Emotion recognition and achievement prediction for foreign language learners under the background of network teaching.

At present, there are so many learners in online classroom that teachers cannot master the learning situation of each student comprehensively and in real time. Therefore, this paper first constructs a multimodal emotion recognition (ER) model based on CNN-BiGRU. Through the feature extraction of video and voice information, combined with temporal attention mechanism, the attention distribution of each modal information at different times is calculated in real time. In addition, based on the recognition of learners' emotions, a prediction model of learners' achievement based on emotional state assessment is proposed. C4.5 algorithm is used to predict students' academic achievement in the multi-polarized emotional state, and the relationship between confusion and academic achievement is further explored. The experimental results show that the proposed multi-scale self-attention layer and multi-modal fusion layer can improve the achievement of ER task; moreover, there is a strong correlation between students' confusion and foreign language achievement. Finally, the model can accurately and continuously observe students' learning emotion and state, which provides a new idea for the reform of education modernization.

Application of network teaching in nursing undergraduate education during the coronavirus disease 2019 epidemic.

BACKGROUND AND OBJECTIVES: Coronavirus disease 2019 (COVID-19) is currently raging all over the world. COVID-19 can be transmitted among humans. To control the spread of the epidemic and meet the learning needs of students, Chinese universities have used a variety of multimedia forms to conduct online teaching. However, the influence of different teaching methods on the learning effects of nursing students has not been conclusive, and few studies have directly compared the differences in the effects of different teaching methods. Therefore, it is necessary to evaluate the impact of different teaching methods on students' learning effects. METHODS: A total of 119 participants from the graduating class of 2022 performed 4 validated classes (fundamental nursing, medical nursing, surgical nursing, and paediatric nursing) through network teaching. A total of 126 participants from the graduating class of 2021 used the traditional teaching method and were enrolled as a control group. All participants completed a questionnaire, which was designed by the school for teaching evaluation, and took a test after the courses. RESULTS: A total of 245 nursing undergraduates were ultimately enrolled. The analysis of the academic performance and the student evaluations from the four courses showed no significant difference between the network teaching group and the traditional teaching group for nursing undergraduates (all P > 0.05). CONCLUSION: Through the convenience of network teaching, teachers and students can choose the time and place of both their teaching and learning independently. Moreover, such use effectively prevents the spread of the epidemic. After the epidemic concludes, the continued use of the network teaching method can help improve teaching efficiency by being combined with the traditional teaching method.

Analysis of factors influencing the network teaching effect of college students in a medical school during the COVID-19 epidemic.

BACKGROUND: The purpose of this study is to understand the influencing factors of Chinese college students' satisfaction with online teaching and psychological pressure on learning during the novel coronavirus epidemic. METHODS: We assessed the effect of online teaching of 7084 medical students from wannan medical college in March 5 to April 2, 2020 using cluster sampling. The respondents were asked to complete a 7-item self-compiled online teaching satisfaction questionnaire. Chi-square test and multivariate logistic regression analysis are used. RESULTS: Sex is female (OR = 1.257, 95%CI: 1.132 ~ 1.396), grades are second and third grades (second grades: OR = 1.228, 95%CI: 1.080 ~ 1.397; third grades: OR = 1.197, 95%CI: 1.048 ~ 1.367), normal/unfamiliar learning platform operation (OR = 3.692, 95%CI: 3.321 ~ 4.103) were risk factors for satisfactory teaching effect. In addition, students whose school year system is four-year (OR = 0.870, 95%CI: 0.781 ~ 0.969) and grade 4 and above (OR = 0.594, 95%CI: 0.485 ~ 0.727) were more satisfied with the teaching effect of teachers. And, during the period of the COVID-19 epidemic, the risk factors for college students to have psychological stress were: female (OR = 1.258, 95%CI: 1.096 ~ 1.442), from rural areas (OR = 1.511, 95%CI: 1.312 ~ 1.740), and the academic year system is four-year system (OR = 1.191, 95%CI: 1.028 ~ 1.380), using mobile phones and other learning tools (OR = 1.388, 95%CI: 1.205 ~ 1.600), general/unfamiliar with learning platform operations (OR = 2.273), 95%CI: 1.888 ~ 2.735). While the protective factors for college students' psychological stress included: grade three and four and above (OR = 0.463, 95%CI: 0.387 ~ 0.554; OR = 0.232, 95%CI: 0.187 ~ 0.286), and they think that the teaching effect is satisfactory (OR = 0.314, 95%CI: 0.261 ~ 0.379). CONCLUSION: This survey shows that compared with male college students, female college students were more dissatisfied with the teaching effect of teachers and havd greater psychological pressure on learning. Psychological counseling should be strengthened for students in rural areas and those who were not familiar with the operating platform to relieve their psychological pressure on learning.

An integrated multi-criteria decision making approach with linguistic hesitant fuzzy sets for E-learning website evaluation and selection.

Network teaching has been widely developed under the influence of COVID-19 pandemic to guarantee the implementation of teaching plans and protect the learning rights of students. Selecting a particular website for network teaching can directly affects end users' performance and promote network teaching quality. Normally, e-learning website selection can be considered as a complex multi-criteria decision making (MCDM) problem, and experts' evaluations over the performance of e-learning websites are often imprecise and fuzzy due to the subjective nature of human thinking. In this article, we propose a new integrated MCDM approach on the basis of linguistic hesitant fuzzy sets (LHFSs) and the TODIM (an acronym in Portuguese of interactive and multi-criteria decision making) method to evaluate and select the best e-learning website for network teaching. This introduced method deals with the linguistic assessments of experts based on the LHFSs, determines the weights of evaluation criteria with the best-worst method (BWM), and acquires the ranking of e-learning websites utilizing an extended TODIM method. The applicability and superiority of the presented linguistic hesitant fuzzy TODIM (LHF-TODIM) approach are demonstrated through a realistic e-learning website selection example. Results show that the LHF-TODIM model being proposed is more practical and effective for solving the e-learning website selection problem under vague and uncertain linguistic environment.