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

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 ].

Increasing Strength of Sub-grade Layer of Pavement using Geo-grid

This Paper describes the beneficial impact of reinforcing the sub-grade layer with a single layerof geo-grid at different positions and thereby determination of optimum position of reinforcement layer. The( best) optimum position was determined based on California Bearing Ratio (CBR value) and unconfined compression tests were conducted to decide the optimum position of geo-grid. The CBR value of a soil increases by 50-100% when it is reinforced with a single layer of geogrid. The amount of development (Improvement) depends upon the type of soil and position of geo-grid. CBR of sub-grade soil is 6.53% without reinforcement and when geo-grid was placed at 0.2H from the top, the CBR value increased to 19.66%. Soaked Condition CBR of sub-grade soil is 4.77% without reinforcement and when geo-grid was placed at 0.2H from the top, the CBR value increased to 4.46%. Keywords: Pavement, Geo-grid, Reinforced, Sub-grade, CBR, Filtration, Reinforcing

Aluminum Doping Effect on Surface Structure of Silver Ultrathin Films

Ultrathin silver films with low loss in the visible and near-infrared spectrum range have been widely used in the fields of metamaterials and optoelectronics. In this study, Al-doped silver films were prepared by the magnetron sputtering method and were characterized by surface morphology, electrical conductivity, and light transmittance analyses. Molecular dynamics simulations and first-principles density functional theory calculations were applied to study the surface morphologies and migration pathway for the formation mechanisms in Al-doped silver films. The results indicate that the migration barrier of silver on a pristine silver surface is commonly lower than that of an Al-doped surface, revealing that the aluminum atoms in the doping site decrease the surface mobility and are conducive to the formation of small islands of silver. When the islands are dense, they coalesce into a single layer, leading to a smoother surface. This might be the reason for the observably lower 3D growth mode of silver on an Al-doped silver surface. Our results with electronic structure insights on the mechanism of the Al dopants on surface morphologies might benefit the quality control of the silver thin films.