An efficient hybrid filter and evolutionary wrapper approach for sentiment analysis of various topics on Twitter

Hassonah, Mohammad A.; Al-Sayyed, Rizik; Rodan, Ali; Al-Zoubi, Ala’ M.; Aljarah, Ibrahim; Faris, Hossam

doi:10.1016/j.knosys.2019.105353

Cited by 75 publications

(35 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…However, ML requires domain-specific datasets, which can be considered as a limitation (Al-Natour and Turetken 2020). After data preprocessing, feature selection is performed as per the requirement, following which one obtains the final results after the analysis of the given data as per the adopted approach (Hassonah et al 2019).…”

Section: Sentiment Analysis (Sa)mentioning

confidence: 99%

Comprehensive review of text-mining applications in finance

et al. 2020

View full text Add to dashboard Cite

Text-mining technologies have substantially affected financial industries. As the data in every sector of finance have grown immensely, text mining has emerged as an important field of research in the domain of finance. Therefore, reviewing the recent literature on text-mining applications in finance can be useful for identifying areas for further research. This paper focuses on the text-mining literature related to financial forecasting, banking, and corporate finance. It also analyses the existing literature on text mining in financial applications and provides a summary of some recent studies. Finally, the paper briefly discusses various text-mining methods being applied in the financial domain, the challenges faced in these applications, and the future scope of text mining in finance.

show abstract

Section: Sentiment Analysis (Sa)mentioning

confidence: 99%

Comprehensive review of text-mining applications in finance

et al. 2020

View full text Add to dashboard Cite

show abstract

“…A dozen of research e.g., [1], [2], [5], [11], [12], [16], and [55] have been employed by considering the Twitter data as a source dataset for sentiment and emotion extractions. Still, there is a common problem of accurate sentiment classification.…”

Section: Related Workmentioning

confidence: 99%

“…Generally, there are three methods for SA; machine learning, including supervised practice [9], [10], lexiconbased, including unsupervised methods [11], [12], and hybrid approach containing both supervised and unsupervised method [12], [13]. Most of the researchers [13]- [15] worked over the Machine Learning (ML) approach for the sentiment and text mining, where a labeled dataset is used to train their model [9], [16]. The most typical algorithms for ML are Naïve Bayes (NB) [2] and Support Vector Machine (SVM) [17].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

GAWA–A Feature Selection Method for Hybrid Sentiment Classification

et al. 2020

View full text Add to dashboard Cite

Sentiment analysis or opinion mining is the key to natural language processing for the extraction of useful information from the text documents of numerous sources. Several different techniques, i.e., simple rule-based to lexicon-based and more sophisticated machine learning algorithms, have been widely used with different classifiers to get the factual analysis of sentiment. However, lexicon-based sentiment classification is still suffering from low accuracies, mainly due to the deficiency of domain-oriented competitive dictionaries. Similarly, machine learning-based sentiment is also tackling the accuracy constraints because of feature ambiguity from social data. One of the best ways to deal with the accuracy issue is to select the best feature-set and reduce the volume of the feature. This paper proposes a method (namely, GAWA) for feature selection by utilizing the Wrapper Approaches (WA) to select the premier features and the Genetic Algorithm (GA) to reduce the size of the premier features. The novelty of this work is the modified fitness function of heuristic GA to compute the optimal features by reducing the redundancy for better accuracy. This work aims to present a comprehensive model of hybrid sentiment by using the proposed method, GAWA. It will be valued in developing a new approach for the selection of feature-set with a better accuracy level. The experiments revealed that these techniques could reduce the feature-set upto 61.95% without negotiating the accuracy level. The new optimal feature sets enhanced the efficiency of the Naïve Bayes algorithm up to 92%. This work is compared with the conventional method of feature selection and concluded the 11% better accuracy than PCA and 8% better than PSO. Furthermore, the results are compared with the literature work and found that the proposed method outperformed the previous research.

show abstract

“…Por exemplo, a sentença "eu adorei a sobremesa" mencionada anteriormenteé positiva. Há também trabalhos que investigam a polaridade com mais profundidade e tentam identificar sentimentos como medo, raiva, felicidade e tristeza [Hassonah et al 2020, Dosciatti et al 2013. Há ainda trabalhos que classificam a polaridade como uma escala, por exemplo, em um intervalo de 1 a -1 [Esuli and Sebastiani 2006, De Smedt and Daelemans 2012, Cambria et al 2010.…”

Section: Introductionunclassified

Investigando Features de Sentenças para Classificação de Subjetividade e Polaridade em Português do Brasil

Oliveira¹,

Melo²

2020

Anais Do Encontro Nacional De Inteligência Artificial E Computacional (ENIAC 2020)

View full text Add to dashboard Cite

Identificar sentenças subjetivas e calcular a polaridade destas sentenças são duas importantes tarefas de análise de sentimentos. Apesar de não serem problemas novos, a maioria das soluções são voltadas para o idioma inglês. Neste artigo, nós propusemos e avaliamos uma abordagem baseada em aprendizagem de máquina para lidar com as duas tarefas em português. Nós investigamos o uso de dois modelos de classificação e também propusemos um conjunto de características linguísticas do próprio texto. Nós experimentamos e avaliamos os métodos contra um representativo conjunto de baselines e em um conjunto diversificado de datasets. Nossa abordagem alcançou os melhores resultados nas duas tarefas e em todos os conjuntos de dados de teste.

show abstract

An efficient hybrid filter and evolutionary wrapper approach for sentiment analysis of various topics on Twitter

Cited by 75 publications

References 35 publications

Comprehensive review of text-mining applications in finance

Comprehensive review of text-mining applications in finance

GAWA–A Feature Selection Method for Hybrid Sentiment Classification

Investigando Features de Sentenças para Classificação de Subjetividade e Polaridade em Português do Brasil

Contact Info

Product

Resources

About