Deep Learning for predicting neutralities in Offensive Language Identification Dataset

Sharma, Mayukh; Kandasamy, Ilanthenral; Kandasamy, W. B. Vasantha

doi:10.1016/j.eswa.2021.115458

Cited by 20 publications

(3 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Learning architecture can be designed to perform several tasks, such as classification, identification, and prediction [33]. Deep learning enables predictive serving using a neural network architecture consisting of several layers [34].…”

Section: Deep Learningmentioning

confidence: 99%

Prediction of Drug Demand Based on Deep Learning Approach and Classification Model

Yanto¹,

Arlis²,

Putra³

et al. 2023

Int. J. Adv. Sci. Eng. Inf. Technol.

View full text Add to dashboard Cite

The high demand for drugs in the last period has caused problems with drug shortages in several pharmacies. Almost all pharmacies experience the same problem, causing many people who do not to get their drug needs during the current pandemic. To overcome this, analyzing the process of predicting drug demand in the next period is necessary. The prediction process can be used as an initial solution in solving problems to see the number of drug demand numbers that will occur. This study aims to develop a predictive analysis model for drug demand using a deep learning approach and a classification model. Deep learning is an approach that does well in the case of prediction. The classification model also includes the right concept for solving the problem. The prediction and classification analysis methods include K-Means clustering, Multiple Linear Regression (MRL), Artificial Neural Network (ANN), and Decision Tree algorithms C.45. This method can provide better performance results in the prediction process to get precise and accurate output. Prediction results obtained from the learning process provide an accuracy rate of 99.99%. The output of the classification model also provides an overview of the knowledge base in the form of a decision tree. The level of classification model testing carried out gives the accuracy of the classification pattern of 97.05% so that the analytical model developed can predict future drug demand.

show abstract

Section: Deep Learningmentioning

confidence: 99%

Prediction of Drug Demand Based on Deep Learning Approach and Classification Model

Yanto¹,

Arlis²,

Putra³

et al. 2023

Int. J. Adv. Sci. Eng. Inf. Technol.

View full text Add to dashboard Cite

show abstract

“…Ancak bazı tanımlar, bu çalışmadan farklılıklar göstermektedir. Bununla birlikte saldırgan dil ile ilgili tanımlamaların kullanılan öğrenme yöntemlerin performansını iyileştirici etkisi olduğunu bilinmektedir [43].…”

Section: Veri Setinin Etiketlenmesiunclassified

Twitter Platformundan Elde Edilen Türkçe Saldırgan Dil Derlemi

YILMAZ

Özer

Gökçen³

2022

Mühendislik Bilimleri Ve Araştırmaları Dergisi

View full text Add to dashboard Cite

Sosyal medya platformlarında kullanıcıların paylaşımlar arasında saldırgan dil barındıran içeriklerin önemli oranda arttığı gözlemlenmiştir. Çalışma Türkçe dilinde bu sorunun çözümüne katkı sağlamayı amaçlamaktadır. Bu çalışmada Twitter platformundan elde edilen bir veri seti oluşturulmuştur. 14752 Türkçe tweet metninden oluşan bu veri seti etiketleyiciler tarafından manuel olarak etiketlenmiştir. Buna ek olarak oluşturulan veri seti kullanılarak LSTM (Long ShortTerm Memory) ve GRU (Gated Recurrent Units) modellerinin sınıflandırma performansları karşılaştırılmıştır. Çalışmada ikili ve çoklu sınıflandırma yapılmıştır. Saldırgan dil ile ilgili Türkçe için çoklu sınıflandırma yapılan ilk çalışmadır. Bunlara ek olarak Twitter platformundan 1 milyon 860 bin tweet metninden oluşan genişletilmiş derlem elde edilmiştir. Burada word2vec yöntemi ile kelime temsilleri elde edilmiştir. Böylelikle genişletilmiş derlem kullanımının sınıflandırma performanslarına katkısı karşılaştırılmıştır. Çalışmada yapılan ikili sınıflandırma da genişletilmiş derlem kullanımıyla en yüksek performans GRU modeli F1-skor değeri %94,49’dur. Bu sebeple çoklu sınıflandırma yapılırken GRU modeli kullanılmıştır. Çoklu sınıflandırmada elde edilen sınıflandırma performans değerleri genişletilmiş derlemin katkısıyla GRU F1-makro değeri %71,97 ve %54,10’dur. Bu alanda Türk dili literatürüne katkı sağlamak amacıyla mevcut çalışmanın veri setleri ve genişletilmiş derlem kelime vektörleri paylaşılacaktır.

show abstract

“…In recent times there has been an exponential rise in hateful content and, in particular, the phenomenon of hate against women on social media (Pamungkas et al, 2020) (Hewitt et al, 2016). There have been previous attempts to identify hate/toxic content on social media platforms ( (Zampieri et al, 2019) (Sharma et al, 2021a) (Pavlopoulos et al, 2021) but none deal specifically with identifying the hate against women. The first benchmark dataset to identify misogynous con-1 https://github.com/04mayukh/ R2D2-at-SemEval-2022-Task-5-MAMI tent was proposed in .…”

Section: Introductionmentioning

confidence: 99%

R2D2 at SemEval-2022 Task 5: Attention is only as good as its Values! A multimodal system for identifying misogynist memes

Sharma¹,

Kandasamy²,

Vasantha³

2022

Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022)

Self Cite

View full text Add to dashboard Cite

This paper describes the multimodal deep learning system proposed for SemEval 2022 Task 5: MAMI -Multimedia Automatic Misogyny Identification. We participated in both Subtasks, i.e. Subtask A: Misogynous meme identification, and Subtask B: Identifying type of misogyny among potential overlapping categories (stereotype, shaming, objectification, violence). The proposed architecture uses pretrained models as feature extractors for text and images. We use these features to learn multimodal representation using methods like concatenation and scaled dot product attention. Classification layers are used on fused features as per the subtask definition. We also performed experiments using unimodal models for setting up comparative baselines. Our best performing system achieved an F1 score of 0.757 and was ranked 3 rd in Subtask A. On Subtask B, our system performed well with an F1 score of 0.690 and was ranked 10 th on the leaderboard. We further show extensive experiments using combinations of different pre-trained models which will be helpful as baselines for future work.

show abstract

Deep Learning for predicting neutralities in Offensive Language Identification Dataset

Cited by 20 publications

References 20 publications

Prediction of Drug Demand Based on Deep Learning Approach and Classification Model

Prediction of Drug Demand Based on Deep Learning Approach and Classification Model

Twitter Platformundan Elde Edilen Türkçe Saldırgan Dil Derlemi

R2D2 at SemEval-2022 Task 5: Attention is only as good as its Values! A multimodal system for identifying misogynist memes

Contact Info

Product

Resources

About