Learning Sentence-to-Hashtags Semantic Mapping for Hashtag Recommendation on Microblogs

The growing use of microblogging platforms is generating a huge amount of posts that need effective methods to be classified and searched. In Twitter and other social media platforms, hashtags are exploited by users to facilitate the search, categorization, and spread of posts. Choosing the appropriate hashtags for a post is not always easy for users, and therefore posts are often published without hashtags or with hashtags not well defined. To deal with this issue, we propose a new model, called HASHET ( HAshtag recommendation using Sentence-to-Hashtag Embedding Translation ), aimed at suggesting a relevant set of hashtags for a given post. HASHET is based on two independent latent spaces for embedding the text of a post and the hashtags it contains. A mapping process based on a multi-layer perceptron is then used for learning a translation from the semantic features of the text to the latent representation of its hashtags. We evaluated the effectiveness of two language representation models for sentence embedding and tested different search strategies for semantic expansion, finding out that the combined use of BERT ( Bidirectional Encoder Representation from Transformer ) and a global expansion strategy leads to the best recommendation results. HASHET has been evaluated on two real-world case studies related to the 2016 United States presidential election and COVID-19 pandemic. The results reveal the effectiveness of HASHET in predicting one or more correct hashtags, with an average F -score up to 0.82 and a recommendation hit-rate up to 0.92. Our approach has been compared to the most relevant techniques used in the literature ( generative models , unsupervised models, and attention-based supervised models ) by achieving up to 15% improvement in F -score for the hashtag recommendation task and 9% for the topic discovery task.

Models for Efficient Utilization of Resources for Upgrading Android Mobile Technology

The need of the customers to be connected to the network at all times has led to the evolution of mobile technology. Operating systems play a vitol role when we talk of technology. Nowadays, Android is one of the popularly used operating system in mobile phones. Authors have analysed three stable versions of Android, 6.0, 7.0 and 8.0. Incorporating a change in the version after it is released requires a lot of rework and thus huge amount of costs are incurred. In this paper, the aim is to reduce this rework by identifying certain parts of a version during early phase of development which need careful attention. Machine learning prediction models are developed to identify the parts which are more prone to changes. The accuracy of such models should be high as the developers heavily rely on them. The high dimensionality of the dataset may hamper the accuracy of the models. Thus, the authors explore four dimensionality reduction techniques, which are unexplored in the field of network and communication. The results concluded that the accuracy improves after reducing the features.

Minimizing human race creating an unknown climate leading to pandemics-Need of the time

We are on a planet that orbits the Sun which emits a huge amount of energy. The climate we experience is a result of an energy gradient across Earth and an imbalance in energy across the world due to axial tilt of Earth rotation.

A Survey on Differential Privacy for Unstructured Data Content

Huge amount of unstructured data including image, video, audio, and text are ubiquitously generated and shared, it is a challenge to protect sensitive personal information in them, such as human faces, voiceprints, and authorships. Differential privacy is the standard privacy protection technology that provides rigorous privacy guarantees for various data. This survey summarizes and analyzes differential privacy solutions to protect unstructured data content before they are shared with untrusted parties. These differential privacy methods obfuscate unstructured data after they are represented with vectors, and then reconstruct them with obfuscated vectors. We summarize specific privacy models and mechanisms together with possible challenges in them. We also conclude their privacy guarantees against AI attacks and utility losses. Finally, we discuss several possible directions for future research.

Comparative Life Cycle Assessment of Safety Shoes Toe Caps Manufacturing Processes

Toe caps are fundamental components of safety footwear used to prevent injuries which can be caused by falling objects. They can be realized by exploiting different materials (metal, composites and plastics) and manufacturing processes (stamping, injection molding, compression molding, etc.). However, they have always to fulfill the stringent requirements of safety regulations. In addition, in order to guarantee an ergonomic use, they must be as light as possible. It is estimated that at least 300 million pairs of safety footwear, with 600 million of toe caps, end up in landfill or are incinerated every year. This huge amount of wastes generates a relevant environmental impact, mainly attributable to toe caps manufacturing. In this context, it is important to develop new solutions which minimize the environmental impacts of toe caps manufacturing. Among others, the reuse of carbon fiber prepreg scraps has been recognized as a valid method to produce effective toe caps. In this paper, a detailed analysis of the environmental impacts associated to toe caps realized with reclaimed prepreg scraps has been conducted exploiting the Life Cycle Assessment methodology. The results have been compared to those obtained by analyzing toe caps realized in steel, aluminum, polycarbonate and glass fiber composite. Results demonstrate that the reclaim process for carbon fiber prepreg scraps can be a valid circular economy model to produce more sustainable toe caps for safety footwear.

Recognition of Gurmukhi Handwritten City Names Using Deep Learning and Cloud Computing

The challenges involved in the traditional cloud computing paradigms have prompted the development of architectures for the next generation cloud computing. The new cloud computing architectures can generate and handle huge amount of data, which was not possible to handle with the help of traditional architectures. Deep learning algorithms have the ability to process this huge amount of data and, thus, can now solve the problem of the next generation computing algorithms. Therefore, these days, deep learning has become the state-of-the-art approach for solving various tasks and most importantly in the field of recognition. In this work, recognition of city names is proposed. Recognition of handwritten city names is one of the potential research application areas in the field of postal automation For recognition using a segmentation-free approach (Holistic approach). This proposed work demystifies the role of convolutional neural network (CNN), which is one of the methods of deep learning technique. Proposed CNN model is trained, validated, and analyzed using Adam and stochastic gradient descent (SGD) optimizer with a batch size of 2, 4, and 8 and learning rate (LR) of 0.001, 0.01, and 0.1. The model is trained and validated on 10 different classes of the handwritten city names written in Gurmukhi script, where each class has 400 samples. Our analysis shows that the CNN model, using an Adam optimizer, batch size of 4, and a LR of 0.001, has achieved the best average validation accuracy of 99.13.

Utilizing Half Convolutional Autoencoder to Generate User and Item Vectors for Initialization in Matrix Factorization

Recommendation systems based on convolutional neural network (CNN) have attracted great attention due to their effectiveness in processing unstructured data such as images or audio. However, a huge amount of raw data produced by data crawling and digital transformation is structured, which makes it difficult to utilize the advantages of CNN. This paper introduces a novel autoencoder, named Half Convolutional Autoencoder, which adopts convolutional layers to discover the high-order correlation between structured features in the form of Tag Genome, the side information associated with each movie in the MovieLens 20 M dataset, in order to generate a robust feature vector. Subsequently, these new movie representations, along with the introduction of users’ characteristics generated via Tag Genome and their past transactions, are applied into well-known matrix factorization models to resolve the initialization problem and enhance the predicting results. This method not only outperforms traditional matrix factorization techniques by at least 5.35% in terms of accuracy but also stabilizes the training process and guarantees faster convergence.

A Survey on Comparison of Performance Analysis on a Cloud-Based Big Data Framework

Cloud computing is offering various IT services to many users in the work on the basis of pay-as-you-use model. As the data is increasing day by day, there is a huge requirement for cloud applications that manage such a huge amount of data. Basically, a best solution for analyzing such amounts of data and handles a large dataset. Various companies are providing such framesets for particular applications. A cloud framework is the accruement of different components which is similar to the development tools, various middleware for particular applications and various other database management services that are needed for cloud computing deployment, development and managing the various applications of the cloud. This results in an effective model for scaling such a huge amount of data in dynamically allocated recourses along with solving their complex problems. This article is about the survey on the performance of the big data framework based on a cloud from various endeavors which assists ventures to pick a suitable framework for their work and get a desired outcome.

Dynamic Obstacle Avoidance Algorithm Based on DYNAMIC Environment MR

With the rapid development of computer technology, the importance of database systems as an indispensable part of information systems is becoming more and more prominent. And nowadays, the society has been increasingly using modern means to program databases. Database is a large and complex, huge amount of data and has a certain structure and independence of the important system, its programming requires certain technical means, the author will be in the text for the database programming involved in the key technology to explain.

Big Data Analytics and Visualization for Food Health Status Determination Using Bigmart Data

Being premature, the traditional data visualization techniques suffer from several challenges and lack the ability to handle a huge amount of data, particularly in gigabytes and terabytes. In this research, we propose an R-tool and data analytics framework for handling a huge amount of commercial market stored data and discover knowledge patterns from the dataset for conveying the derived conclusion. In this chapter, we elaborate on pre-processing a commercial market dataset using the R tool and its packages for information and visual analytics. We suggest a recommendation system based on the data which identifies if the food entry inserted into the database is hygienic or non-hygienic based on the quality preserved attributes. For a precise recommendation system with strong predictive accuracy, we will put emphasis on Algorithms such as J48 or Naive Bayes and utilize the one who outclasses the comparison based on accuracy. Such a system, when combined with R language, can be potentially used for enhanced decision making.