Legal Judgment Elements Extraction Approach with Law Article-aware Mechanism

Legal judgment elements extraction (LJEE) aims to identify the different judgment features from the fact description in legal documents automatically, which helps to improve the accuracy and interpretability of the judgment results. In real court rulings, judges usually need to scan both the fact descriptions and the law articles repeatedly to find out the relevant information, and it is hard to acquire the key judgment features quickly, so legal judgment elements extraction is a crucial and challenging task for legal judgment prediction. However, most existing methods follow the text classification framework, which fails to model the attentive relations of the law articles and the legal judgment elements. To address this issue, we simulate the working process of human judges, and propose a legal judgment elements extraction method with a law article-aware mechanism, which captures the complex semantic correlations of the law article and the legal judgment elements. Experimental results show that our proposed method achieves significant improvements than other state-of-the-art baselines on the element recognition task dataset. Compared with the BERT-CNN model, the proposed “All labels Law Articles Embedding Model (ALEM)” improves the accuracy, recall, and F1 value by 0.5, 1.4 and 1.0, respectively.

A Classification Framework for Analyzing the War and Peacemaking Potential of News Media in Pakistan

In this study, we present a contextual model for analyzing the escalatory and de-escalatory trends in media reporting of seven conflicts in Pakistan. For this purpose, we combined findings from both survey and content analysis. While the survey helped to examine the journalists’ perceptions about the security threats of conflicts and the factors that influence the reportage, the content analysis was utilized to analyze the escalatory and de-escalatory characteristics in the coverage. The findings show that high security conflicts lead to a patriotic reporting scenario that results in high escalatory coverage. There is a significant decrease in the escalatory coverage as the assumed threat level of a conflict decreases. Similarly, we found that a conflict in which journalists exercised more relative freedom from pressure groups was reported in de-escalatory fashion. These findings can be useful for strategizing for the implementation of peace journalism in Pakistan in particular and elsewhere in general.

Rise and Fall of Digital Activism in Mexico From 2000-2019

Political activism is more alive than ever. After the scandal of Facebook and Cambridge Analytica, online social media platforms restricted the distribution of content to privacy laws. But populism disruption in many countries fosters political discontent. Online protests and everyday claims are rising. Add to this context environmental problems and an absence of an ideological framework. All these conditions foster the use of digital activism. But this field of research has studied single cases, losing connections with societies and history. The aim of this chapter is to explain the evolution of digital activism in a long period of time. To achieve such purpose, the author analyzes 11 Mexican events that took place from 2000 to 2019 and provide a classification framework to understand how digital activism transforms over time.

Tiled Sparse Coding in Eigenspaces for Image Classification

The automation in the diagnosis of medical images is currently a challenging task. The use of Computer Aided Diagnosis (CAD) systems can be a powerful tool for clinicians, especially in situations when hospitals are overflowed. These tools are usually based on artificial intelligence (AI), a field that has been recently revolutionized by deep learning approaches. blackThese alternatives usually obtain a large performance based on complex solutions, leading to a high computational cost and the need of having large databases. In this work, we propose a classification framework based on sparse coding. Images are blackfirst partitioned into different tiles, and a dictionary is built after applying PCA to these tiles. The original signals are then transformed as a linear combination of the elements of the dictionary. blackThen, they are reconstructed by iteratively deactivating the elements associated with each component. Classification is finally performed employing as features the subsequent reconstruction errors. Performance is evaluated in a real context where distinguishing between four different pathologies: control versus bacterial pneumonia versus viral pneumonia versus COVID-19. blackOur system differentiates between pneumonia patients and controls with an accuracy of 97.74%, whereas in the 4-class context the accuracy is 86.73%. The excellent results and the pioneering use of sparse coding in this scenario evidence that our proposal can assist clinicians when their workload is high.

Asso approach for classifying gene expression data based on optimal features

Gene expression profiles are sequences of numbers, and the need to analyze them has now increased significantly. Gene expression data contain a large number of genes and models used for cancer classification. As the wealth of these data being produced, new prediction, classification and clustering techniques are applied to the analysis of the data. Although there are a number of proposed methods with good results, there is still limited diagnostics and a lot of problems still to be solved. To solve the difficulty, in this paper, an efficient gene expression data classification is proposed. To predict the cancer class of patients from the gene expression profile, this paper presents a novel classification framework in the manner of three steps namely, Pre-processing, feature selection and classification. In pre-processing, missing value is filled and redundant data are removed. To attain the enhanced classification outcomes, the important features are selected from the database with the help of Adaptive Salp Swarm Optimization (ASSO) algorithm. Then, the selected features are given to the multi kernel SVM (MKSVM) to classify the gene expression data namely, BRCA, KIRC, COAD, LUAD and PRAD. The performance of proposed methodology is analyzed in terms of different metrics namely, accuracy, sensitivity and specificity. The performance of proposed methodology is 4.5% better than existing method in terms of accuracy.

Architectural Distortion-Based Digital Mammograms Classification Using Depth Wise Convolutional Neural Network

Architectural distortion is the third most suspicious appearance on a mammogram representing abnormal regions. Architectural distortion (AD) detection from mammograms is challenging due to its subtle and varying asymmetry on breast mass and small size. Automatic detection of abnormal ADs regions in mammograms using computer algorithms at initial stages could help radiologists and doctors. The architectural distortion star shapes ROIs detection, noise removal, and object location, affecting the classification performance, reducing accuracy. The computer vision-based technique automatically removes the noise and detects the location of objects from varying patterns. The current study investigated the gap to detect architectural distortion ROIs (region of interest) from mammograms using computer vision techniques. Proposed an automated computer-aided diagnostic system based on architectural distortion using computer vision and deep learning to predict breast cancer from digital mammograms. The proposed mammogram classification framework pertains to four steps such as image preprocessing, augmentation and image pixel-wise segmentation. Architectural distortion ROI`s detection, training deep learning, and machine learning networks to classify AD`s ROIs into malignant and benign classes. The proposed method has been evaluated on three databases, the PINUM, the CBIS-DDSM, and the DDSM mammogram images, using computer vision and depth-wise 2D V-net 64 convolutional neural networks and achieved 0.95, 0.97, and 0.98 accuracies, respectively. Experimental results reveal that our proposed method outperforms as compared with the ShuffelNet, MobileNet, SVM, K-NN, RF, and previous studies.

A Comparative Analysis of Reporting Verbs Used in Literature Review Chapters of Bachelor’s and Master’s Theses of Chinese English Majors

Reporting Verbs (RVs), a crucial aspect of citations in academic writing, are used to report the work of other researchers. A Literature Review Chapter, as a key part-genre of any thesis, or a bigger genre where it is embedded, is the main place that has the highest number of RVs. Accordingly, this study aimed to analyze and compare the use of RVs between 30 bachelor’s thesis (BT) Literature Review Chapters and 30 master’s thesis (MT) Literature Review Chapters of Chinese English majors in terms of denotation and evaluation of RVs based on Hyland’s (2002) classification framework. The findings reveal that the RVs used in the BT Literature Reviews were smaller in amount and narrower in range compared with those in the MT counterparts. Regarding the denotation of RVs, Discourse Act RVs were found to be the most predominant in the BT corpus, while Research Act RVs prevailed in the MT corpus. Cognition Act RVs were the least used in the two corpora. Regarding the evaluation of RVs, factive RVs were the most frequently used in the BT Literature Reviews, while non-factive RVs were the most prominent in the MT counterparts. However, negative RVswere infrequent in both corpora. This study would increase the thesis writers’ knowledge on the significance of RVs, raise their awareness of employing RVs, and help them use RVs appropriately and effectively in writing their thesis and other academic writings. This paper also provides practical implications for teaching RVs in preparing research dissertations.