section: Introductionmentioning

confidence: 99%

Narrow Convolutional Neural Network for Arabic Dialects Polarity Classification

et al. 2019

View full text Add to dashboard Cite

The complexities and tangles of Arabic dialect in orthography and morphology typically make the sentimental analysis quite challenging. Moreover, most of the classification approaches have addressed this problem based on hand-crafted features. Since the Arabic language has multi-dialects and the language has no word-based order, the extraction process and the classification tasks are more difficult and time consuming. Deep neural network approaches applied to the Arabic language colloquial are very limited. These deep learning approaches typically comprise a structure that is very complex for small quantities of data. The structures are based on wide convolutional networks that are not capable of capturing the entire semantic and sentiment features for Arabic dialects. In this paper, a narrow structure of the convolutional neural network (CNN) has been proposed in order to obtain the tweets representations and classify the Arabic tweets into five, three and two polarities. Sensitivity analysis has been conducted to evaluate the impact of various combination structural properties, such as the number of convolutional filters, pooling size, and filter size on the classification performances. The proposed Arabic narrow convolutional neural network (NCNN) has captured the entire semantic and sentiment information contained in the tweet by maximizing the features of the detector's range. The NCNN performances were estimated to be at its optimum when structured by three convolutional layers, each one followed by the max pooling layer. The model has been developed without using lexicon resources and lexical features or augmented the dataset with extra training data. The narrow model is the first baseline model for Arabic dialects sentiment classifications for a sentence level as it is the first narrow CNN model addressing the Arabic Dialect tweets. NCNN model achieved the lowest macro average mean absolute error (MAE M ) for five polarity and higher Macro average recall (P) for three and two polarities on the SemEval-2017 Arabic dialect Twitter datasets when compared to the other state-of-the-art approaches.INDEX TERMS Arabic tweets sentiment analysis, multilayers convolutional neural network, narrow convolutional neural network.

show abstract

“…Nevertheless, producing good performances via deep neural systems requires providing large-sized labeled training data, tuning many hyper parameters and high computation/time cost. In line with Tw-StAR framework (Mulki et al, 2017(Mulki et al, , 2018a, we propose, here, an HS model based on the hypothesis that, pairing between ngram embeddings and less-complicated architectures i.e. feedforward neural network can lead to an efficient HS detection with least complexity.…”

Section: Introductionmentioning

confidence: 99%

Tw-StAR at SemEval-2019 Task 5: N-gram embeddings for Hate Speech Detection in Multilingual Tweets

Mulki¹,

Ali²,

Haddad³

et al. 2019

Proceedings of the 13th International Workshop on Semantic Evaluation

Self Cite

View full text Add to dashboard Cite

In this paper, we describe our contribution in SemEval-2019: subtask A of task 5 "Multilingual detection of hate speech against immigrants and women in Twitter (HatEval)". We developed two hate speech detection model variants through Tw-StAR framework. While the first model adopted one-hot encoding ngrams to train an NB classifier, the second generated and learned n-gram embeddings within a feedforward neural network. For both models, specific terms, selected via MWT patterns, were tagged in the input data. With two feature types employed, we could investigate the ability of n-gram embeddings to rival one-hot n-grams. Our results showed that in English, n-gram embeddings outperformed one-hot ngrams. However, representing Spanish tweets by one-hot n-grams yielded a slightly better performance compared to that of n-gram embeddings. The official ranking indicated that Tw-StAR ranked 9 th for English and 20 th for Spanish.

show abstract

Tw-StAR at SemEval-2017 Task 4: Sentiment Classification of Arabic Tweets

Cited by 18 publications

References 24 publications

Mapping Linguistic Variations in Colloquial Arabic through Twitter

Mapping Linguistic Variations in Colloquial Arabic through Twitter

Narrow Convolutional Neural Network for Arabic Dialects Polarity Classification

Tw-StAR at SemEval-2019 Task 5: N-gram embeddings for Hate Speech Detection in Multilingual Tweets

Contact Info

Product

Resources

About