Persian Fake News Detection: Neural Representation and Classification at Word and Text Levels

Author(s):  
Mohammadreza Samadi ◽  
Maryam Mousavian ◽  
Saeedeh Momtazi

Nowadays, broadcasting news on social media and websites has grown at a swifter pace, which has had negative impacts on both the general public and governments; hence, this has urged us to build a fake news detection system. Contextualized word embeddings have achieved great success in recent years due to their power to embed both syntactic and semantic features of textual contents. In this article, we aim to address the problem of the lack of fake news datasets in Persian by introducing a new dataset crawled from different news agencies, and propose two deep models based on the Bidirectional Encoder Representations from Transformers model (BERT), which is a deep contextualized pre-trained model for extracting valuable features. In our proposed models, we benefit from two different settings of BERT, namely pool-based representation, which provides a representation for the whole document, and sequence representation, which provides a representation for each token of the document. In the former one, we connect a Single Layer Perceptron (SLP) to the BERT to use the embedding directly for detecting fake news. The latter one uses Convolutional Neural Network (CNN) after the BERT’s embedding layer to extract extra features based on the collocation of words in a corpus. Furthermore, we present the TAJ dataset, which is a new Persian fake news dataset crawled from news agencies’ websites. We evaluate our proposed models on the newly provided TAJ dataset as well as the two different Persian rumor datasets as baselines. The results indicate the effectiveness of using deep contextualized embedding approaches for the fake news detection task. We also show that both BERT-SLP and BERT-CNN models achieve superior performance to the previous baselines and traditional machine learning models, with 15.58% and 17.1% improvement compared to the reported results by Zamani et al. [ 30 ], and 11.29% and 11.18% improvement compared to the reported results by Jahanbakhsh-Nagadeh et al. [ 9 ].

2021 ◽  
Vol 13 (14) ◽  
pp. 2656
Author(s):  
Furong Shi ◽  
Tong Zhang

Deep-learning technologies, especially convolutional neural networks (CNNs), have achieved great success in building extraction from areal images. However, shape details are often lost during the down-sampling process, which results in discontinuous segmentation or inaccurate segmentation boundary. In order to compensate for the loss of shape information, two shape-related auxiliary tasks (i.e., boundary prediction and distance estimation) were jointly learned with building segmentation task in our proposed network. Meanwhile, two consistency constraint losses were designed based on the multi-task network to exploit the duality between the mask prediction and two shape-related information predictions. Specifically, an atrous spatial pyramid pooling (ASPP) module was appended to the top of the encoder of a U-shaped network to obtain multi-scale features. Based on the multi-scale features, one regression loss and two classification losses were used for predicting the distance-transform map, segmentation, and boundary. Two inter-task consistency-loss functions were constructed to ensure the consistency between distance maps and masks, and the consistency between masks and boundary maps. Experimental results on three public aerial image data sets showed that our method achieved superior performance over the recent state-of-the-art models.


Author(s):  
Jie Lian ◽  
Xu Yuan ◽  
Ming Li ◽  
Nian-Feng Tzeng

The fall detection system is of critical importance in protecting elders through promptly discovering fall accidents to provide immediate medical assistance, potentially saving elders' lives. This paper aims to develop a novel and lightweight fall detection system by relying solely on a home audio device via inaudible acoustic sensing, to recognize fall occurrences for wide home deployment. In particular, we program the audio device to let its speaker emit 20kHz continuous wave, while utilizing a microphone to record reflected signals for capturing the Doppler shift caused by the fall. Considering interferences from different factors, we first develop a set of solutions for their removal to get clean spectrograms and then apply the power burst curve to locate the time points at which human motions happen. A set of effective features is then extracted from the spectrograms for representing the fall patterns, distinguishable from normal activities. We further apply the Singular Value Decomposition (SVD) and K-mean algorithms to reduce the data feature dimensions and to cluster the data, respectively, before input them to a Hidden Markov Model for training and classification. In the end, our system is implemented and deployed in various environments for evaluation. The experimental results demonstrate that our system can achieve superior performance for detecting fall accidents and is robust to environment changes, i.e., transferable to other environments after training in one environment.


2021 ◽  
Author(s):  
Lamya Alderywsh ◽  
Aseel Aldawood ◽  
Ashwag Alasmari ◽  
Farah Aldeijy ◽  
Ghadah Alqubisy ◽  
...  

BACKGROUND There is a serious threat from fake news spreading in technologically advanced societies, including those in the Arab world, via deceptive machine-generated text. In the last decade, Arabic fake news identification has gained increased attention, and numerous detection approaches have revealed some ability to find fake news throughout various data sources. Nevertheless, many existing approaches overlook recent advancements in fake news detection, explicitly to incorporate machine learning algorithms system. OBJECTIVE Tebyan project aims to address the problem of fake news by developing a fake news detection system that employs machine learning algorithms to detect whether the news is fake or real in the context of Arab world. METHODS The project went through numerous phases using an iterative methodology to develop the system. This study analysis incorporated numerous stages using an iterative method to develop the system of misinformation and contextualize fake news regarding society's information. It consists of implementing the machine learning algorithms system using Python to collect genuine and fake news datasets. The study also assesses how information-exchanging behaviors can minimize and find the optimal source of authentication of the emergent news through system testing approaches. RESULTS The study revealed that the main deliverable of this project is the Tebyan system in the community, which allows the user to ensure the credibility of news in Arabic newspapers. It showed that the SVM classifier, on average, exhibited the highest performance results, resulting in 90% in every performance measure of sources. Moreover, the results indicate the second-best algorithm is the linear SVC since it resulted in 90% in performance measure with the societies' typical type of fake information. CONCLUSIONS The study concludes that conducting a system with machine learning algorithms using Python programming language allows the rapid measures of the users' perception to comment and rate the credibility result and subscribing to news email services.


2018 ◽  
Vol 10 (12) ◽  
pp. 1934 ◽  
Author(s):  
Bao-Di Liu ◽  
Wen-Yang Xie ◽  
Jie Meng ◽  
Ye Li ◽  
Yanjiang Wang

In recent years, the collaborative representation-based classification (CRC) method has achieved great success in visual recognition by directly utilizing training images as dictionary bases. However, it describes a test sample with all training samples to extract shared attributes and does not consider the representation of the test sample with the training samples in a specific class to extract the class-specific attributes. For remote-sensing images, both the shared attributes and class-specific attributes are important for classification. In this paper, we propose a hybrid collaborative representation-based classification approach. The proposed method is capable of improving the performance of classifying remote-sensing images by embedding the class-specific collaborative representation to conventional collaborative representation-based classification. Moreover, we extend the proposed method to arbitrary kernel space to explore the nonlinear characteristics hidden in remote-sensing image features to further enhance classification performance. Extensive experiments on several benchmark remote-sensing image datasets were conducted and clearly demonstrate the superior performance of our proposed algorithm to state-of-the-art approaches.


2022 ◽  
Author(s):  
Jathin Badam ◽  
Akash Bonagiri ◽  
Kvln Raju ◽  
Dipanjan Chakraborty
Keyword(s):  

Materials ◽  
2020 ◽  
Vol 13 (9) ◽  
pp. 2029
Author(s):  
Tianyu Zhang ◽  
Asu Li ◽  
Ren Sheng ◽  
Mingyang Sun ◽  
Ping Chen

High-efficiency single-layer organic light-emitting diodes (OLEDs) based on a simple structure doped with iridium(III) bis(4-phenylthieno[3,2-c]pyridinato-N,C2′) acetylacetonate (PO-01) as emission dyes are realized, achieving maximum current efficiency (CE) and power efficiency (PE) of 37.1 cd A−1 and 33.3 lm W−1 as well as low turn-on voltage of 3.31 V. Such superior performance is mainly attributed to the employment of a uniform co-host structure and assisted charge transport property of phosphors dyes, which were in favor of the balance of charge carrier injection and transport in the single emitting layer (EML). Moreover, systematic researches on the position of exciton recombination region and the dopant effect on charge carriers were subsequently performed to better understand the operational mechanism. It could be experimentally found that the orange emitting dopants promoted the acceleration of the charge carriers transport and raised the exciton recombination efficiency, eventually leading to an excellent performance of single-layer OLEDs.


Sensors ◽  
2020 ◽  
Vol 20 (16) ◽  
pp. 4540
Author(s):  
Kieran Rendall ◽  
Antonia Nisioti ◽  
Alexios Mylonas

Phishing is one of the most common threats that users face while browsing the web. In the current threat landscape, a targeted phishing attack (i.e., spear phishing) often constitutes the first action of a threat actor during an intrusion campaign. To tackle this threat, many data-driven approaches have been proposed, which mostly rely on the use of supervised machine learning under a single-layer approach. However, such approaches are resource-demanding and, thus, their deployment in production environments is infeasible. Moreover, most previous works utilise a feature set that can be easily tampered with by adversaries. In this paper, we investigate the use of a multi-layered detection framework in which a potential phishing domain is classified multiple times by models using different feature sets. In our work, an additional classification takes place only when the initial one scores below a predefined confidence level, which is set by the system owner. We demonstrate our approach by implementing a two-layered detection system, which uses supervised machine learning to identify phishing attacks. We evaluate our system with a dataset consisting of active phishing attacks and find that its performance is comparable to the state of the art.


Sign in / Sign up

Export Citation Format

Share Document