Stacking-based modelling for improved over-indebtedness predictions

In a world now starkly divided into pre- and post-COVID times, it's imperative to examine the impact of this public health crisis on the banking functions - particularly overindebtedness risks. In this work, a flexible analytics-based model is proposed to improve the banking process of detecting customers who are likely to have difficulty in managing their debt. The proposed model assists the banks in improving their predictions. The proposed meta-model extracts information from existing data to determine patterns and to predict future outcomes and trends. We test and evaluate a large variety of Machine Learning Algorithms (MLAs) by using new techniques like feature selection. Moreover, models of previous months are combined in order to build a meta-model representing several months using stacked generalisation technique. The new model will identify 91% of the customers potentially unable to repay their debt six months ahead and enable the bank to implement targeted collections strategies. Copyright © 2022 Inderscience Enterprises Ltd.

A Comparative Study of Question Answering over Knowledge Bases

Question answering over knowledge bases (KBQA) has become a popular approach to help users extract information from knowledge bases. Although several systems exist, choosing one suitable for a particular application scenario is difficult. In this article, we provide a comparative study of six representative KBQA systems on eight benchmark datasets. In that, we study various question types, properties, languages, and domains to provide insights on where existing systems struggle. On top of that, we propose an advanced mapping algorithm to aid existing models in achieving superior results. Moreover, we also develop a multilingual corpus COVID-KGQA, which encourages COVID-19 research and multilingualism for the diversity of future AI. Finally, we discuss the key findings and their implications as well as performance guidelines and some future improvements. Our source code is available at https://github.com/tamlhp/kbqa. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Gaining Actionable Insights in COVID-19 Dataset Using Word Embeddings

The field of unsupervised natural language processing (NLP) is gradually growing in prominence and popularity due to the overwhelming amount of scientific and medical data available as text, such as published journals and papers. To make use of this data, several techniques are used to extract information from these texts. Here, in this paper, we have made use of COVID-19 corpus (https://www.kaggle.com/allen-institute-for-ai/CORD-19-research-challenge ) related to the deadly corona virus, SARS-CoV-2, to extract useful information which can be invaluable in finding the cure of the disease. We make use of two word-embeddings model, Word2Vec and global vector for word representation (GloVe), to efficiently encode all the information available in the corpus. We then follow some simple steps to find the possible cures of the disease. We got useful results using these word-embeddings models, and also, we observed that Word2Vec model performed better than GloVe model on the used dataset. Another point highlighted by this work is that latent information about potential future discoveries are significantly contained in past papers and publications. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Detection of COVID-19 using a Deep Neural Network with Transfer Learning Approach

The COVID-19 has infected around 340 million people, and 5.5 million died. Due to the rapid growth of the virus, and limited resources, the healthcare sector collapsed in many countries. Hence, there is a need to study deep learning- based applications that can aid the healthcare sector. The primitive machine learning approaches require learned features to extract information for classification, whereas Convolutional Neural Network (CNN) performs the same by extracting image features from raw images. CNN tends to overfit often for small datasets, and hence, the concept of transfer learning comes into play. This paper aims to study and modify a pre-trained CNN VGG-16 model using the concept of transfer learning. The algorithm has been validated using a private and a public dataset with normal and COVID-19 positive chest X-ray images. © 2022 IEEE.

A Multimodal Misinformation Detector for COVID-19 Short Videos on TikTok

This paper studies an emerging and important problem of identifying misleading COVID-19 short videos where the misleading content is jointly expressed in the visual, audio, and textual content of videos. Existing solutions for misleading video detection mainly focus on the authenticity of videos or audios against AI algorithms (e.g., deepfake) or video manipulation, and are insufficient to address our problem where most videos are user-generated and intentionally edited. Two critical challenges exist in solving our problem: i) how to effectively extract information from the distractive and manipulated visual content in TikTok videos? ii) How to efficiently aggregate heterogeneous information across different modalities in short videos? To address the above challenges, we develop TikTec, a multimodal misinformation detection framework that explicitly exploits the captions to accurately capture the key information from the distractive video content, and effectively learns the composed misinformation that is jointly conveyed by the visual and audio content. We evaluate TikTec on a real-world COVID- 19 video dataset collected from TikTok. Evaluation results show that TikTec achieves significant performance gains compared to state-of-the-art baselines in accurately detecting misleading COVID-19 short videos. © 2021 IEEE.