PQSCT: Pseudo-Siamese BERT for Concept Tagging With Both Questions and Solutions

The global outbreak of the new coronavirus epidemic has promoted the development of intelligent education and the utilization of online learning systems. In order to provide students with intelligent services such as cognitive diagnosis and personalized exercises recommendation, a fundamental task is the concept tagging for exercises, which extracts knowledge index structures and knowledge representations for exercises. Unfortunately, to the best of our knowledge, existing tagging approaches based on exercise content either ignore multiple components of exercises, or ignore that exercises may contain multiple concepts. To this end, in this paper, we present a study of concept tagging. First, we propose an improved pre-trained BERT for concept tagging with both questions and solutions (QSCT). Specifically, we design a question-solution prediction task and apply the BERT encoder to combine questions and solutions, ultimately obtaining the final exercise representation through feature augmentation. Then, to further explore the relationship between questions and solutions, we extend the QSCT to a pseudo-siamese BERT for concept tagging with both questions and solutions (PQSCT). We optimize the feature fusion strategy, which integrates five different vector features from local and global into the final exercise representation. Finally, we conduct extensive experiments on real-world datasets, which clearly demonstrate the effectiveness of our proposed models for concept tagging. IEEE

Diverse feature extraction techniques in internet search query to forecast tourism demand: An in-depth comparison

It is an effective approach to improve forecasting by extracting effective information from large panels of search query data. Feature extraction techniques (FETs) can extract information from all features by creating new fewer features based on algebraic transformation;however, they have not been extensively investigated and compared for tourism forecasting. We employ five FETs to process multi-dimensional search query data, and build a bunch of models based on econometrics, machine learning, ensemble learning and hybrid methods. The improving performances of FETs based on tourism demand forecasting in Sanya after COVID-19 and in Macau before COVID-19 are evaluated. The results show that forecasting models with FETs outperform the benchmark model SARIMAX without FETs, which demonstrates the efficacy of FETs in search query data extraction. This study provides meaningful guidance for improving the quality of multi-dimensional data and optimizing tourism forecasting. © 2023 Elsevier Ltd

Chinese EFL Teachers' Reflections of Online English Teaching during the COVID-19 Pandemic: A Qualitative Study

To better understand English as a Foreign Language (EFL) teachers' voices in online English teaching in China, a qualitative case study was carried out by analyzing semi-interviews, and in-depth data of six EFL teachers from a central Chinese university. With thematic analysis, seven themes emerged, including the choices of teaching platforms or Apps, the negative attitude, the preparation for online teaching, teaching design, teaching assessment, advantages, and challenges. Overall, the study contributed to the existing knowledge of online language teaching theoretically and practically by providing a Chinese contextual phenomenon of EFL teaching. © ICCE 2022.All rights reserved.

Survival in Pandemic Times: Managing Energy Efficiency, Food Diversity, and Sustainable Practices of Nutrient Intake Amid COVID-19 Crisis

The COVID-19 pandemic led to an economic crisis and health emergency, threatening energy efficiency consumption, sustainable food diversity, and households’ nutrition security. The literature documented that environmental threats can divert attention from renewable energy and food security challenges that affect humans’ environmental behaviors. The COVID-19 crisis has consistently influenced environmental behaviors, as it primarily decreased income and disrupted food systems worldwide. This study investigated the COVID-19 consequences on household income, sustainable food diversity, sustainable energy consumption, and nutritional security challenges. The study used a self-structured online survey due to non-pharmaceutical restrictions and collected data from 728 households. The investigators applied t-test and logit regression to analyze the data for drawing results. Descriptive statistics show that COVID-19 has adversely affected the income of more than two-thirds (67%) of households. The pandemic has influenced households’ food consumption, energy, and dietary patterns to safeguard their income. The t-test analysis indicated that households’ food diversity and energy consumption significantly declined during the pandemic, and households consumed low-diversified food to meet their dietary needs more than twofold compared to pre-pandemic levels. The results showed that all nutrient consumption remained considerably lower in the COVID-19. Cereals are the primary source of daily dietary needs, accounting for over two-thirds of total energy and half of the nutrient consumption amid COVID-19. The share of vegetables and fruits in household energy consumption dropped by 40 and 30%. Results exhibited that increasing monthly income was inversely associated with worsening food diversity and intake with energy efficiency. Compared with farmers and salaried employment, wage earners were 0.15 and 0.28 times more likely to experience a decline in consuming food diversity. Medium and large households were 1.95 times and 2.64 times more likely than small, to experience decreased food diversity consumption. Launching a nutrition-sensitive program will help minimize the COVID-19 impacts on energy consumption, food diversity, and nutritional security for low-income individuals. This survey relied on the recall ability of the households for the consumed quantities of food commodities, which may lack accuracy. Longitudinal studies employing probability sampling with larger samples can verify this study’s insightful results. Copyright © 2022 Geng, Haq, Abbas, Ye, Shahbaz, Abbas and Cai.

Heterogeneity learning for SIRS model: an application to the COVID-19

We propose a Bayesian Heterogeneity Learning approach for Susceptible-Infected-Removal-Susceptible (SIRS) model that allows underlying clustering patterns for transmission rate, recovery rate, and loss of immunity rate for the latest corona virus (COVID-19) among different regions. Our proposed method provides simultaneously inference on parameter estimation and clustering information which contains both number of clusters and cluster configurations. Specifically, our key idea is to formulates the SIRS model into a hierarchical form and assign the Mixture of Finite mixtures priors for heterogeneity learning. The properties of the proposed models are examined and a Markov chain Monte Carlo sampling algorithm is used to sample from the posterior distribution. Extensive simulation studies are carried out to examine empirical performance of the proposed methods. We further apply the proposed methodology to analyze the state level COVID-19 data in U.S.

[Preliminary analysis on COVID-19 case spectrum and spread intensity in different provinces in China except Hubei province].

Objective: To analyze the characteristics of COVID-19 case spectrum and spread intensity in different provinces in China except Hubei province. Methods: The daily incidence data and case information of COVID-19 were collected from the official websites of provincial and municipal health commissions. The morbidity rate, severity rate, case-fatality rate, and spread ratio of COVID-19 were calculated. Results: As of 20 March, 2020, a total of 12 941 cases of COVID-19 had been conformed, including 116 deaths, and the average morbidity rate, severity rate and case-fatality rate were 0.97/100 000, 13.5% and 0.90%, respectively. The morbidity rates in Zhejiang (2.12/100 000), Jiangxi (2.01/100 000) and Beijing (1.93/100 000) ranked top three. The characteristics of COVID-19 case spectrum varied from province to province. The first three provinces (autonomous region, municipality) with high severity rates were Tianjin (45.6%), Xinjiang (35.5%) and Heilongjiang (29.5%). The case-fatality rate was highest in Xinjiang (3.95%), followed by Hainan (3.57%) and Heilongjiang (2.70%). The average spread ratio was 0.98 and the spread intensity varied from province to province. Tibet had the lowest spread ratio (0), followed by Qinghai (0.20) and Guangdong (0.23). Conclusion: The intervention measures were effective in preventing the spread of COVID-19 and improved treatment effect in China. However, there were significant differences among different regions in severity, case-fatality rate and spread ratio.