How can we manage Offensive Text in Social Media - A Text Classification Approach using LSTM-BOOST

Wadud, Md. Anwar Hussen; Kabir, Md. Mohsin; Mridha, M. F.; Ali, Mohsan; Hamid, Md. Abdul; Monowar, Muhammad Mostafa

doi:10.1016/j.jjimei.2022.100095

Cited by 29 publications

(4 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…By combining contextual embeddings from advanced models such as BERT with LSTM layers, a balance is achieved between model performance and generalization, which emphasizes the current research focus on developing more robust and adaptable text classification systems [34]. Figure 1 illustrates the concept of unrolling a loop in the context of RNNs [35], showcasing their efficiency in modeling sequential data, including textual content, with promising results; however, RNNs face challenges when long-term memory is crucial for problem-solving, such as in scenarios requiring the prediction of words in lengthy sentences where key information begins to fade as the sequence progresses. This situation can lead to a significant increase in the gap between necessary information and its point of use.…”

Section: Nlp Models: Rnn and Lstmmentioning

confidence: 99%

Beyond Word-Based Model Embeddings: Contextualized Representations for Enhanced Social Media Spam Detection

Alshattnawi,

Shatnawi,

AlSobeh

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

As social media platforms continue their exponential growth, so do the threats targeting their security. Detecting disguised spam messages poses an immense challenge owing to the constant evolution of tactics. This research investigates advanced artificial intelligence techniques to significantly enhance multiplatform spam classification on Twitter and YouTube. The deep neural networks we use are state-of-the-art. They are recurrent neural network architectures with long- and short-term memory cells that are powered by both static and contextualized word embeddings. Extensive comparative experiments precede rigorous hyperparameter tuning on the datasets. Results reveal a profound impact of tailored, platform-specific AI techniques in combating sophisticated and perpetually evolving threats. The key innovation lies in tailoring deep learning (DL) architectures to leverage both intrinsic platform contexts and extrinsic contextual embeddings for strengthened generalization. The results include consistent accuracy improvements of more than 10–15% in multisource datasets, unlocking actionable guidelines on optimal components of neural models, and embedding strategies for cross-platform defense systems. Contextualized embeddings like BERT and ELMo consistently outperform their noncontextualized counterparts. The standalone ELMo model with logistic regression emerges as the top performer, attaining exceptional accuracy scores of 90% on Twitter and 94% on YouTube data. This signifies the immense potential of contextualized language representations in capturing subtle semantic signals vital for identifying disguised spam. As emerging adversarial attacks exploit human vulnerabilities, advancing defense strategies through enhanced neural language understanding is imperative. We recommend that social media companies and academic researchers build on contextualized language models to strengthen social media security. This research approach demonstrates the immense potential of personalized, platform-specific DL techniques to combat the continuously evolving threats that threaten social media security.

show abstract

Section: Nlp Models: Rnn and Lstmmentioning

confidence: 99%

Beyond Word-Based Model Embeddings: Contextualized Representations for Enhanced Social Media Spam Detection

Alshattnawi,

Shatnawi,

AlSobeh

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…Adaptive boosting [16] (AdaBoost) is a common type of integrated learning algorithm boosting class, first applied to classification problems and gradually used in regression tasks as the algorithm evolves [17]. AdaBoost's key feature is its adaptability.…”

Section: Adaptive Enhancement Algorithmmentioning

confidence: 99%

Prediction Model of Ammonia Nitrogen Concentration in Aquaculture Based on Improved AdaBoost and LSTM

Wang,

Xu,

et al. 2024

Mathematics

View full text Add to dashboard Cite

The concentration of ammonia nitrogen is significant for intensive aquaculture, and if the concentration of ammonia nitrogen is too high, it will seriously affect the survival state of aquaculture. Therefore, prediction and control of the ammonia nitrogen concentration in advance is essential. This paper proposed a combined model based on X Adaptive Boosting (XAdaBoost) and the Long Short-Term Memory neural network (LSTM) to predict ammonia nitrogen concentration in mariculture. Firstly, the weight assignment strategy was improved, and the number of correction iterations was introduced to retard the shortcomings of data error accumulation caused by the AdaBoost basic algorithm. Then, the XAdaBoost algorithm generated and combined several LSTM su-models to predict the ammonia nitrogen concentration. Finally, there were two experiments conducted to verify the effectiveness of the proposed prediction model. In the ammonia nitrogen concentration prediction experiment, compared with the LSTM and other comparison models, the RMSE of the XAdaBoost–LSTM model was reduced by about 0.89–2.82%, the MAE was reduced by about 0.72–2.47%, and the MAPE was reduced by about 8.69–18.39%. In the model stability experiment, the RMSE, MAE, and MAPE of the XAdaBoost–LSTM model decreased by about 1–1.5%, 0.7–1.7%, and 7–14%. From these two experiments, the evaluation indexes of the XAdaBoost–LSTM model were superior to the comparison models, which proves that the model has good prediction accuracy and stability and lays a foundation for monitoring and regulating the change of ammonia nitrogen concentration in the future.

show abstract

“…Personal recommendation and learning system adaptability research are currently in the early stages of weak artificial intelligence [27,28]. is is not ideal for the personalized learning needs of English audio-visual courses because of the limitations of weak artificial intelligence [29,30].…”

Section: Related Workmentioning

confidence: 99%

A Personalized Recommendation System for English Teaching Resources Based on Learning Behavior Detection

Yuanfei

2022

Mobile Information Systems

View full text Add to dashboard Cite

When confronted with a plethora of resources, many students struggle to quickly filter out the content that is relevant to them. Because there are many English teaching resources and it is difficult to accurately recommend suitable teaching resources for students. Therefore, in this paper we suggest a personalized recommendation system for English teaching resources, which is founded on learning behavior detection. To begin with, a spatiotemporal convolutional network is introduced to effectively identify students’ online classroom behavior, and a global attention module is added to increase the model’s ability to learn global feature information. Furthermore, the identified characteristics of student behavior are incorporated into the recommendation module. Similarly, the differential evolution (DE) algorithm is implemented to the smoothing factor and kernel function center of a generalized regression neural network (CRNN) for resource recommendation mode, while taking into account the strong dependence of the GRNN training effect on the smoothing factor and the kernel function center. The smoothing factor and offset factor are optimized and solved, and the optimized smoothing factor and offset factor are used to recommend GRNN resources. Experiments show that the approach described in this work first has a high precision (i.e., 90.98%) in behavior recognition, and second, the recommendation performance is superior to both of the comparison algorithms (i.e., 85.23% and 78.33%), resulting in better resource recommendation accuracy. The fundamental goal of this work is to deliver several important guidelines for the informatization and intelligence of the English educational resources and services.

show abstract

How can we manage Offensive Text in Social Media - A Text Classification Approach using LSTM-BOOST

Cited by 29 publications

References 43 publications

Beyond Word-Based Model Embeddings: Contextualized Representations for Enhanced Social Media Spam Detection

Beyond Word-Based Model Embeddings: Contextualized Representations for Enhanced Social Media Spam Detection

Prediction Model of Ammonia Nitrogen Concentration in Aquaculture Based on Improved AdaBoost and LSTM

A Personalized Recommendation System for English Teaching Resources Based on Learning Behavior Detection

Contact Info

Product

Resources

About