Claim Extraction and Dynamic Stance Detection in COVID-19 Tweets

The information ecosystem today is noisy, and rife with messages that contain a mix of objective claims and subjective remarks or reactions. Any automated system that intends to capture the social, cultural, or political zeitgeist, must be able to analyze the claims as well as the remarks. Due to the deluge of such messages on social media, and their tremendous power to shape our perceptions, there has never been a greater need to automate these analyses, which play a pivotal role in fact-checking, opinion mining, understanding opinion trends, and other such downstream tasks of social consequence. In this noisy ecosystem, not all claims are worth checking for veracity. Such a check-worthy claim, moreover, must be accurately distilled from subjective remarks surrounding it. Finally, and especially for understanding opinion trends, it is important to understand the stance of the remarks or reactions towards that specific claim. To this end, we introduce a COVID-19 Twitter dataset, and present a three-stage process to (i) determine whether a given Tweet is indeed check-worthy, and if so, (ii) which portion of the Tweet ought to be checked for veracity, and finally, (iii) determine the author's stance towards the claim in that Tweet, thus introducing the novel task of topic-agnostic stance detection. © 2023 ACM.

iCompass at WANLP 2022 Shared Task: ARBERT and MARBERT for Multilabel Propaganda Classification of Arabic Tweets

Propaganda content has seen massive spread in the biggest social media networks. Major global events such as Covid-19, presidential elections, and wars have all been infested with various propaganda techniques. In participation in the WANLP 2022 Shared Task(Alam et al., 2022), this paper provides a detailed overview of our machine learning system for propaganda techniques classification and its achieved results. The task was carried out using pre-trained transformer based models: ARBERT and MARBERT. The models were fine-tuned for the downstream task in hand: multilabel classification of Arabic tweets. According to the results, MARBERT and ARBERT attained 0.562 and 0.567 micro F1-score on the development set of subtask 1. The submitted model was MARBERT which attained a 0.597 micro F1-score and got the fifth rank. © 2022 Association for Computational Linguistics.

Disruptions in Global Supply Chains due to COVID 19

The recent witnessed pandemic COVID-19 caused severe distress in the Global Supply Chains (GSCs). Worldwide lockdowns, job losses, etc. helped in the creation of this problem. We describe the characteristics that distinguish epidemic outbreaks as a distinct supply chain disruption risk category. It is clearly highlighted that there is lack of visibility of disruptions in GLOBAL SUPPLY Chains and delayed industry response to COVID-19. The COVID-19 outbreak has certainly forced firms to re-evaluate their business strategies. The lead time, the speed of epidemic propagation and the upstream and downstream interruption durations in the supply chain are all significant aspects. This research can be used by decision teams to predict the short-term and long-term impacts of supply chain occurrences and to define pandemic supply chain strategies and tactics. This paper discusses the impact of COVID-19, the effect of lockdown and problems in existing technologies. Possible solutions regarding reducing the effect of pandemic and plans to prepare for the future are also depicted. © 2022 The authors and IOS Press. All rights reserved.

FAST: FPGA-based Acceleration of Genomic Sequence Trimming

The sheer amount of genomic sequencing data generated daily that requires time-sensitive processing for downstream analysis calls for accelerating the bioinformatics pipelines. Previous studies mainly have attempted accelerating the alignment stage, leaving the other pipeline stages as performance bottlenecks. In this work, we propose the first FPGA-based framework dubbed FAST to accelerate the stages that deal with sequence trimming, in particular adapter and primer removal. FAST supports a comprehensive set of functionalities and is convenient to use by operating on standard genomics data formats. The proposed framework is fully configurable and supports variety of runtime settings. It surpasses the state-of-the-art widely-used adapter trimmer (fastp) by 4.7×-29.4× speed-up, with 10.1×-54.9 less energy, respectively. For clipping primers, which with current existing tool (iVar) accounts for ∼50% of SARS-CoV-2 analysis pipeline, FAST achieves up to 62× speed-up in trimming the virus sequences with a low FPGA resource utilization of 12%. © 2022 IEEE.

Modeling Access Differences to Reduce Disparity in Resource Allocation

Motivated by COVID-19 vaccine allocation, where vulnerable subpopulations are simultaneously more impacted in terms of health and more disadvantaged in terms of access to the vaccine, we formalize and study the problem of resource allocation when there are inherent access differences that correlate with advantage and disadvantage. We identify reducing resource disparity as a key goal in this context and show its role as a proxy to more nuanced downstream impacts. We develop a concrete access model that helps quantify how a given allocation translates to resource flow for the advantaged vs. the disadvantaged, based on the access gap between them. We then provide a methodology for access-aware allocation. Intuitively, the resulting allocation leverages more vaccines in locations with higher vulnerable populations to mitigate the access gap and reduce overall disparity. Surprisingly, knowledge of the access gap is often not needed to perform access-aware allocation. To support this formalism, we provide empirical evidence for our access model and show that access-aware allocation can significantly reduce resource disparity and thus improve downstream outcomes. We demonstrate this at various scales, including at county, state, national, and global levels. © 2022 Owner/Author.

Contrastive learning enables rapid mapping to multimodal single-cell atlas of multimillion scale

Single-cell datasets continue to grow in size, posing computational challenges for dealing with expanded scale, extended modality and inevitable batch effects. Deep learning-based approaches have recently emerged to address these points by deriving nonlinear cell embeddings. Here we present contrastive learning of cell representations, Concerto, which leverages a self-supervised distillation framework to model multimodal single-cell atlases. Simply by discriminating each cell from the others, Concerto can be adapted to various downstream tasks such as automatic cell type classification, data integration and especially reference mapping. Unlike current mainstream packages, Concerto’s contrastive setting well supports operating on all genes to preserve biological variations. Concerto can flexibly generalize to multiomics to obtain unified cell representations. Benchmarking on both simulated and real datasets, Concerto substantially outperforms competing methods. By mapping to a comprehensive reference, Concerto recapitulates differential immune responses and discovers disease-specific cell states in patients with COVID-19. Concerto is easily parallelizable and efficiently scalable to build a 10-million-cell reference within 1.5 h and query 10,000 cells within 8 s. Overall, Concerto will facilitate biomedical research by enabling iteratively constructing single-cell reference atlases and rapidly mapping novel dataset against them to transfer relevant cell annotations. © 2022, The Author(s), under exclusive licence to Springer Nature Limited.

Step Change Transformation of Legacy Rigs to Autonomous Drilling Rigs

During the past decade, drilling automation systems have been an attractive target for a lot of operating and drilling companies. Despite progress in automation in various industries, like mining and downstream, the drilling industry has lagged far behind in the real application of autonomous technologies implementation. This can be attributed to harsh environment, high level of uncertainty in input data, and that majority of stock is legacy drilling rigs, resulting in capital intensive implementations. In the past years there have been several attempts to create fully automated rigs, that includes surface automation and drilling automation. Such solutions are very attractive, because they allow people to move out of hazardous zones and, at the same time, improve performance. However, the main deficiency of such an approach is the very high capital investment required for development of highly bespoke rigs (Slagmulder 2016). And in the current business environment, with high volatility in oil and gas prices, plus the huge negative effect of the Covid-19 crisis on the world's economic situation, it would be hard to imagine that there are a lot of companies willing to make such a risky investment. In addition to this, due to the lack of demand, the market is full of relatively new, high-performance rigs. Taking all these into account, the obvious question is whether it makes sense to invest money and time into the development of drilling automation. The answer should be yes, for three substantial reasons: • Automation improves personal safety, by moving people out of danger zones;• Automation improves process safety, by transferring execution from person to machine, which reduces the risk of human error;• Automation improves efficiency by bringing consistency to drilling and through the use of self-learning algorithms, which allow machines to drill each successive well better than the previous. This paper will not look into surface automation, such as pipe-handling, chemical and mud handling on site. The paper is focused on the subsurface, namely on the drilling automation process, the challenges that need to be overcome to deploy a vendor agnostic system on a majority of existing rigs. A vendor agnostic system is a modification of an operator's autonomous drilling system (Rassenfoss 2011), designed to use existing rigs, BHAs, and have minimum footprint on the rigs for operational use. A vendor agnostic system will increase adoption of automated technologies and further drive improvements in operational and business performance. © Copyright 2021, Society of Petroleum Engineers

Digital Integration, Success Story of Accelerating Business Integration of Two Biggest Midstream-Downstream Natural Gas Company in Indonesia

To achieve 24% portion of natural gas in targeted national energy mix in 2050, Indonesia government has integrated Pertagas, biggest transmission company into PGN, biggest distribution company under Oil & Gas Holding Pertamina. But survey from PWC in 2004 resulted that around 75% post-merger companies reported integration difficulties, especially both companies have long history of competition. Even more, government mandated 6 USD gas price policy at plant gate, which create enormous urgency to accelerate pipeline and digital integration in the most efficient way. Especially, in this pandemic era, midstream industry needs to foster digital transformation by rethinking outdated business models and strategically applying technology to change rather than focusing on simply cutting costs. From this integration, Pertagas with more than 2,418 km pipeline in 12 provinces spread from Sumatra, Java and Kalimantan has a big potency to be synergized with PGN, as Sub Holding Gas with the total of 10,169 km of pipeline which represent 96% of national gas infrastructure. During 2020. Both companies resulted more than 1.255 MMSCFD of transported gas and 828 BBTUD of sales gas to more than 460 thousand customers. So, PGN and Pertagas management has high expectation on this digital integration to transform from previous fragmented pipeline to be interconnected network to give flexibility in reaching unmet growing demand of strategic industry like refinery, fertilizer, electricity, steel and petrochemical in post-COVID recovery. In this paper, will be described the challenges and its solutions as a success story in digital integration. The important steps start from strategy development, digital assessment, creating coalition, culture acculturation, and change management are explained as guiding pathway for sustainable implementation. It will also portray the measured benefit and value from investment cost efficiency, time effectiveness from the initiation until launched, billing improvement, product development, and up to developed real-time integrated management dashboard for better decision making and part of the milestone for future National Dispatching Center for optimizing Sub Holding Gas portfolio of gas supply and subsidiary's infrastructure to meet growing Indonesia's demand. © Copyright 2021, Society of Petroleum Engineers

Learning Domain-Specific Word Embeddings from COVID-19 Tweets

The COVID-19 global pandemic has been a major catastrophic event that impacted the world's economy. During the pandemic there was a rise in the use of social media such as Twitter by people to express their reactions and responses to the global pandemic. This drove researchers to analyze these micro-blogging texts, using natural language processing (NLP) methods, to understand information inherent in those texts. Most of these NLP tasks employ the use of word embeddings in training neural network models. These word embeddings are mainly trained on general text corpus which produce sub-optimal performance when used in domain-specific NLP tasks such as in COVID-19 related tweets. In this paper, we present a learned COVID-19 tweets domain-specific word embeddings for use in COVID-19 related tweets NLP tasks. Our evaluation results show that our domain-specific COVID-19 tweets word embeddings perform better than pretrained general word embeddings in a downstream domain-specific NLP task. Our COVID-19 tweets word embeddings are available for use by researchers who wish to perform downstream NLP tasks with pretrained domain-specific COVID-19 tweets word embeddings. © 2021 IEEE.

TAX-B2BREC: Multi-Stage Cascade Downstream Company Recommender System Based on Taxation Data

The public crisis triggered by the COVID-19 pandemic has disastrous effects for B2B markets. With the supply chain and trade disrupted, the benefits of the company have been affected to varying degrees. In order to help companies find potential customers and recover the supply chain, we propose a multi-stage cascade downstream company recommender system based on taxation data. The proposed system can recommend potential buyers for upstream companies, which can help upstream companies find new sales channels. This system includes data processing, matching module, ranking module and system deployment. In the match module, we propose a hybrid recall algorithm to generate the candidate enterprises. In the ranking module, we use DCNV2 model to rank the candidate companies. Moreover, the multistage cascade recommendation algorithm achieves better results compared with the traditional algorithm in B2B recommender system. © 2021 IEEE.

Analysis of Ammonia in Kali Lamong River Estuary Surabaya during Pandemic Covid-19

Water quality monitoring is an important instrument in the management of freshwater resources because they offer essential information about the physical, chemical, and biological water resources status, determining patterns and changes over time, and identifying emerging water quality issues especially in a specific situation. This study investigates the ammonia concentration in Kali Lamong river estuaries Surabaya to comprehensive the level of pollution that occurs during pandemic Covid-19. This research was conducted in the river downstream of Kali Lamong in the dry season. Sampling has occurred in 3 stations. Each station has 3 sampling sites that were ¼ of the left side, ½ from the side of the left, and ¼ of the right side. The measurement ammonia in water was measured by SNI 06-6989.30-2005 method. The laboratory result depicted the highest of ammonia concentration (0.765 mg/L) at B1 site. The ammonia concentration in water was <0.02 to 0.13 mg/L in another site. The water sampling result was classified based on PP number 22 of 2021 implementation of protection and management of environment in sixth appendix about national water quality standard with third-class purpose. © 2021 Institute of Physics Publishing. All rights reserved.

Impact of the Covid Pandemic on Construction Organisations in India-a Case Study

The construction sector in India employs nearly 60 million people, so the unprecedented two-month lockdown to slow the spread of Covid-19 in 2020 had devastating economic and social effects. The reduced demand for projects slowed demand for downstream industries, increased labour migration to villages and reduced logistics support for supplies and resources. This paper reports on the challenges experienced by one of India's leading construction organisations on a major metro contract in Mumbai. It describes the impact of the pandemic on project delivery, including time, cost and supply chain issues, and discusses the mitigation strategies adopted. © 2021 ICE Publishing: All rights reserved.