Surface and Deep Features Ensemble for Sentiment Analysis of Arabic Tweets

Al-Twairesh, Nora; Al-Negheimish, Hadeel

doi:10.1109/access.2019.2924314

Cited by 72 publications

(41 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The annotation was performed based on the manually annotated phrases and the frequency of positive and negative words appearing in the text. Another work was done in [20] by collecting 10 million tweets from Twitter and using a list of positive and negative Arabic words as search keywords. The annotation was performed automatically by considering tweets containing positive search keywords as positive tweets and similarly tweets containing negative search keywords as negative tweets.…”

Section: Sentiment Annotationmentioning

confidence: 99%

AraSenCorpus: A Semi-Supervised Approach for Sentiment Annotation of a Large Arabic Text Corpus

et al. 2021

View full text Add to dashboard Cite

At a time when research in the field of sentiment analysis tends to study advanced topics in languages, such as English, other languages such as Arabic still suffer from basic problems and challenges, most notably the availability of large corpora. Furthermore, manual annotation is time-consuming and difficult when the corpus is too large. This paper presents a semi-supervised self-learning technique, to extend an Arabic sentiment annotated corpus with unlabeled data, named AraSenCorpus. We use a neural network to train a set of models on a manually labeled dataset containing 15,000 tweets. We used these models to extend the corpus to a large Arabic sentiment corpus called “AraSenCorpus”. AraSenCorpus contains 4.5 million tweets and covers both modern standard Arabic and some of the Arabic dialects. The long-short term memory (LSTM) deep learning classifier is used to train and test the final corpus. We evaluate our proposed framework on two external benchmark datasets to ensure the improvement of the Arabic sentiment classification. The experimental results show that our corpus outperforms the existing state-of-the-art systems.

show abstract

Section: Sentiment Annotationmentioning

confidence: 99%

AraSenCorpus: A Semi-Supervised Approach for Sentiment Annotation of a Large Arabic Text Corpus

et al. 2021

View full text Add to dashboard Cite

show abstract

“…In order to improve the performance of the existing models, the combination models have been written about extensively in sentiment analysis such as in [2], [19], [23], [28], [29], [36]. Rehman et al [28] provided a hybrid model using LSTM and a deep CNN model named Hybrid CNN-LSTM model to improve the accuracy of the sentiment analysis problem by using the word to vector approach to train first-word embeddings.…”

Section: Related Workmentioning

confidence: 99%

“…However, this method only focused on the surface features of the word without considering the impact of the in-depth features. Hence, Al-Twairesh et al [2] proposed a feature ensemble model by considering the surface and in-depth features. The surface features are manually extracted features, and the in-depth features are generic word embeddings and sentiment specific word embeddings.…”

Section: Related Workmentioning

confidence: 99%

“…Twitter's user activity has grown quickly, with approximately 500 million tweets published daily in 2014, the last time official stats were released. 1,2 According to statistics on April 17 th , 2019, 3 the number of active Twitter users per month is 330 million worldwide for Q1 2019 (from January 1 st to March 31 th ) versus 326 million for Q3 2018. 1 http://www.internetlivestats.com/twitter-statistics/ 2 https://www.businessofapps.com/data/twitter-statistics/ 3 https://zephoria.com/twitter-statistics-top-ten/ The information on Twitter is a source that could provide many benefits if we know how to exploit it.…”

Section: Introductionmentioning

confidence: 99%

“…A feature ensemble model is a combination of a set of models (base classifiers) to obtain a more accurate and reliable model in comparison with what a single model can achieve [2]. This model is used as a support tool for other models (especially as deep learning models) to solve many real tasks.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Improving the Performance of Sentiment Analysis of Tweets Containing Fuzzy Sentiment Using the Feature Ensemble Model

Phan¹,

Tran²,

Nguyen³

et al. 2020

IEEE Access

114

View full text Add to dashboard Cite

The increase in the volume of user-generated content on Twitter has resulted in tweet sentiment analysis becoming an essential tool for the extraction of information about Twitter users' emotional state. Consequently, there has been a rapid growth of tweet sentiment analysis in the area of natural language processing. Tweet sentiment analysis is increasingly applied in many areas, such as decision support systems and recommendation systems. Therefore, improving the accuracy of tweet sentiment analysis has become practical and an area of interest for many researchers. Many approaches have tried to improve the performance of tweet sentiment analysis methods by using the feature ensemble method. However, most of the previous methods attempted to model the syntactic information of words without considering the sentiment context of these words. Besides, the positioning of words and the impact of phrases containing fuzzy sentiment have not been mentioned in many studies. This study proposed a new approach based on a feature ensemble model related to tweets containing fuzzy sentiment by taking into account elements such as lexical, word-type, semantic, position, and sentiment polarity of words. The proposed method has been experimented on with real data, and the result proves effective in improving the performance of tweet sentiment analysis in terms of the F 1 score. INDEX TERMS Feature ensemble model, fuzzy sentiment, tweet embeddings, tweet sentiment analysis.

show abstract

COVID-19’s Impact on the Telecommunications Companies

Almuqren

Cristea

2021

Advances in Intelligent Systems and Computing

View full text Add to dashboard Cite

Now the world is witnessing most significant challenges due the Covid-19 crisis. Beyond health effects, it has social and economic effects. With the enormous amount of data available and the widespread use of social web globally, research can and should use it to provide solutions. Customer satisfaction is known to affect customer churn (customers leaving companies), which is a problem affecting many companies in competitive and volatile markets -like the current one.One easily available open source of customer opinions are tweets -more relevant now in the online world. Whilst Natural Language Processing (NLP) on tweets is not new, few studies target customer satisfaction, and NLP body of research on Arabic tweets is modest; we are not aware of any other study on this during a global pandemic. Our research thus aims to propose a new model based on Twitter mining to measure customer satisfaction during Covid-19, as well as compare customer satisfaction before and during the crisis. This is a use case for the largest Telecom companies in Saudi Arabia, and we involve the popular method of Sentiment Analysis (SA) for the task. We additionally propose a new Saudi lexicon and apply it to monitor real-time customer satisfaction on Twitter using three different transfer network models on Arabic sentiment analysis. Also, this research evaluates using these models on Arabic Sentiment Analysis as the first study comparing between three different transfer network models on Arabic text.

show abstract

Surface and Deep Features Ensemble for Sentiment Analysis of Arabic Tweets

Cited by 72 publications

References 42 publications

AraSenCorpus: A Semi-Supervised Approach for Sentiment Annotation of a Large Arabic Text Corpus

AraSenCorpus: A Semi-Supervised Approach for Sentiment Annotation of a Large Arabic Text Corpus

Improving the Performance of Sentiment Analysis of Tweets Containing Fuzzy Sentiment Using the Feature Ensemble Model

COVID-19’s Impact on the Telecommunications Companies

Contact Info

Product

Resources

About