Arabic aspect based sentiment classification using BERT

Abdelgwad, Mohammed M.

doi:10.48550/arxiv.2107.13290

Cited by 5 publications

(10 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The BERT model was used by many researchers to classify the sentiments. Abdelgwad (2021) used the BERT model for sentiment classification on the hotel-review dataset, fitted the model on 10 epochs, and achieved an 89.50% accuracy by employing 10% dropout layers and 24 batch sizes. Singh, Jakhar & Pandey (2021) used the BERT model for emotion classification on Twitter data and attained 93.80% accuracy.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

What people think about fast food: opinions analysis and LDA modeling on fast food restaurants using unstructured tweets

Mujahid

Rustam

Alasim

et al. 2023

PeerJ Computer Science

View full text Add to dashboard Cite

With the rise of social media platforms, sharing reviews has become a social norm in today’s modern society. People check customer views on social networking sites about different fast food restaurants and food items before visiting the restaurants and ordering food. Restaurants can compete to better the quality of their offered items or services by carefully analyzing the feedback provided by customers. People tend to visit restaurants with a higher number of positive reviews. Accordingly, manually collecting feedback from customers for every product is a labor-intensive process; the same is true for sentiment analysis. To overcome this, we use sentiment analysis, which automatically extracts meaningful information from the data. Existing studies predominantly focus on machine learning models. As a consequence, the performance analysis of deep learning models is neglected primarily and of the deep ensemble models especially. To this end, this study adopts several deep ensemble models including Bi long short-term memory and gated recurrent unit (BiLSTM+GRU), LSTM+GRU, GRU+recurrent neural network (GRU+RNN), and BiLSTM+RNN models using self-collected unstructured tweets. The performance of lexicon-based methods is compared with deep ensemble models for sentiment classification. In addition, the study makes use of Latent Dirichlet Allocation (LDA) modeling for topic analysis. For experiments, the tweets for the top five fast food serving companies are collected which include KFC, Pizza Hut, McDonald’s, Burger King, and Subway. Experimental results reveal that deep ensemble models yield better results than the lexicon-based approach and BiLSTM+GRU obtains the highest accuracy of 95.31% for three class problems. Topic modeling indicates that the highest number of negative sentiments are represented for Subway restaurants with high-intensity negative words. The majority of the people (49%) remain neutral regarding the choice of fast food, 31% seem to like fast food while the rest (20%) dislike fast food.

show abstract

Section: Resultsmentioning

confidence: 99%

“… Abdelgwad (2021) used bidirectional encoder representations from transformers (BERT) model for sentiment classification of Arabic text. They used three datasets: Arabic news, hotel reviews, and human-annotated book reviews for the experiments.…”

Section: Related Workmentioning

confidence: 99%

What people think about fast food: opinions analysis and LDA modeling on fast food restaurants using unstructured tweets

Mujahid

Rustam

Alasim

et al. 2023

PeerJ Computer Science

View full text Add to dashboard Cite

show abstract

“…To validate the effectiveness of multi-task model, we compared the best multi-task model (AR-LCF-ATEPC-Fusion) with state-of-the-art Deep-based and transformer-based approaches that used the same benchmark dataset: RNN-BiLSTM-CRF [69], BiGRU [70], attention mechanism with neural network [71], BERT [72], and Bert-Flair-BiLSTM/BiGRU-CRF [75], Sequence to Sequence mode for preprocessing and BERT for classification (Seq-seq BERT) [76] and BERT with liner layer (Bert-linerpair) [77]. The results demonstrated that LCF-ATEPC model outperformed other comparable models.…”

Section: Performance Of Proposed Multi-task Model On the Original Dat...mentioning

confidence: 99%

Multi-Task Learning Model with Data Augmentation for Arabic Aspect-Based Sentiment Analysis

Fadel¹,

Abulnaja²,

Saleh³

2023

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

Aspect-based sentiment analysis (ABSA) is a fine-grained process. Its fundamental subtasks are aspect term extraction (ATE) and aspect polarity classification (APC), and these subtasks are dependent and closely related. However, most existing works on Arabic ABSA content separately address them, assume that aspect terms are preidentified, or use a pipeline model. Pipeline solutions design different models for each task, and the output from the ATE model is used as the input to the APC model, which may result in error propagation among different steps because APC is affected by ATE error. These methods are impractical for real-world scenarios where the ATE task is the base task for APC, and its result impacts the accuracy of APC. Thus, in this study, we focused on a multi-task learning model for Arabic ATE and APC in which the model is jointly trained on two subtasks simultaneously in a single model. This paper integrates the multi-task model, namely Local Cotext Foucse-Aspect Term Extraction and Polarity classification (LCF-ATEPC) and Arabic Bidirectional Encoder Representation from Transformers (AraBERT) as a shred layer for Arabic contextual text representation. The LCF-ATEPC model is based on a multi-head selfattention and local context focus mechanism (LCF) to capture the interactive information between an aspect and its context. Moreover, data augmentation techniques are proposed based on state-of-the-art augmentation techniques (word embedding substitution with constraints and contextual embedding (AraBERT)) to increase the diversity of the training dataset. This paper examined the effect of data augmentation on the multi-task model for Arabic ABSA. Extensive experiments were conducted on the original and combined datasets (merging the original and augmented datasets). Experimental results demonstrate that the proposed Multi-task model outperformed existing APC techniques. Superior results were obtained by AraBERT and LCF-ATEPC with fusion layer (AR-LCF-ATEPC-Fusion) and the proposed data augmentation word embedding-based method (FastText) on the combined dataset.

show abstract

“…Position data added by position embeddings is not included in those token embeddings. Finally, it is not clear if each token is associated with sentence A or B; however, this may be determined by creating a new fixed token called as a part installing [32].First of all, we pack the input features N 0 = {T1, ...., Te} WhereTe (e ] ,…”

Section: Word Embedding Using Modified Bertmentioning

confidence: 99%

Mounting-based knowledge transfer network Model Using Aspect-based sentiment analysis

Sowjanya,

srivi,

Devi

2023

Preprint

View full text Add to dashboard Cite

Aspect-based sentiment analysis is a complex subtask of sentiment analysis in which the sentiment polarities of given aspect terms in phrases are determined. In this paper, we suggested a novel Mounting-based knowledge transmission network for aspect-based sentiment analysis. First and foremost, before entering data into models, data preparation (data pre-processing) is crucial, as it contributes to achieving high accuracy. For the textual data, special procedures were required, including tokenization, stop word deletion, and the Weighting Factor, which was all applied in this study. Second, employing feature extraction based on the Aspect term using NB, Modified BERT (MBERT) together with Entropy measure may focus on the critical context words to the given aspect terms in sentences. Finally, Convolution neural network is used to predict the result of sentiment classification aspect polarities as positive or negative.Experimental results show that our proposed approach accomplishes the most extreme accuracy outcome of 92%. Comparable to the TMSC and DNN, which achieves 78%, 72%. The MGAN and CNN had the accuracyworst of 70% and 71%. The HSCN had the very worst accuracy69%.

show abstract

Arabic aspect based sentiment classification using BERT

Cited by 5 publications

References 0 publications

What people think about fast food: opinions analysis and LDA modeling on fast food restaurants using unstructured tweets

What people think about fast food: opinions analysis and LDA modeling on fast food restaurants using unstructured tweets

Multi-Task Learning Model with Data Augmentation for Arabic Aspect-Based Sentiment Analysis

Mounting-based knowledge transfer network Model Using Aspect-based sentiment analysis

Contact Info

Product

Resources

About