An Empirical Evaluation of Arabic-Specific Embeddings for Sentiment Analysis

Barhoumi, Amira; Camelin, Nathalie; Aloulou, Chafik; Estève, Yannick; Belguith, Lamia Hadrich

doi:10.1007/978-3-030-32959-4_3

Cited by 6 publications

(5 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Expert features have the advantage to convey human understandable information but there are not the only way to represent data. From other research domains such as SA, we assist to the rising of pre-trained self-supervised feature to represent the data, especially with word embeddings such as GloVe [24] or Word2Vec [41]. As there are trained on a massive amount of data, they tend to be able to efficiently represent data, without the need of human annotation.…”

Section: Pre-trained Features For Nlpmentioning

confidence: 99%

“…B. Linguistic modality 1) Baseline features : Word2Vec: Word2Vec embeddings have been extensively used for sentiment analysis or opinion mining from text [41], [42], this motivated us to use such representation for the prediction of satisfaction. In the following experiments, a Word2Vec model has been trained with the toolkit GENSIM [69], using private data owned by Allo-Media composed of manual call transcriptions received by call centers, totaling over 500 hours of speech, with CBoW algorithm [53].…”

Section: Acoustic and Linguistic Featuresmentioning

confidence: 99%

See 1 more Smart Citation

On the Use of Self-Supervised Pre-Trained Acoustic and Linguistic Features for Continuous Speech Emotion Recognition

Macary

Tahon

Estève³

et al. 2021

2021 IEEE Spoken Language Technology Workshop (SLT)

View full text Add to dashboard Cite

Pre-training for feature extraction is an increasingly studied approach to get better continuous representations of audio and text content. In the present work, we use wav2vec and camemBERT as self-supervised learned models to represent our data in order to perform continuous emotion recognition from speech (SER) on AlloSat, a large French emotional database describing the satisfaction dimension, and on the state of the art corpus SEWA focusing on valence, arousal and liking dimensions. To the authors' knowledge, this paper presents the first study showing that the joint use of wav2vec and BERT-like pre-trained features is very relevant to deal with continuous SER task, usually characterized by a small amount of labeled training data. Evaluated by the well-known concordance correlation coefficient (CCC), our experiments show that we can reach a CCC value of 0.825 instead of 0.592 when using MFCC in conjunction with word2vec word embedding on the AlloSat dataset.

show abstract

Section: Pre-trained Features For Nlpmentioning

confidence: 99%

Section: Acoustic and Linguistic Featuresmentioning

confidence: 99%

On the Use of Self-Supervised Pre-Trained Acoustic and Linguistic Features for Continuous Speech Emotion Recognition

Macary

Tahon

Estève³

et al. 2021

2021 IEEE Spoken Language Technology Workshop (SLT)

View full text Add to dashboard Cite

show abstract

“…The purpose of this comparison is the classification, disregarding the research objective of these works. We emphasize that the works cited in the table concern the Algerian dialect [30,31], the Moroccan dialect [32], Modern Standard Arabic and Colloquial Arabic [33]. All of them used ML or DL techniques.…”

Section: Lossmentioning

confidence: 99%

Subject Detection of Algerian Posts for Opinion Analysis

Bousmaha,

Hamadouche,

Cheurfaoui

et al. 2024

ISI

View full text Add to dashboard Cite

“…For the LABR dataset, the literature showed that many studies focused on classical machine learning, but only a few worked [42][43][44][45][46][47] on deep learning. A study was conducted using deep learning techniques [48], in which three models were implemented: CNN, LSTM, and a hybrid CNN-LSTM model.…”

Section: Arabic Languagementioning

confidence: 99%

Arabic Sentiment Analysis Based on Word Embeddings and Deep Learning

Elhassan,

Varone,

Ahmed

et al. 2023

Computers

View full text Add to dashboard Cite

Social media networks have grown exponentially over the last two decades, providing the opportunity for users of the internet to communicate and exchange ideas on a variety of topics. The outcome is that opinion mining plays a crucial role in analyzing user opinions and applying these to guide choices, making it one of the most popular areas of research in the field of natural language processing. Despite the fact that several languages, including English, have been the subjects of several studies, not much has been conducted in the area of the Arabic language. The morphological complexities and various dialects of the language make semantic analysis particularly challenging. Moreover, the lack of accurate pre-processing tools and limited resources are constraining factors. This novel study was motivated by the accomplishments of deep learning algorithms and word embeddings in the field of English sentiment analysis. Extensive experiments were conducted based on supervised machine learning in which word embeddings were exploited to determine the sentiment of Arabic reviews. Three deep learning algorithms, convolutional neural networks (CNNs), long short-term memory (LSTM), and a hybrid CNN-LSTM, were introduced. The models used features learned by word embeddings such as Word2Vec and fastText rather than hand-crafted features. The models were tested using two benchmark Arabic datasets: Hotel Arabic Reviews Dataset (HARD) for hotel reviews and Large-Scale Arabic Book Reviews (LARB) for book reviews, with different setups. Comparative experiments utilized the three models with two-word embeddings and different setups of the datasets. The main novelty of this study is to explore the effectiveness of using various word embeddings and different setups of benchmark datasets relating to balance, imbalance, and binary and multi-classification aspects. Findings showed that the best results were obtained in most cases when applying the fastText word embedding using the HARD 2-imbalance dataset for all three proposed models: CNN, LSTM, and CNN-LSTM. Further, the proposed CNN model outperformed the LSTM and CNN-LSTM models for the benchmark HARD dataset by achieving 94.69%, 94.63%, and 94.54% accuracy with fastText, respectively. Although the worst results were obtained for the LABR 3-imbalance dataset using both Word2Vec and FastText, they still outperformed other researchers’ state-of-the-art outcomes applying the same dataset.

show abstract

An Empirical Evaluation of Arabic-Specific Embeddings for Sentiment Analysis

Cited by 6 publications

References 31 publications

On the Use of Self-Supervised Pre-Trained Acoustic and Linguistic Features for Continuous Speech Emotion Recognition

On the Use of Self-Supervised Pre-Trained Acoustic and Linguistic Features for Continuous Speech Emotion Recognition

Subject Detection of Algerian Posts for Opinion Analysis

Arabic Sentiment Analysis Based on Word Embeddings and Deep Learning

Contact Info

Product

Resources

About