Rapid bibliometric analysis in deep learning domain

Mukhamediev, Ravil I.; Assanov, Ilyas; Yelis, Marina; Сымагулов, Адилхан; Kuchin, Yan; Yakunin, Kirill; Aubakirov, Margulan; Tabynbayeva, Laila; Sedlaček, Peter

doi:10.1109/idt52577.2021.9497591

Cited by 1 publication

(1 citation statement)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We selected their study as the second baseline for comparison. Other approaches include a spinning language model ( Bagdasaryan & Shmatikov, 2021 ), mixed-code text with deep learning ( Tundis, Mukherjee & Mühlhäuser, 2021 ), topic-modeling with fuzzy logic ( Mukhamediev, Filatova & Yakunin, 2021 ), visual and textual content with a balanced dataset ( Guo & Vosoughi, 2021 ), linguistic features ( Barfar, 2022 ) and fake news ( Huang et al, 2022 ). The summary of related studies is presented in Table S1 .…”

Section: Related Workmentioning

confidence: 99%

How to detect propaganda from social media? Exploitation of semantic and fine-tuned language models

Malik

Imran

Mamdouh

2023

PeerJ Computer Science

View full text Add to dashboard Cite

Online propaganda is a mechanism to influence the opinions of social media users. It is a growing menace to public health, democratic institutions, and public society. The present study proposes a propaganda detection framework as a binary classification model based on a news repository. Several feature models are explored to develop a robust model such as part-of-speech, LIWC, word uni-gram, Embeddings from Language Models (ELMo), FastText, word2vec, latent semantic analysis (LSA), and char tri-gram feature models. Moreover, fine-tuning of the BERT is also performed. Three oversampling methods are investigated to handle the imbalance status of the Qprop dataset. SMOTE Edited Nearest Neighbors (ENN) presented the best results. The fine-tuning of BERT revealed that the BERT-320 sequence length is the best model. As a standalone model, the char tri-gram presented superior performance as compared to other features. The robust performance is observed against the combination of char tri-gram + BERT and char tri-gram + word2vec and they outperformed the two state-of-the-art baselines. In contrast to prior approaches, the addition of feature selection further improves the performance and achieved more than 97.60% recall, f1-score, and AUC on the dev and test part of the dataset. The findings of the present study can be used to organize news articles for various public news websites.

show abstract