Analysis of Text Feature Extractors using Deep Learning on Fake News

Ahmed, Basem H.; Ghazanfar, Ali; Hussain, Abid; Baseer, Abdul; Ahmed, Javed

doi:10.48084/etasr.4069

Cited by 12 publications

(4 citation statements)

References 17 publications

(17 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…By using supervised learning, many traditional techniques were applied [10][11][12][13] or more advanced, using pre-trained models, specifically BERT and its improved models such as M-BERT, XLM-R, etc. MTL is an approach that achieves the generalization of results by using the inductive transfer method [14].…”

Section: B Paraphrase Identification Methodsmentioning

confidence: 99%

See 1 more Smart Citation

English-Vietnamese Cross-Lingual Paraphrase Identification Using MT-DNN

Anh

Thanh

et al. 2021

Eng. Technol. Appl. Sci. Res.

View full text Add to dashboard Cite

Paraphrase identification is a crucial task in natural language understanding, especially in cross-language information retrieval. Nowadays, Multi-Task Deep Neural Network (MT-DNN) has become a state-of-the-art method that brings outstanding results in paraphrase identification [1]. In this paper, our proposed method based on MT-DNN [2] to detect similarities between English and Vietnamese sentences, is proposed. We changed the shared layers of the original MT-DNN from original the BERT [3] to other pre-trained multi-language models such as M-BERT [3] or XLM-R [4] so that our model could work on cross-language (in our case, English and Vietnamese) information retrieval. We also added some tasks as improvements to gain better results. As a result, we gained 2.3% and 2.5% increase in evaluated accuracy and F1. The proposed method was also implemented on other language pairs such as English – German and English – French. With those implementations, we got a 1.0%/0.7% improvement for English – German and a 0.7%/0.5% increase for English – French.

show abstract

Section: B Paraphrase Identification Methodsmentioning

confidence: 99%

“…BERT was trained on 2 main tasks: MLM (Masked Language Modeling) and NSP (Next Sentence Prediction). BERT has been applied in many applications [9,10]. M-BERT is a single language model pre-trained from 104 languages (including English and Vietnamese).…”

Section: A Pre-trained Model and Transfer Learningmentioning

confidence: 99%

English-Vietnamese Cross-Lingual Paraphrase Identification Using MT-DNN

Anh

Thanh

et al. 2021

Eng. Technol. Appl. Sci. Res.

View full text Add to dashboard Cite

show abstract

“…After looping through the contours, the rectangular part is cropped and passed to the Optical Character Recognition (OCR) system [17] for text extraction. With the deep learning approach, text is extracted with better accuracy [25]. Figure 10 shows some sample results of text extraction.…”

Section: Caption Generation With Text Extraction (Phase Iii)mentioning

confidence: 99%

D-CNN: A New model for Generating Image Captions with Text Extraction Using Deep Learning for Visually Challenged Individuals

Bhalekar

Bedekar

2022

Eng. Technol. Appl. Sci. Res.

View full text Add to dashboard Cite

Automatically describing the information of an image using properly constructed sentences is a tricky task in any language. However, it has the potential to have a significant effect by enabling visually challenged individuals to better understand their surroundings. This paper proposes an image captioning system that generates detailed captions and extracts text from an image, if any, and uses it as a part of the caption to provide a more precise description of the image. To extract the image features, the proposed model uses Convolutional Neural Networks (CNNs) followed by Long Short-Term Memory (LSTM) that generates corresponding sentences based on the learned image features. Further, using the text extraction module, the extracted text (if any) is included in the image description and the captions are presented in audio form. Publicly available benchmark datasets for image captioning like MS COCO, Flickr-8k, Flickr-30k have a variety of images, but they hardly have images that contain textual information. These datasets are not sufficient for the proposed model and this has resulted in the creation of a new image caption dataset that contains images with textual content. With the newly created dataset, comparative analysis of the experimental results is performed on the proposed model and the existing pre-trained model. The obtained experimental results show that the proposed model is equally effective as the existing one in subtitle image captioning models and provides more insights about the image by performing text extraction.

show abstract

“…There are several fact-checking websites being operated overseas, but it is very insufficient compared to the amount of fake news being created. In spite of the insufficiency, research is ongoing on fake news detection using the data provided by fact-checking websites [5,6].…”

Section: Introductionmentioning

confidence: 99%

Fake Sentence Detection Based on Transfer Learning: Applying to Korean COVID-19 Fake News

Lee

Kim

2022

Applied Sciences

View full text Add to dashboard Cite

With the increasing number of social media users in recent years, news in various fields, such as politics, economics, and so on, can be easily accessed by users. However, most news spread through social networks including Twitter, Facebook, and Instagram has unknown sources, thus having a significant impact on news consumers. Fake news on COVID-19, which is affecting the global population, is propagating quickly and causes social disorder. Thus, a lot of research is being conducted on the detection of fake news on COVID-19 but is facing the problem of a lack of datasets. In order to alleviate the problem, we built a dataset on COVID-19 fake news from fact-checking websites in Korea and propose deep learning for detecting fake news on COVID-19 using the datasets. The proposed model is pre-trained with large-scale data and then performs transfer learning through a BiLSTM model. Moreover, we propose a method for initializing the hidden and cell states of the BiLSTM model to a [CLS] token instead of a zero vector. Through experiments, the proposed model showed that the accuracy is 78.8%, which was improved by 8% compared with the linear model as a baseline model, and that transfer learning can be useful with a small amount of data as we know it. A [CLS] token containing sentence information as the initial state of the BiLSTM can contribute to a performance improvement in the model.

show abstract

Analysis of Text Feature Extractors using Deep Learning on Fake News

Cited by 12 publications

References 17 publications

English-Vietnamese Cross-Lingual Paraphrase Identification Using MT-DNN

English-Vietnamese Cross-Lingual Paraphrase Identification Using MT-DNN

D-CNN: A New model for Generating Image Captions with Text Extraction Using Deep Learning for Visually Challenged Individuals

Fake Sentence Detection Based on Transfer Learning: Applying to Korean COVID-19 Fake News

Contact Info

Product

Resources

About