Combining Context-Aware Embeddings and an Attentional Deep Learning Model for Arabic Affect Analysis on Twitter

Elfaik, Hanane; Nfaoui, El Habib

doi:10.1109/access.2021.3102087

Cited by 20 publications

(10 citation statements)

References 63 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Their findings indicate a micro F1 score of 0.615% and an accuracy of 0.498%. 11 conducted a follow-up study to address the issue of emotion recognition in Arabic messages. A tweet can be in any number of different emotional states (love, joy, optimism, etc.).…”

Section: /17mentioning

confidence: 99%

WITHDRAWN: Emotion Detection in Arabic Short Text: A Deep-Learning Approach

Aljwari*,

Zamzami

2023

Preprint

View full text Add to dashboard Cite

In modern society, writing down thoughts, ideas, and pleasant experiences has become a widespread way to express feelings. X, formerly known as Twitter, is a rich data source that companies can use to study individuals’ ideas, thoughts, and emotions for a range of useful applications. The analysis of positive and negative feelings is a key focus of NLP research literature, while emotion detection receives relatively little attention. Very few studies to date have examined the classification of emotions in text, particularly Arabic written content. The new study uses deep learning approaches to solve this difficulty and close these existing gaps in the literature. A number of different deep learning models are available and each one has been developed based on a unique feature engineering approach to classify the emotions conveyed in the SemEval-2018 dataset into four groups, namely joy, fear, anger and sadness. The results show that the CNN model that employs Word2vec outperforms the other models, with an accuracy of 80%. Furthermore, it has been found to perform better in Arabic than the most current comparable model, with improvements varying between 12–54.96% for F1 scores to 5–26% for accuracy.

show abstract

Section: /17mentioning

confidence: 99%

WITHDRAWN: Emotion Detection in Arabic Short Text: A Deep-Learning Approach

Aljwari*,

Zamzami

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…To ensure the improvements of the MVODRL-AA model over other models, a comparative study is given in Table 5 and Fig. 13 [22]. The outcomes implied the supremacy of the MVODRL-AA model over other models.…”

Section: Performance Validationmentioning

confidence: 99%

Multi-Versus Optimization with Deep Reinforcement Learning Enabled Affect Analysis on Arabic Corpus

Duhayyim,

Al-onazi,

Alzahrani

et al. 2023

CSSE

View full text Add to dashboard Cite

Sentiment analysis (SA) of the Arabic language becomes important despite scarce annotated corpora and confined sources. Arabic affect Analysis has become an active research zone nowadays. But still, the Arabic language lags behind adequate language sources for enabling the SA tasks. Thus, Arabic still faces challenges in natural language processing (NLP) tasks because of its structure complexities, history, and distinct cultures. It has gained lesser effort than the other languages. This paper developed a Multi-versus Optimization with Deep Reinforcement Learning Enabled Affect Analysis (MVODRL-AA) on Arabic Corpus. The presented MVODRL-AA model majorly concentrates on identifying and classifying effects or emotions that occurred in the Arabic corpus. Firstly, the MVODRL-AA model follows data pre-processing and word embedding. Next, an n-gram model is utilized to generate word embeddings. A deep Q-learning network (DQLN) model is then exploited to identify and classify the effect on the Arabic corpus. At last, the MVO algorithm is used as a hyperparameter tuning approach to adjust the hyperparameters related to the DQLN model, showing the novelty of the work. A series of simulations were carried out to exhibit the promising performance of the MVODRL-AA model. The simulation outcomes illustrate the betterment of the MVODRL-AA method over the other approaches with an accuracy of 99.27%.

show abstract

“…This allows the learning capability of the LSTM to be further improved to better understand contextual information [30,31]. Considering that the advantage of LSTM is that long-term memory functions can be achieved by connecting previous and present contexts, the advantage of BiLSTM is that past and future contexts can be extracted by considering both directions of the information flow [32]. Based on this, this paper proposes to add a bidirectional LSTM network to the LSTM network and use the BiLSTM_LSTM model for training and the prediction of sentiment analysis.…”

Section: Sentiment Analysis Of Official Account Commentary In Time Contextmentioning

confidence: 99%

Sentimental Knowledge Graph Analysis of the COVID-19 Pandemic Based on the Official Account of Chinese Universities

Tian

2021

Electronics

View full text Add to dashboard Cite

With the advent of the new media mobile Internet era, the network public opinion in colleges and universities, as an extension of social network public opinion, is also facing a crisis in the prevention, control, and governance system. In this paper, the Fiddler was used to collect the comments and other relevant data of the COVID-19 topic articles on the WeChat Official Accounts of China’s top ten universities in 2020. The BILSTM_LSTM sentiment analysis model was used to analyze the sentiment tendency of the comments, and the LDA topic model was used to mine the topics of the comments with different emotional attributes at different stages of COVID-19. Based on sentiment analysis and text mining, entities and relationships in the theme graph of public opinion events in colleges and universities were identified, and the Neo4j graph database was established to construct the sentimental knowledge graph of the pandemic theme of university public accounts. People’s attitudes in university public opinion are easily influenced by a variety of factors, and the degree of emotional disposition changes over time, with the stage the pandemic is in, and with different commentators; official account opinion topics change with the development of the time stage of the pandemic, and students’ positive and negative comment topics show a diverse trend. By incorporating topic mining into the sentimental knowledge graph, the graph can realize functions such as the emotion retrieval of comments on university public numbers, a source search of security threats in university social networks, and monitoring of comments on public opinion under the theme of the pandemic, which provides new ideas for further exploring the research and governance system of university network public opinion and is conducive to preventing and resolving campus public opinion crises.

show abstract

Combining Context-Aware Embeddings and an Attentional Deep Learning Model for Arabic Affect Analysis on Twitter

Cited by 20 publications

References 63 publications

WITHDRAWN: Emotion Detection in Arabic Short Text: A Deep-Learning Approach

WITHDRAWN: Emotion Detection in Arabic Short Text: A Deep-Learning Approach

Multi-Versus Optimization with Deep Reinforcement Learning Enabled Affect Analysis on Arabic Corpus

Sentimental Knowledge Graph Analysis of the COVID-19 Pandemic Based on the Official Account of Chinese Universities

Contact Info

Product

Resources

About