UTSA: Urdu Text Sentiment Analysis Using Deep Learning Methods

Naqvi, Uzma; Majid, Abdul; Abbas, Syed Ali

doi:10.1109/access.2021.3104308

Cited by 43 publications

(21 citation statements)

References 24 publications

(22 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The proposed architecture outperforms the baseline methods with improved accuracy of 8%. Naqvi et al [32] propose a framework for Urdu SA using DL models combined with different word representations. The performance of LSTM, CNN, and CNN-LSTM DL models are evaluated, and additionally, stacked layers are used in sequential C-LSTM, LSTM, and BiLSTM models by applying different filters to the convolutional layer.…”

Section: Deep Learning Approachmentioning

confidence: 99%

Deep Learning Based Cross Domain Sentiment Classification for Urdu Language

Altaf

Jamal

et al. 2022

IEEE Access

View full text Add to dashboard Cite

Sentiment analysis is a widely researched area due to its various applications in customer services, brand monitoring, and market research. Automatic sentiment classification is an important but challenging task. Contrary to the English language, sentiment analysis for low-resource languages like Urdu is an under-explored research area. Most of the work on sentiment analysis in the Urdu language is domain-dependent where models are mostly trained and tested on the same dataset on limited domains. However, sentiments in different domains are expressed differently, and manually annotating the datasets for all possible domains is unfeasible. Training a sentiment classifier using annotated data on one domain and testing it on another domain results in poor performance as the terms appearing in the source domain (training data) might not appear in the target (testing data) domain. In this paper, we present a baseline method for cross-domain sentiment analysis in the Urdu language using two different domains. Feature extraction is performed using n-grams and word embedding techniques. Sentiment classification is performed using machine learning and deep learning classifiers. The proposed method achieves an accuracy, precision, recall, and F1 scores of 0.77, 0.83, 0.68, and 0.75, respectively.INDEX TERMS Cross-domain sentiment analysis; deep learning; Urdu language processing; feature engineering

show abstract

Section: Deep Learning Approachmentioning

confidence: 99%

Deep Learning Based Cross Domain Sentiment Classification for Urdu Language

Altaf

Jamal

et al. 2022

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Sentiment analysis and emotional analysis are used in different domains like finance, marketing (Momtazi and Layeghi, 2021), sports (Cohen-Kalaf et al, 2021), healthcare (Abualigah et al, 2020), etc. to understand person's opinion (Naqvi et al, 2021;Kumari et al, 2021), analyze product reviews (Doo et al, 2021), etc. Although researchers have utilized sentiment analysis in many studies, few studies have utilized emotional aspects (Siering et al, 2018).…”

Section: Sentiment and Emotion Analysismentioning

confidence: 99%

Predicting ratings of social media feeds: combining latent-factors and emotional aspects for improving performance of different classifiers

Ray

Bala

Rana

et al. 2022

AJIM

View full text Add to dashboard Cite

PurposeThe widespread acceptance of various social platforms has increased the number of users posting about various services based on their experiences about the services. Finding out the intended ratings of social media (SM) posts is important for both organizations and prospective users since these posts can help in capturing the user’s perspectives. However, unlike merchant websites, the SM posts related to the service-experience cannot be rated unless explicitly mentioned in the comments. Additionally, predicting ratings can also help to build a database using recent comments for testing recommender algorithms in various scenarios.Design/methodology/approachIn this study, the authors have predicted the ratings of SM posts using linear (Naïve Bayes, max-entropy) and non-linear (k-nearest neighbor, k-NN) classifiers utilizing combinations of different features, sentiment scores and emotion scores.FindingsOverall, the results of this study reveal that the non-linear classifier (k-NN classifier) performed better than the linear classifiers (Naïve Bayes, Max-entropy classifier). Results also show an improvement of performance where the classifier was combined with sentiment and emotion scores. Introduction of the feature “factors of importance” or “the latent factors” also show an improvement of the classifier performance.Originality/valueThis study provides a new avenue of predicting ratings of SM feeds by the use of machine learning algorithms along with a combination of different features like emotional aspects and latent factors.

show abstract

“…Pedoman PICO sangat berguna dan memudahkan dalam merumuskan pertanyaan penelitian [20]. Tabel Dataset Peneliti Jumlah Twitter [33], [34], [35], [36], [23], [24], [37], [38], [39], [22], [40], [41], [42], [43], [44], [45], [46] 17 Berita berbahasa Arab [28], [47], [48], [49], [27], [25], [50], [51] 8…”

Section: Tahap Pembuatan Rencana Awalunclassified

“…Tabel 6. Analisis Metode Representasi Teks dalam Arabic Natural Language Processing Metode Untuk Representasi Teks Peneliti Jumlah TF-IDF [4], [9], [48], [30], [23], [24], [29], [53], [54], [7], [38], [55], [32], [56], [25], [31], [59], [1], [51], [60] 20 Word2Vec [34], [24], [49], [7], [57], [39], [41], [43], [45], [46] 10 AraVec [34], [35], [37], [40], [41], [42] 6 FastText [34], [47], [35], [57], [41], [42], [50], [46] 8 mBERT [27], [22], [41], [46] 4 AraBERT [36],…”

Section: Tahap Pembuatan Rencana Awalmentioning

confidence: 99%

Analisis Metode Representasi Teks Untuk Deteksi Interelasi Kitab Hadis: Systematic Literature Review

Ariyanto

fatichah²,

Arifin³

2021

RESTI

View full text Add to dashboard Cite

Hadith is the second source of reference for Islamic law after the Qur'an, which explains the sentences in the Qur'an which are still global by referring to the provisions of the Prophet Muhammad SAW. Classification of text documents can also be used to overcome the problem of interrelation between the Qur'an and hadith. The problem of interrelation between books of hadith needs to be done because some hadiths in certain hadith books have the same meaning as other hadith books. This study aims to analyze the development of text representation and classification methods suitable to overcome similarity meaning problems in detecting interrelationships between hadith books. The research method used is Systematic Literature Review (SLR) sourced from Google Scholar, Science Direct, and IEEE. There are 42 pieces of literature that have been studied successfully. The results showed that contextual embedding as the newest text representation method considered word context and sentence meaning better than static embedding. As a classification method, the ensemble method has better performance in classifying text documents than using only a single classifier model. Thus, future research can consider using a combination of contextual embedding and ensemble methods to detect interrelationships between books of hadith.

show abstract

UTSA: Urdu Text Sentiment Analysis Using Deep Learning Methods

Cited by 43 publications

References 24 publications

Deep Learning Based Cross Domain Sentiment Classification for Urdu Language

Deep Learning Based Cross Domain Sentiment Classification for Urdu Language

Predicting ratings of social media feeds: combining latent-factors and emotional aspects for improving performance of different classifiers

Analisis Metode Representasi Teks Untuk Deteksi Interelasi Kitab Hadis: Systematic Literature Review

Contact Info

Product

Resources

About