Search

The explosive growth of the social media community has increased many kinds of misinformation and is attracting tremendous attention from the research community. One of the most prevalent ways of misleading news is cheapfakes. Cheapfakes utilize non-AI techniques such as unaltered images with false context news to create false news, which makes it easy and "cheap" to create and leads to an abundant amount in the social media community. Moreover, the development of deep learning also opens and invents many domains relevant to news such as fake news detection, rumour detection, fact-checking, and verification of claimed images. Nevertheless, despite the impact on and harmfulness of cheapfakes for the social community and the real world, there is little research on detecting cheapfakes in the computer science domain. It is challenging to detect misused/false/out-of-context pairs of images and captions, even with human effort, because of the complex correlation between the attached image and the veracity of the caption content. Existing research focuses mostly on training and evaluating on given dataset, which makes the proposal limited in terms of categories, semantics and situations based on the characteristics of the dataset. In this paper, to address these issues, we aimed to leverage textual semantics understanding from the large corpus and integrated with different combinations of text-image matching and image captioning methods via ANN/Transformer boosting schema to classify a triple of (image, caption1, caption2) into OOC (out-of-context) and NOOC (no out-of-context) labels. We customized these combinations according to various exceptional cases that we observed during data analysis. We evaluate our approach using the dataset and evaluation metrics provided by the COSMOS baseline. Compared to other methods, including the baseline, our method achieves the highest Accuracy, Recall, and F1 scores. [ABSTRACT FROM AUTHOR]

With the increased popularity of social media platforms such as Twitter or Facebook, sentiment analysis (SA) over the microblogging content becomes of crucial importance. The literature reports good results for well-resourced languages such as English, Spanish or German, but open research space still exists for underrepresented languages such as Romanian, where there is a lack of public training datasets or pretrained word embeddings. The majority of research on Romanian SA tackles the issue in a binary classification manner (positive vs. negative), using a single public dataset which consists of product reviews. In this paper, we respond to the need for a media surveillance project to possess a custom multinomial SA classifier for usage in a restrictive and specific production setup. We describe in detail how such a classifier was built, with the help of an English dataset (containing around 15 , 000 tweets) translated to Romanian with a public translation service. We test the most popular classification methods that could be applied to SA, including standard machine learning, deep learning and BERT. As we could not find any results for multinomial sentiment classification (positive, negative and neutral) in Romanian, we set two benchmark accuracies of ≈78% using standard machine learning and ≈81% using BERT. Furthermore, we demonstrate that the automatic translation service does not downgrade the learning performance by comparing the accuracies achieved by the models trained on the original dataset with the models trained on the translated data. [ABSTRACT FROM AUTHOR]

Deep learning, with increasingly large datasets and complex neural networks, is widely used in computer vision and natural language processing. A resulting trend is to split and train large-scale neural network models across multiple devices in parallel, known as parallel model training. Existing parallel methods are mainly based on expert design, which is inefficient and requires specialized knowledge. Although automatically implemented parallel methods have been proposed to solve these problems, these methods only consider a single optimization aspect of run time. In this paper, we present Trinity, an adaptive distributed parallel training method based on reinforcement learning, to automate the search and tuning of parallel strategies. We build a multidimensional performance evaluation model and use proximal policy optimization to co-optimize multiple optimization aspects. Our experiment used the CIFAR10 and PTB datasets based on InceptionV3, NMT, NASNet and PNASNet models. Compared with Google's Hierarchical method, Trinity achieves up to 5% reductions in runtime, communication, and memory overhead, and up to a 40% increase in parallel strategy search speeds. [ABSTRACT FROM AUTHOR]

First-order algorithms have long dominated the training of deep neural networks, excelling in tasks like image classification and natural language processing. Now there is a compelling opportunity to explore alternatives that could outperform current state-of-the-art results. From the estimation theory, the Extended Kalman Filter (EKF) arose as a viable alternative and has shown advantages over backpropagation methods. Current computational advances offer the opportunity to review algorithms derived from the EKF, almost excluded from the training of convolutional neural networks. This article revisits an approach of the EKF with decoupling and it brings the Fully Decoupled Extended Kalman Filter (FDEKF) for training convolutional neural networks in image classification tasks. The FDEKF is a second-order algorithm with some advantages over the first-order algorithms, so it can lead to faster convergence and higher accuracy, due to a higher probability of finding the global optimum. In this research, experiments are conducted on well-known datasets that include Fashion, Sports, and Handwritten Digits images. The FDEKF shows faster convergence compared to other algorithms such as the popular Adam optimizer, the sKAdam algorithm, and the reduced extended Kalman filter. Finally, motivated by the finding of the highest accuracy of FDEKF with images of natural scenes, we show its effectiveness in another experiment focused on outdoor terrain recognition. [ABSTRACT FROM AUTHOR]

Deep learning uses artificial neural networks to recognize patterns and learn from them to make decisions. Deep learning is a type of machine learning that uses artificial neural networks to mimic the human brain. It uses machine learning methods such as supervised, semi-supervised, or unsupervised learning strategies to learn automatically in deep architectures and has gained much popularity due to its superior ability to learn from huge amounts of data. It was found that deep learning approaches can be used for big data analysis successfully. Applications include virtual assistants such as Alexa and Siri, facial recognition, personalization, natural language processing, autonomous cars, automatic handwriting generation, news aggregation, the colorization of black and white images, the addition of sound to silent films, pixel restoration, and deep dreaming. As a review, this paper aims to categorically cover several widely used deep learning algorithms along with their architectures and their practical applications: backpropagation, autoencoders, variational autoencoders, restricted Boltzmann machines, deep belief networks, convolutional neural networks, recurrent neural networks, generative adversarial networks, capsnets, transformer, embeddings from language models, bidirectional encoder representations from transformers, and attention in natural language processing. In addition, challenges of deep learning are also presented in this paper, such as AutoML-Zero, neural architecture search, evolutionary deep learning, and others. The pros and cons of these algorithms and their applications in healthcare are explored, alongside the future direction of this domain. This paper presents a review and a checkpoint to systemize the popular algorithms and to encourage further innovation regarding their applications. For new researchers in the field of deep learning, this review can help them to obtain many details about the advantages, disadvantages, applications, and working mechanisms of a number of deep learning algorithms. In addition, we introduce detailed information on how to apply several deep learning algorithms in healthcare, such as in relation to the COVID-19 pandemic. By presenting many challenges of deep learning in one section, we hope to increase awareness of these challenges, and how they can be dealt with. This could also motivate researchers to find solutions for these challenges. [ABSTRACT FROM AUTHOR]

Sentiment analysis holds great importance within the domain of natural language processing as it examines both the expressed and underlying emotions conveyed through review content. Furthermore, researchers have discovered that relying solely on the overall sentiment derived from the textual content is inadequate. Consequently, sentiment analysis was developed to extract nuanced expressions from textual information. One of the challenges in this field is effectively extracting emotional elements using multi-label data that covers various aspects. This article presents a novel approach called the Ensemble of DenseNet based on Aquila Optimizer (EDAO). EDAO is specifically designed to enhance the precision and diversity of multi-label learners. Unlike traditional multi-label methods, EDAO strongly emphasizes improving model diversity and accuracy in multi-label scenarios. To evaluate the effectiveness of our approach, we conducted experiments on seven distinct datasets, including emotions, hotels, movies, proteins, automobiles, medical, news, and birds. Our initial strategy involves establishing a preprocessing mechanism to obtain precise and refined data. Subsequently, we used the Vader tool with Bag of Words (BoW) for feature extraction. In the third stage, we created word associations using the word2vec method. The improved data were also used to train and test the DenseNet model, which was fine-tuned using the Aquila Optimizer (AO). On the news, emotion, auto, bird, movie, hotel, protein, and medical datasets, utilizing the aspect-based multi-labeling technique, we achieved accuracy rates of 95%, 97%, and 96%, respectively, with DenseNet-AO. Our proposed model demonstrates that EDAO outperforms other standard methods across various multi-label datasets with different dimensions. The implemented strategy has been rigorously validated through experimental results, showcasing its effectiveness compared to existing benchmark approaches. [ABSTRACT FROM AUTHOR]

In this research, we present an algorithm that leverages language-transformer technologies to automate the generation of product requirements, utilizing E-Shop consumer reviews as a data source. Our methodology combines classical natural language processing techniques with diverse functions derived from transformer concepts, including keyword and summary generation. To effectively capture the most critical requirements, we employ the opportunity matrix as a robust mechanism for identifying and prioritizing urgent needs. Utilizing transformer technologies, mainly through the implementation of summarization and sentiment analysis, we can extract fundamental requirements from consumer assessments. As a practical demonstration, we apply our technology to analyze the ratings of the Amazon echo dot, showcasing our algorithm's superiority over conventional approaches by extracting human-readable problem descriptions to identify critical user needs. The results of our study exemplify the potential of transformer-enhanced opportunity mining in advancing the requirements-elicitation processes. Our approach streamlines product improvement by extracting human-readable problem descriptions from E-Shop consumer reviews, augmenting operational efficiency, and facilitating decision-making. These findings underscore the transformative impact of incorporating transformer technologies within requirements engineering, paving the way for more effective and scalable algorithms to elicit and address user needs. [ABSTRACT FROM AUTHOR]

Arabic text classification is a process to simultaneously categorize the different contextual Arabic contents into a proper category. In this paper, a novel deep learning Arabic text computer-aided recognition (ArCAR) is proposed to represent and recognize Arabic text at the character level. The input Arabic text is quantized in the form of 1D vectors for each Arabic character to represent a 2D array for the ArCAR system. The ArCAR system is validated over 5-fold cross-validation tests for two applications: Arabic text document classification and Arabic sentiment analysis. For document classification, the ArCAR system achieves the best performance using the Alarabiya-balance dataset in terms of overall accuracy, recall, precision, and F1-score by 97.76%, 94.08%, 94.16%, and 94.09%, respectively. Meanwhile, the ArCAR performs well for Arabic sentiment analysis, achieving the best performance using the hotel Arabic reviews dataset (HARD) balance dataset in terms of overall accuracy and F1-score by 93.58% and 93.23%, respectively. The proposed ArCAR seems to provide a practical solution for accurate Arabic text representation, understanding, and classification. [ABSTRACT FROM AUTHOR]

Text classification is widely studied in natural language processing (NLP). Deep learning models, including large pre-trained models like BERT and DistilBERT, have achieved impressive results in text classification tasks. However, these models' robustness against adversarial attacks remains an area of concern. To address this concern, we propose three data augmentation methods to improve the robustness of such pre-trained models. We evaluated our methods on four text classification datasets by fine-tuning DistilBERT on the augmented datasets and exposing the resulting models to adversarial attacks to evaluate their robustness. In addition to enhancing the robustness, our proposed methods can improve the accuracy and F1-score on three datasets. We also conducted comparison experiments with two existing data augmentation methods. We found that one of our proposed methods demonstrates a similar improvement in terms of performance, but all demonstrate a superior robustness improvement. [ABSTRACT FROM AUTHOR]