PANACEA: An Automated Misinformation Detection System on COVID-19

In this demo, we introduce a web-based misinformation detection system PANACEA on COVID-19 related claims, which has two modules, fact-checking and rumour detection. Our fact-checking module, which is supported by novel natural language inference methods with a self-attention network, outperforms state-of-the-art approaches. It is also able to give automated veracity assessment and ranked supporting evidence with the stance towards the claim to be checked. In addition, PANACEA adapts the bi-directional graph convolutional networks model, which is able to detect rumours based on comment networks of related tweets, instead of relying on the knowledge base. This rumour detection module assists by warning the users in the early stages when a knowledge base may not be available. © 2023 Association for Computational Linguistics.

Large-Scale Analysis of New Employee Network Dynamics

The COVID-19 pandemic has accelerated digital transformations across industries, but also introduced new challenges into workplaces, including the difficulties of effectively socializing with colleagues when working remotely. This challenge is exacerbated for new employees who need to develop workplace networks from the outset. In this paper, by analyzing a large-scale telemetry dataset of more than 10,000 Microsoft employees who joined the company in the first three months of 2022, we describe how new employees interact and telecommute with their colleagues during their "onboarding"period. Our results reveal that although new hires are gradually expanding networks over time, there still exists significant gaps between their network statistics and those of tenured employees even after the six-month onboarding phase. We also observe that heterogeneity exists among new employees in how their networks change over time, where employees whose job tasks do not necessarily require extensive and diverse connections could be at a disadvantaged position in this onboarding process. By investigating how web-based people recommendations in organizational knowledge base facilitate new employees naturally expand their networks, we also demonstrate the potential of web-based applications for addressing the aforementioned socialization challenges. Altogether, our findings provide insights on new employee network dynamics in remote and hybrid work environments, which may help guide organizational leaders and web application developers on quantifying and improving the socialization experiences of new employees in digital workplaces. © 2023 ACM.

Dual Consistency-enhanced Semi-supervised Sentiment Analysis towards COVID-19 Tweets

In the context of COVID-19, numerous people present their opinions through social networks. It is thus highly desired to conduct sentiment analysis towards COVID-19 tweets to learn the public's attitudes, and facilitate the government to make proper guidelines for avoiding the social unrest. Although many efforts have studied the text-based sentiment classification from various domains (e.g., delivery and shopping reviews), it is hard to directly use these classifiers for the sentiment analysis towards COVID-19 tweets due to the domain gap. In fact, developing the sentiment classifier for COVID-19 tweets is mainly challenged by the limited annotated training dataset, as well as the diverse and informal expressions of user-generated posts. To address these challenges, we construct a large-scale COVID-19 dataset from Weibo and propose a dual COnsistency-enhanced semi-superVIseD network for Sentiment Anlaysis (COVID-SA). In particular, we first introduce a knowledge-based augmentation method to augment data and enhance the model's robustness. We then employ BERT as the text encoder backbone for both labeled data, unlabeled data, and augmented data. Moreover, we propose a dual consistency (i.e., label-oriented consistency and instance-oriented consistency) regularization to promote the model performance. Extensive experiments on our self-constructed dataset and three public datasets show the superiority of COVID-SA over state-of-the-art baselines on various applications. IEEE

ASSOCIATION RULE MINING FOR PREDICTION OF COVID-19

COVID-19 is a raging pandemic that has created havoc with its impact ranging from loss of millions of human lives to social and economic disruptions of the entire world. Therefore, error-free prediction, quick diagnosis, disease identification, isolation and treatment of a COVID patient have become extremely important. Nowadays, mining knowledge and providing scientific decision making for diagnosis of diseases from clinical datasets has found wide-ranging applications in healthcare sector. In this direction, among different data mining tools, association rule mining has already emerged out as a popular technique to extract invaluable information and develop important knowledge-base to help in intelligent diagnosis of distinct diseases quickly and automatically. In this paper, based on 5434 records of COVID cases collected from a popular data science community and using Rapid Miner Studio software, an attempt is put forward to develop a predictive model based on frequent pattern growth algorithm of association rule mining to determine the likelihood of COVID-19 in a patient. It identifies breathing problem, fever, dry cough, sore throat, abroad travel and attended large gathering as the main indicators of COVID-19. Employing the same clinical dataset, a linear regression model is also proposed having a moderately high coefficient of determination of 0.739 in accurately predicting the occurrence of COVID-19. A decision support system can also be developed using the association rules to ease out and automate early detection of other diseases. © 2023 by the authors.

Privacy, Security and Usability Comparison of Online Learning Platforms in Developing Countries: A Study on Bangladeshi Universities

As the number of MS Teams, Zoom, and Google Meet users increases with online education, so do the privacy and security vulnerabilities. This study aims to investigate the privacy, security, and usability aspects of few tools that are frequently used for educational purposes by Bangladeshi universities. Consumer security, privacy, and usability are also concerns when it comes to online-based software. This study assesses the most commonly used tools that are used for online education based on three important factors: privacy, security, and usability. Assessment factors concerning the privacy, security, and usability aspects are initially identified. Afterwards, each of the applications was assessed and ranked by comparing their characteristics, functionalities, and terms and conditions (T&C) in contradiction of those factors. In addition, for the purpose of additional validation, a survey was carried out with 57 university students who were enrolled at one of several private universities in Bangladesh. Microsoft Teams, Zoom, and Google Meet have been ranked based on an evaluation of their security, privacy, and usability features, which was accomplished through the use of a knowledge base and a user survey. © 2022 IEEE.

Do Online Challenge-Based Learning Help Professors Identify and Solve Community Problems During the COVID-19 Pandemic?

This research aims to identify online challenge-based learning (CBL) that builds on the problem-based learning practice to support professors working in two Mexican institutions with solutions to six social challenges defined by the institutions. Thirty-five professors from Tecnologico de Monterrey participated in developing the solutions related to given challenges by taking a social approach. For this activity, an online training session of one week was organized by the Faculty Development and Educational Innovation Center (CEDDIE) of Tecnologico de Monterrey in Mexico City, Mexico. The data was collected through an online survey based on quantitative and qualitative questionnaires. We received fifteen complete responses out of thirty-five. Analyzing the results of this study affirmed that online CBL activities served professors to promote social interactions, develop pedagogical competencies, and share knowledge based on their learning experience through active collaboration with peers in the same institutions but from different disciplines and campuses to identify and solve existing societal issues. © 2023 IEEE.

Innovation and Entrepreneurship Theory and Practice at HICSS-55

Since its inception six years ago, the Innovation and Entrepreneurship Theory and Practice minitrack of the Hawaiian International Conference on System Science (HICSS) has focused on the intersection of knowledge management and system science with innovation and entrepreneurship. Whereas the context of traditional knowledge management research is established organizations, this minitrack features the works of researchers who apply system science methods to knowledge management in the context of innovation and entrepreneurship, which is distinguished by uncertainty and resource constraints. The minitrack, part of the HICSS Knowledge Innovation and Entrepreneurial Systems track, continues to attract quality manuscripts relevant to the researcher, instructor, and practitioner, despite this being the second year that the coronavirus pandemic has forced the conference format to be virtual. This year's eight minitrack papers investigate environments for innovation including accelerators, incubators, and makerspaces, the digitalization of innovation, and sustainability. © 2022 IEEE Computer Society. All rights reserved.

Entrepreneurs' Response to the Dark Side of Knowledge During Covid19

Small business entrepreneurs faced tremendous knowledge-based challenges during COVID19. Some entrepreneurs, even in the same industry sector and city, with similar offerings, responded to these knowledge challenges in diverse ways. For instance, some chose to adopt online store technologies while others did not. In this study, we investigate differences in retail small business entrepreneurs' COVID19 resilience enactment using a qualitative retroductive-analytic approach. Identity motives were uncovered as a likely explanatory construct, as those with externally-focused identity motives generally adopted these technologies while those with internally-focused identity motives generally did not. In addition, identity motives appear to influence entrepreneurs' perceptions of technology affordances, potentially moderating the impact of these perceptions on technology adoption decisions. Contrary to conceptualizations of individual resilience being a trait, we find support that resilience is a mindset. Implications for entrepreneurship theory, practice, and education are discussed. © 2022 IEEE Computer Society. All rights reserved.

Unlearning in crisis: Forces of change in unlearning

The study of unlearning continues to be important, not only due to the relevance of the concept itself, but in light of current strong, unforeseen forces, knowledge change opportunities have been created beyond our prediction. A knowledge exchange is often needed to revise processes, use new technologies, or due to forces that stem from catastrophic situations. Examples include economic, such as in business failures or the recent public health concerns from the COVID-19 pandemic. Building from new insights using the typological model from Rushmer and Davies (2004), deep unlearning may the end result of catastrophic forces of change. First, deep unlearning occurs with striking events, or yield change that adds anxiety, psychological, or technological upset. Second, inherent in many catastrophic changes are rapid interruptions in the trajectory of "previous” actions and unique processes toward recovery where knowledge base may be forever altered. We address the following question: "Is Rushmer and Davies' deep unlearning typology exhibited during catastrophic situations?” This theoretical paper examines the concept of deep unlearning, the process of replacement or lack of use of a belief, action, or process in a context of an emergency situation where little is currently known. What type of agent for change would be needed? Will unintended consequences not be identified by individuals and organizations;what may be the cost to future learning skills when deep unlearning of current tasks occurs? Third, some insights and directions for future research are presented. © 2022 IEEE Computer Society. All rights reserved.

Opportunities Presented by COVID-19 for Healthcare Green Supply Chain Management and Sustainability Performance: The Moderating Effect of Social Media Usage

This research explores the opportunities presented by COVID-19 for green supply chains' environmental practices and ecological sustainability performances in the healthcare sector. This study investigates the connections between uncertainty-fear of COVID-19, healthcare green supply chain management (GSCM), and the three pillars of a firm's sustainability performance (environmental, economic, and social). Moreover, this study examines the moderating role of social media usage (SMU) on the effect of uncertainty-fear of COVID-19 on healthcare-GSCM. When conducting the empirical part, this study uses the partial least squares structural equation modeling method based on a sample of 483 healthcare managers. The findings prove that the uncertainty-fear of COVID-19 has a beneficial impact on healthcare-GSCM. Besides, SMU moderates the relationship between uncertainty-fear of COVID-19 and healthcare-GSCM, indicating the importance of SMU in gathering information for the healthcare sector during COVID-19. Likewise, when interacting with healthcare firms' sustainability performances, healthcare-GSCM positively impacts environmental and social performances, though it has a negligible impact on economic performance. This study adds to the “social cognitive theory”by introducing the concept of uncertainty-fear of COVID-19. Furthermore, this research adds to the “resource-based view theory”and the “knowledge-based view theory”by exploring the SMU's role during the outbreak. IEEE

Opening up Minds with Argumentative Dialogues

Recent research on argumentative dialogues has focused on persuading people to take some action, changing their stance on the topic of discussion, or winning debates. In this work, we focus on argumentative dialogues that aim to open up (rather than change) people's minds to help them become more understanding to views that are unfamiliar or in opposition to their own convictions. To this end, we present a dataset of 183 argumentative dialogues about 3 controversial topics: veganism, Brexit and COVID-19 vaccination. The dialogues were collected using the Wizard of Oz approach, where wizards leverage a knowledge-base of arguments to converse with participants. Open-mindedness is measured before and after engaging in the dialogue using a questionnaire from the psychology literature, and success of the dialogue is measured as the change in the participant's stance towards those who hold opinions different to theirs. We evaluate two dialogue models: a Wikipedia-based and an argument-based model. We show that while both models perform closely in terms of opening up minds, the argument-based model is significantly better on other dialogue properties such as engagement and clarity. © 2022 Association for Computational Linguistics.

Modeling of Factors Impacting Remote Workforce During COVID-19

The way an organization operates has a pattern to it. A knowledge-based way of understanding these patterns and implementing according to them retains the competitive advantage of the organizations. Thus, identifying factors is important because, if successful, it results in shared intellectual capital. Changing the core of the pattern upon which the organization works creates several problems in retaining an organization's competitiveness. This research focuses on identifying the elements which have a significant influence on an organization's operations due to the remote working of employees during situations like the COVID-19 pandemic. Further, the relationships of factors among each other have been explored from the available research. Based on the study of various organizations it has been found that not much work has been done to identify such factors even though several organizations have suddenly opted for their workforce to work remotely due to the COVID-19 pandemic. This has resulted in lost productivity and opportunities, organizational dis-balances, and a slower rate of development. The generated model may help organizations to understand the weak notes of remote working and implement structural changes accordingly to improve the productivity in remote working and tackle the productivity and opportunity loss due to remote workforce. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Analysis of the Capabilities for Research, Development, and Innovation in Telecommunications Engineering Careears

International organizations notes that the main weakness for innovation in Latin American countries is that their national research organizations only evaluate and stimulate pure academic personnel by publications and citations, forgetting those who work in industry, losing a vast potential in each country. Higher education institutions must increase the development and innovation if they want to contribute to the third mission, which means the economic development of a country, in addition to the traditional advanced education and research, to adapt to new realities for the knowledge-based economies. Commercial war, SARS COV-2, and energy crisis drive policymakers and university managers to rethink and redesign institutions. This work offers an approach to measure the research, development, and innovation capabilities of three telecommunications engineering careers in three Latin American universities in Mexico and Ecuador looking for to increasing capabilities when doing collaboration. Results confirm that the knowledge contribution in engineering is proportional to the number of supported engineering careers, even mapped to national and international rankings. Also is confirmed that research is related to the academic production, but development and innovation are more related to an effective relation to industry. © 2022 IEEE.

Organisational Factors Affecting Knowledge Retention in a Public Organisation

Knowledge is a strategic resource for any organisation to maintain optimal operational efficiency and competitiveness. Knowledge could be in the knower's mind (tacit) or codified and stored in knowledge repositories for retrieval when needed (explicit). Knowledge retention in organisations is becoming a global concern as the shortage of professionals or knowledge workers persists. Organisations over the years have focused on investing in activities leading to knowledge creation, improving technological capabilities, and increasing performance with less attention given to knowledge retention. The Covid-19 pandemic has exacerbated this concern leading to the exit of more knowledge workers from organisations voluntarily or involuntarily. The current study seeks to investigate the role of organisational factors on knowledge retention in public organisations using the water sector in a South African metropolitan city. This study seeks to deepen the knowledge management scholarship by viewing knowledge retention as a system rather than a process or strategy only, as explored by most studies. The water sector is a knowledge-driven sector that utilises heterogeneous knowledge (engineers, hydrologists, technicians, IT specialists) to achieve its mandate, making it information and knowledge-rich. This study intends to use the knowledge-based view as a sensitising lens to explore how a public organisation systemically integrates and coordinates its heterogeneous knowledge resources to ensure that knowledge is retained as well as maintain optimal operational efficiency. The basic assumptions of the knowledge base view are that knowledge is the most strategic resource in an organisation, and its coordination facilitates optimised efficiency. The study will adopt a pragmatist paradigm to uncover the role of organisational factors on knowledge retention. A purposive sample of supervisors and managers in the water sector will be interviewed. Qualitative data will be collected, and qualitative methods will be used to analyse the data. © 2022, Academic Conferences and Publishing International Limited. All rights reserved.

Knowledge Construction in Engineering Education Research - Assessing the Role of Journals, Books, Conferences, and Other Products of Research

This panel will discuss the role of different knowledge artifacts in creating, maintaining, and circulating knowledge within the engineering education community. The past decade has seen a significant increase in the venues available for sharing engineering education research and as the field grows and builds more knowledge, it is equally important to also take stock of prior work and of strategies to create novelty. Within this context, what is the role of different knowledge encapsulating artifacts and why do those who engage with creating these artifacts do so? In this panel we touch upon these issues while taking stock of the knowledge base in the field. We will also discuss what the future of knowledge creation in the field might look like given the move towards open access online publications as the primary form of knowledge circulation. Finally, in the post-COVID context, what will and should be the role of in-person events in this process. In terms of equity of participation, what potential avenues are available?. © 2022 IEEE.

Structuring and mathematical modeling for investment choice: a multi-method approach from Value-Focused Thinking and CRITIC-GRA-3N method

Investments should be decisions made by companies at a strategic level, aiming to maximize the return on invested capital. However, the evaluation required to obtain the best results demand, in addition to information about available assets, the ability of decision-makers to relate and weigh all the criteria that must be maximized or minimized to achieve the expected goal. This article plays an important role in supporting the decision making of a micro company, located in the state of Rio de Janeiro, which needs to invest the available amount in investment. In order to obtain the investment alternatives, as well as the evaluation criteria, the Value-Focused Thinking (VFT) was applied. After obtaining all necessary data, the CRITIC-GRA-3N method was used as a Multicriteria Decision Support technique, with the CRiteria Importance Through Intercriteria Correlation (CRITIC) method to generate the criteria weights and the Grey Relational Analysis (GRA) method, with three normalizations, to order the alternatives. With this, five ordinations were established, being the first three ordinations performed with the help of two normalizations and the last two ordinations being the arithmetic and geometric averages of the first three ordinations normalized with the third normalization. In the end it brought positive results to the microenterprise. © 2022 The Authors. Published by Elsevier B.V.

Modeling of Factors Impacting Remote Workforce During COVID-19

The way an organization operates has a pattern to it. A knowledge-based way of understanding these patterns and implementing according to them retains the competitive advantage of the organizations. Thus, identifying factors is important because, if successful, it results in shared intellectual capital. Changing the core of the pattern upon which the organization works creates several problems in retaining an organization's competitiveness. This research focuses on identifying the elements which have a significant influence on an organization's operations due to the remote working of employees during situations like the COVID-19 pandemic. Further, the relationships of factors among each other have been explored from the available research. Based on the study of various organizations it has been found that not much work has been done to identify such factors even though several organizations have suddenly opted for their workforce to work remotely due to the COVID-19 pandemic. This has resulted in lost productivity and opportunities, organizational dis-balances, and a slower rate of development. The generated model may help organizations to understand the weak notes of remote working and implement structural changes accordingly to improve the productivity in remote working and tackle the productivity and opportunity loss due to remote workforce. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

FGraDA: A Dataset and Benchmark for Fine-Grained Domain Adaptation in Machine Translation

Previous research for adapting a general neural machine translation (NMT) model into a specific domain usually neglects the diversity in translation within the same domain, which is a core problem for domain adaptation in real-world scenarios. One representative of such challenging scenarios is to deploy a translation system for a conference with a specific topic, e.g., global warming or coronavirus, where there are usually extremely less resources due to the limited schedule. To motivate wider investigation in such a scenario, we present a real-world fine-grained domain adaptation task in machine translation (FGraDA). The FGraDA dataset consists of Chinese-English translation task for four sub-domains of information technology: autonomous vehicles, AI education, real-time networks, and smart phone. Each sub-domain is equipped with a development set and test set for evaluation purposes. To be closer to reality, FGraDA does not employ any in-domain bilingual training data but provides bilingual dictionaries and wiki knowledge base, which can be easier obtained within a short time. We benchmark the fine-grained domain adaptation task and present in-depth analyses showing that there are still challenging problems to further improve the performance with heterogeneous resources. © European Language Resources Association (ELRA), licensed under CC-BY-NC-4.0.

Learnings from a Pilot Hybrid Question Answering System: CQAS

The Singapore Government first released their digital government blueprint in 2018 with the key message for all their agencies to be "digital to the core and served with heart". With this push, agencies are moving towards human-centric digital services, especially for individual citizens. During COVID-19, Singapore government agencies introduced many COVID-19 digital initiatives resulting in more incoming inquiries from citizens to respective agencies. This surge in inquiries created the challenge on the agencies' end to meet service level agreements. One widely adopted solution is the use of chatbot technology that directly interfaces with the customer. However, several organisations have faced backlash from the citizens or customers when such chatbots cannot answer or give inappropriate answers to the questions. Hence this research takes a different approach to address this challenge using a question answering (QA) system that supports the CSOs to help answer the citizen inquiries more efficiently. This paper shares our learnings from implementing the pilot QA system;the Citizen Question Answering System (CQAS) was built using a hybrid QA approach that combines techniques from Natural Language Process QA, Knowledge-based QA and Information Retrieval QA. We also highlight the essential learnings in implementing QA systems within a government agency. The research will further share how these learnings could inform the adoption of QA systems in a government setting. The subsequent research following this paper will then focus on conducting a user study with the CSOs to validate further the benefits of this pilot QA system, which is not covered in this paper. © 2022 Owner/Author.

REDIRECTION: Generating drug repurposing hypotheses using link prediction with DISNET data

In recent years and due to COVID-19 pandemic, drug repurposing or repositioning has been placed in the spotlight. Giving new therapeutic uses to already existing drugs, this discipline allows to streamline the drug discovery process, reducing the costs and risks inherent to de novo development. Computational approaches have gained momentum, and emerging techniques from the machine learning domain have proved themselves as highly exploitable means for repurposing prediction. Against this backdrop, one can find that biomedical data can be represented in terms of graphs, which allow depicting in a very expressive manner the underlying structure of the information. Combining these graph data structures with deep learning models enhances the prediction of new links, such as potential disease-drug connections. In this paper, we present a new model named REDIRECTION, which aims to predict new disease-drug links in the context of drug repurposing. It has been trained with a part of the DISNET biomedical graph, formed by diseases, symptoms, drugs, and their relationships. The reserved testing graph for the evaluation has yielded to an AUROC of 0.93 and an AUPRC of 0.90. We have performed a secondary validation of REDIRECTION using RepoDB data as the testing set, which has led to an AUROC of 0.87 and a AUPRC of 0.83. In the light of these results, we believe that REDIRECTION can be a meaningful and promising tool to generate drug repurposing hypotheses. © 2022 IEEE.