CovTiNet: Covid text identification network using attention-based positional embedding feature fusion

Hossain, Md. Rajib; Hoque, Mohammed Moshiul; Siddique, Nazmul; Sarker, Iqbal H.

doi:10.1007/s00521-023-08442-y

Cited by 13 publications

(2 citation statements)

References 64 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…That approach might sound intuitive but at the same time it creates a new set of greater challenges. The first one is the need to provide and maintain a specific model and lexicons for every single language and its dialects, which is already a huge challenge in NLP domain due the variant complexity of many languages and dialects regarding grammar and structure to begin with as these studies show [11,[21][22][23]25]. Then comes the challenge of the doubled resources needed, due to having two ML models (at least) running instead of one.…”

Section: Introductionmentioning

confidence: 99%

Effect of typos on text classification accuracy in word and character tokenization

Peter E. Shawky,

Saleh Mesbah ElKaffas,

Shawkat K Guirguis

2024

ARASET

View full text Add to dashboard Cite

To train a machine to “sense” a users’ feelings through writings (sentiment analysis) has become a crucial process in several domains: marketing, research, surveys and more. Nevertheless in times of crisis like COVID. Typo is one of the underestimated challenges processing user-generated text (comments, tweets, ..etc), it affects both learning and evaluation processes. Word tokenization outcome changes drastically even with a single character change, hence as expected, experiments have shown significant accuracy decreases due to typo. Adding a spelling correction as preprocessing layer, building one for every language, is a very time and resources expensive solution, a huge challenge against large data and real-time processing. Alternatively, a CNN model consuming the same text, once tokenized on characters level and once on words level while inducing typo, showed that as the typo percentage approaches 10% of the text, the results with characters tokens surpasses words tokens. Finally, on %30 typo of the text, the model consuming characters tokenization outperformed itself with the word level by a significant %22.3 in accuracy and %24.9 in F1-Score, using the same exact model. This approach in solving the inevitable typo challenge in NLP proved to be of significant practicality, saving huge resources versus using a spelling-correction model beforehand. It also removes a blocker challenge in front of real-time processing of user-generated text while preserving acceptable accuracy results.

show abstract

Section: Introductionmentioning

confidence: 99%

Effect of typos on text classification accuracy in word and character tokenization

Peter E. Shawky,

Saleh Mesbah ElKaffas,

Shawkat K Guirguis

2024

ARASET

View full text Add to dashboard Cite

show abstract

“…Nevertheless, Bengali stands as the seventh most widely spoken language globally, with approximately 245 million people in Bangladesh and two states of India conversing in Bengali [16]. The growing popularity of Bangla on social media is attributed to the widespread acceptance of the Unicode system and the increasing use of the Internet [17]. Consequently, a substantial volume of Bengali bullying texts has proliferated across the unstructured web.…”

Section: Introductionmentioning

confidence: 99%

Cyberbullying Text Identification based on Deep Learning and Transformer-based Language Models

Saifullah,

Khan,

Jamal

et al. 2024

EAI Endorsed Trans Ind Net Intel Syst

Self Cite

View full text Add to dashboard Cite

In the contemporary digital age, social media platforms like Facebook, Twitter, and YouTube serve as vital channels for individuals to express ideas and connect with others. Despite fostering increased connectivity, these platforms have inadvertently given rise to negative behaviors, particularly cyberbullying. While extensive research has been conducted on high-resource languages such as English, there is a notable scarcity of resources for low-resource languages like Bengali, Arabic, Tamil, etc., particularly in terms of language modeling. This study addresses this gap by developing a cyberbullying text identification system called BullyFilterNeT tailored for social media texts, considering Bengali as a test case. The intelligent BullyFilterNeT system devised overcomes Out-of-Vocabulary (OOV) challenges associated with non-contextual embeddings and addresses the limitations of context-aware feature representations. To facilitate a comprehensive understanding, three non-contextual embedding models GloVe, FastText, and Word2Vec are developed for feature extraction in Bengali. These embedding models are utilized in the classification models, employing three statistical models (SVM, SGD, Libsvm), and four deep learning models (CNN, VDCNN, LSTM, GRU). Additionally, the study employs six transformer-based language models: mBERT, bELECTRA, IndicBERT, XML-RoBERTa, DistilBERT, and BanglaBERT, respectively to overcome the limitations of earlier models. Remarkably, BanglaBERT-based BullyFilterNeT achieves the highest accuracy of 88.04% in our test set, underscoring its effectiveness in cyberbullying text identification in the Bengali language.

show abstract

Intrinsic and Extrinsic Evaluation of Sentiment-Specific Word Embeddings

Afroze,

Hoque

2023

Lecture Notes in Networks and Systems

View full text Add to dashboard Cite

CovTiNet: Covid text identification network using attention-based positional embedding feature fusion

Cited by 13 publications

References 64 publications

Effect of typos on text classification accuracy in word and character tokenization

Effect of typos on text classification accuracy in word and character tokenization

Cyberbullying Text Identification based on Deep Learning and Transformer-based Language Models

Intrinsic and Extrinsic Evaluation of Sentiment-Specific Word Embeddings

Contact Info

Product

Resources

About