Reinforcement Learning-based Counter-Misinformation Response Generation: A Case Study of COVID-19 Vaccine Misinformation

The spread of online misinformation threatens public health, democracy, and the broader society. While professional fact-checkers form the first line of defense by fact-checking popular false claims, they do not engage directly in conversations with misinformation spreaders. On the other hand, non-expert ordinary users act as eyes-on-the-ground who proactively counter misinformation - recent research has shown that 96% counter-misinformation responses are made by ordinary users. However, research also found that 2/3 times, these responses are rude and lack evidence. This work seeks to create a counter-misinformation response generation model to empower users to effectively correct misinformation. This objective is challenging due to the absence of datasets containing ground-truth of ideal counter-misinformation responses, and the lack of models that can generate responses backed by communication theories. In this work, we create two novel datasets of misinformation and counter-misinformation response pairs from in-the-wild social media and crowdsourcing from college-educated students. We annotate the collected data to distinguish poor from ideal responses that are factual, polite, and refute misinformation. We propose MisinfoCorrect, a reinforcement learning-based framework that learns to generate counter-misinformation responses for an input misinformation post. The model rewards the generator to increase the politeness, factuality, and refutation attitude while retaining text fluency and relevancy. Quantitative and qualitative evaluation shows that our model outperforms several baselines by generating high-quality counter-responses. This work illustrates the promise of generative text models for social good - here, to help create a safe and reliable information ecosystem. The code and data is accessible on https://github.com/claws-lab/MisinfoCorrect. © 2023 Owner/Author.

A Knowledge-driven Domain Adaptive Approach to Early Misinformation Detection in an Emergent Health Domain on Social Media

This paper focuses on an important problem of early misinformation detection in an emergent health domain on social media. Current misinformation detection solutions often suffer from the lack of resources (e.g., labeled datasets, sufficient medical knowledge) in the emerging health domain to accurately identify online misinformation at an early stage. To address such a limitation, we develop a knowledge-driven domain adaptive approach that explores a good set of annotated data and reliable knowledge facts in a source domain (e.g., COVID-19) to learn the domain-invariant features that can be adapted to detect misinformation in the emergent target domain with little ground truth labels (e.g., Monkeypox). Two critical challenges exist in developing our solution: i) how to leverage the noisy knowledge facts in the source domain to obtain the medical knowledge related to the target domain? ii) How to adapt the domain discrepancy between the source and target domains to accurately assess the truthfulness of the social media posts in the target domain? To address the above challenges, we develop KAdapt, a knowledge-driven domain adaptive early misinformation detection framework that explicitly extracts rel-evant knowledge facts from the source domain and jointly learns the domain-invariant representation of the social media posts and their relevant knowledge facts to accurately identify misleading posts in the target domain. Evaluation results on five real-world datasets demonstrate that KAdapt significantly outperforms state-of-the-art baselines in terms of accurately detecting misleading Monkeypox posts on social media. © 2022 IEEE.

Measuring emotions in the COVID-19 real world worry dataset

The COVID-19 pandemic is having a dramatic impact on societies and economies around the world. With various measures of lockdowns and social distancing in place, it becomes important to understand emotional responses on a large scale. In this paper, we present the first ground truth dataset of emotional responses to COVID-19. We asked participants to indicate their emotions and express these in text. This resulted in the Real World Worry Dataset of 5,000 texts (2,500 short + 2,500 long texts). Our analyses suggest that emotional responses correlated with linguistic measures. Topic modeling further revealed that people in the UK worry about their family and the economic situation. Tweet-sized texts functioned as a call for solidarity, while longer texts shed light on worries and concerns. Using predictive modeling approaches, we were able to approximate the emotional responses of participants from text within 14% of their actual value. We encourage others to use the dataset and improve how we can use automated methods to learn about emotional responses and worries about an urgent problem. © ACL 2020.All right reserved.

A Novel Automated Classification and Segmentation for COVID-19 using 3D CT Scans

Medical image classification and segmentation based on deep learning (DL) are emergency research topics for diagnosing variant viruses of the current COVID-19 situation. In COVID-19 computed tomography (CT) images of the lungs, ground glass turbidity is the most common finding that requires specialist diagnosis. Based on this situation, some researchers propose the relevant DL models which can replace professional diagnostic specialists in clinics when lacking expertise. However, although DL methods have a stunning performance in medical image processing, the limited datasets can be a challenge in developing the accuracy of diagnosis at the human level. In addition, deep learning algorithms face the challenge of classifying and segmenting medical images in three or even multiple dimensions and maintaining high accuracy rates. Consequently, with a guaranteed high level of accuracy, our model can classify the patients' CT images into three types: Normal, Pneumonia and COVID. Subsequently, two datasets are used for segmentation, one of the datasets even has only a limited amount of data (20 cases). Our system combined the classification model and the segmentation model together, a fully integrated diagnostic model was built on the basis of ResNet50 and 3D U-Net algorithm. By feeding with different datasets, the COVID image segmentation of the infected area will be carried out according to classification results. Our model achieves 94.52% accuracy in the classification of lung lesions by 3 types: COVID, Pneumonia and Normal. For 2 labels (ground truth, lung lesions) segmentation, the model gets 99.57% of accuracy, 0.2191 of train loss and 0.78 ± 0.03 of MeanDice±Std, while the 4 labels (ground truth, left lung, right lung, lung lesions) segmentation achieves 98.89% of accuracy, 0.1132 of train loss and 0.83 ± 0.13 of MeanDice±Std. For future medical use, embedding the model into the medical facilities might be an efficient way of assisting or substituting doctors with diagnoses, therefore, a broader range of the problem of variant viruses in the COVID-19 situation may also be successfully solved. © 2022 IEEE.

Deep-Learning-Based Whole-Lung and Lung-Lesion Quantification Despite Inconsistent Ground Truth: Application to Computerized Tomography in SARS-CoV-2 Nonhuman Primate Models.

RATIONALE AND OBJECTIVES: Animal modeling of infectious diseases such as coronavirus disease 2019 (COVID-19) is important for exploration of natural history, understanding of pathogenesis, and evaluation of countermeasures. Preclinical studies enable rigorous control of experimental conditions as well as pre-exposure baseline and longitudinal measurements, including medical imaging, that are often unavailable in the clinical research setting. Computerized tomography (CT) imaging provides important diagnostic, prognostic, and disease characterization to clinicians and clinical researchers. In that context, automated deep-learning systems for the analysis of CT imaging have been broadly proposed, but their practical utility has been limited. Manual outlining of the ground truth (i.e., lung-lesions) requires accurate distinctions between abnormal and normal tissues that often have vague boundaries and is subject to reader heterogeneity in interpretation. Indeed, this subjectivity is demonstrated as wide inconsistency in manual outlines among experts and from the same expert. The application of deep-learning data-science tools has been less well-evaluated in the preclinical setting, including in nonhuman primate (NHP) models of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection/COVID-19, in which the translation of human-derived deep-learning tools is challenging. The automated segmentation of the whole lung and lung lesions provides a potentially standardized and automated method to detect and quantify disease. MATERIALS AND METHODS: We used deep-learning-based quantification of the whole lung and lung lesions on CT scans of NHPs exposed to SARS-CoV-2. We proposed a novel multi-model ensemble technique to address the inconsistency in the ground truths for deep-learning-based automated segmentation of the whole lung and lung lesions. Multiple models were obtained by training the convolutional neural network (CNN) on different subsets of the training data instead of having a single model using the entire training dataset. Moreover, we employed a feature pyramid network (FPN), a CNN that provides predictions at different resolution levels, enabling the network to predict objects with wide size variations. RESULTS: We achieved an average of 99.4 and 60.2% Dice coefficients for whole-lung and lung-lesion segmentation, respectively. The proposed multi-model FPN outperformed well-accepted methods U-Net (50.5%), V-Net (54.5%), and Inception (53.4%) for the challenging lesion-segmentation task. We show the application of segmentation outputs for longitudinal quantification of lung disease in SARS-CoV-2-exposed and mock-exposed NHPs. CONCLUSION: Deep-learning methods should be optimally characterized for and targeted specifically to preclinical research needs in terms of impact, automation, and dynamic quantification independently from purely clinical applications.

OSEGNET: OPERATIONAL SEGMENTATION NETWORK FOR COVID-19 DETECTION USING CHEST X-RAY IMAGES

Coronavirus disease 2019 (COVID-19) has been diagnosed automatically using Machine Learning algorithms over chest X-ray (CXR) images. However, most of the earlier studies used Deep Learning models over scarce datasets bearing the risk of overfitting. Additionally, previous studies have revealed the fact that deep networks are not reliable for classification since their decisions may originate from irrelevant areas on the CXRs. Therefore, in this study, we propose Operational Segmentation Network (OSegNet) that performs detection by segmenting COVID-19 pneumonia for a reliable diagnosis. To address the data scarcity encountered in training and especially in evaluation, this study extends the largest COVID-19 CXR dataset: QaTa-COV19 with 121, 378 CXRs including 9258 COVID-19 samples with their corresponding ground-truth segmentation masks that are publicly shared with the research community. Consequently, OSegNet has achieved a detection performance with the highest accuracy of 99.65% among the state-of-the-art deep models with 98.09% precision. © 2022 IEEE.

Measure and scoring Arabic countries policies to mitigate the covid19 pandemic based on deaths

This article presents the results of the Arabic countries mitigation using an open-source python package SCORECOVID which calculates the score of the countries based on the death rate. The results presented by the tool reflects the real facts and the ground truth in the different countries and the effectiveness of their policies. © 2022 IEEE.

Hoaxes and Hidden agendas: A Twitter Conspiracy Theory Dataset

Hoaxes and hidden agendas make for compelling conspiracy theories. While many of these theories are ultimately innocuous, others have the potential to do real harm, instigating real-world support or disapproval of the theories. This is further fueled by social media which provides a platform for conspiracy theories to spread at unprecedented rates. Thus, there is a need for the development of automated models to detect conspiracy theories from the social media space in order to quickly and effectively identify the topics of the season and the prevailing stance. To support this development, we create ground truth data through human annotation. In this work, we collect and manually annotate a dataset from Twitter, comprising of four conspiracy theories. Each Tweet is annotated with one of the four topics {climate change, COVID-19 origin, COVID-19 vaccine, Epstein-Maxwell trial}, and its stance towards the conspiracy theory {support, neutral, against}. We perform experiments on this multi-topic dataset to demonstrate its usage in conspiracy-detection, stance-detection and topic-detection. © 2022 Owner/Author.

Self-supervision and Multi-task Learning: Challenges in Fine-Grained COVID-19 Multi-class Classification from Chest X-rays

Quick and accurate diagnosis is of paramount importance to mitigate the effects of COVID-19 infection, particularly for severe cases. Enormous effort has been put towards developing deep learning methods to classify and detect COVID-19 infections from chest radiography images. However, recently some questions have been raised surrounding the clinical viability and effectiveness of such methods. In this work, we investigate the impact of multi-task learning (classification and segmentation) on the ability of CNNs to differentiate between various appearances of COVID-19 infections in the lung. We also employ self-supervised pre-training approaches, namely MoCo and inpainting-CXR, to eliminate the dependence on expensive ground truth annotations for COVID-19 classification. Finally, we conduct a critical evaluation of the models to assess their deploy-readiness and provide insights into the difficulties of fine-grained COVID-19 multi-class classification from chest X-rays. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Autonomous object detection and tracking robot using Kinect v2

Object detection and tracking are one of the key features of a robust autonomous mobile robot, allowing it to navigate places and avoid obstacles. The Mobile robotics market and proliferation has been growing and the Covid-19 era has added another boost to this area where more and more interest is being drawn to the autonomous capabilities of these machines. In this paper we propose a hardware based model to detect and track objects based on color. We propose robust object detection and tracking with minimum environmental constraints to improve accuracy using our algorithm, and capable of behaving well in unknown environmental conditions. At the end of the analysis, the robot was able to detect the object and track it well. We also show frequency analysis, compression and error analysis of the underlying technique. Experimental outcomes verify improved accuracy of our algorithm.

Learning to Learn HVAC Failures: Layering ML Experiments in the Absence of Ground Truth

Passenger comfort systems such as Heating, Ventilation, and Air-Conditioning units (HVACs) usually lack the data monitoring quality enjoyed by mission-critical systems in trains. But climate change, in addition to the high ventilation standards enforced by authorities due to the COVID pandemic, have increased the importance of HVACs worldwide. We propose a machine learning (ML) approach to the challenge of failure detection from incomplete data, consisting of two steps: 1. human-annotation bootstrapping, on a fraction of temperature data, to detect ongoing functional loss and build an artificial ground truth (AGT);2. failure prediction from digital-data, using the AGT to train an ML model based on failure diagnose codes to foretell functional loss. We exercise our approach in trains of Dutch Railways, showing its implementation, ML-predictive capabilities (the ML model for the AGT can detect HVAC malfunctions online), limitations (we could not foretell failures from our digital data), and discussing its application to other assets. © 2022, Springer Nature Switzerland AG.

Measuring discord among multidimensional data sources

Data integration is a classical problem in databases, typically decomposed into schema matching, entity matching and record merging. To solve the latter, it is mostly assumed that ground truth can be determined, either as master data or from user feedback. However, in many cases, this is not the case because firstly the merging processes cannot be accurate enough, and also the data gathering processes in the different sources are simply imperfect and cannot provide high quality data. Instead of enforcing consistency, we propose to evaluate how concordant or discordant sources are as a measure of trustworthiness (the more discordant are the sources, the less we can trust their data). Thus, we define the discord measurement problem in which given a set of uncertain raw observations or aggregate results (such as case/hospitalization/death data relevant to COVID-19) and information on the alignment of different data (for example, cases and deaths), we wish to assess whether the different sources are concordant, or if not, measure how discordant they are. Copyright © 2022 for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).

Vision-based Health Protocol Observance System for Small Rooms

COVID-19 has impacted the daily lives of millions. Businesses and educational institutions had to take preventive measures including social distancing to reduce the spread of COVID-19. This study aims to mitigate COVID-19 transmission in a small areas like classrooms, where occlusion and perspective issues are prevalent and highly challenging, using an innovative vision-based approach. Several human-head detection YOLOv4 models were trained on three different training datasets. Afterwards, they got evaluated to select the most reliable model for the social distancing solution. A 91.12% mAP was reached after improving the SCUT-HEAD dataset by generating face masks on the subjects. Using euclidean distance, triangle similarity and head size ratios a formula was developed to accurately calculate distances in small spaces using one camera;with no need of perspective annotation and highly reducing occlusion issues. Given most studies reviewed lacked ground-truth data, we created a real test scenario, with marks on the floor to readily provide ground-truth data during the experiment. The proposed human-head (triangle similarity) method managed to achieve an F1-Score of 85.66% compared to a reference state-of-the-art solution employing a whole body and perspective transform approach which achieved an F1-Score of 80.46%. Our solution achieved better results in small room scenarios, with high prospects of addressing challenges in a real-world environment. © 2021 IEEE.

COVID-19 Drug Repurposing: A Network-Based Framework for Exploring Biomedical Literature and Clinical Trials for Possible Treatments.

BACKGROUND: With the Coronavirus becoming a new reality of our world, global efforts continue to seek answers to many questions regarding the spread, variants, vaccinations, and medications. Particularly, with the emergence of several strains (e.g., Delta, Omicron), vaccines will need further development to offer complete protection against the new variants. It is critical to identify antiviral treatments while the development of vaccines continues. In this regard, the repurposing of already FDA-approved drugs remains a major effort. In this paper, we investigate the hypothesis that a combination of FDA-approved drugs may be considered as a candidate for COVID-19 treatment if (1) there exists an evidence in the COVID-19 biomedical literature that suggests such a combination, and (2) there is match in the clinical trials space that validates this drug combination. METHODS: We present a computational framework that is designed for detecting drug combinations, using the following components (a) a Text-mining module: to extract drug names from the abstract section of the biomedical publications and the intervention/treatment sections of clinical trial records. (b) a network model constructed from the drug names and their associations, (c) a clique similarity algorithm to identify candidate drug treatments. RESULT AND CONCLUSIONS: Our framework has identified treatments in the form of two, three, or four drug combinations (e.g., hydroxychloroquine, doxycycline, and azithromycin). The identifications of the various treatment candidates provided sufficient evidence that supports the trustworthiness of our hypothesis.

Mapping Sugarcane in Central India with Smartphone Crowdsourcing

In India, the second-largest sugarcane producing country in the world, accurate mapping of sugarcane land is a key to designing targeted agricultural policies. Such a map is not available, however, as it is challenging to reliably identify sugarcane areas using remote sensing due to sugarcane’s phenological characteristics, coupled with a range of cultivation periods for different varieties. To produce a modern sugarcane map for the Bhima Basin in central India, we utilized crowdsourced data and applied supervised machine learning (neural network) and unsupervised classification methods individually and in combination. We highlight four points. First, smartphone crowdsourced data can be used as an alternative ground truth for sugarcane mapping but requires careful correction of potential errors. Second, although the supervised machine learning method performs best for sugarcane mapping, the combined use of both classification methods improves sugarcane mapping precision at the cost of worsening sugarcane recall and missing some actual sugarcane area. Third, machine learning image classification using high-resolution satellite imagery showed significant potential for sugarcane mapping. Fourth, our best estimate of the sugarcane area in the Bhima Basin is twice that shown in government statistics. This study provides useful insights into sugarcane mapping that can improve the approaches taken in other regions.