Students learning performance prediction based on feature extraction algorithm and attention-based bidirectional gated recurrent unit network.

With the development of information technology construction in schools, predicting student grades has become a hot area of application in current educational research. Using data mining to analyze the influencing factors of students' performance and predict their grades can help students identify their shortcomings, optimize teachers' teaching methods and enable parents to guide their children's progress. However, there are no models that can achieve satisfactory predictions for education-related public datasets, and most of these weakly correlated factors in the datasets can still adversely affect the predictive effect of the model. To solve this issue and provide effective policy recommendations for the modernization of education, this paper seeks to find the best grade prediction model based on data mining. Firstly, the study uses the Factor Analyze (FA) model to extract features from the original data and achieve dimension reduction. Then, the Bidirectional Gate Recurrent Unit (BiGRU) model and attention mechanism are utilized to predict grades. Lastly, Comparing the prediction results of ablation experiments and other single models, such as linear regression (LR), back propagation neural network (BP), random forest (RF), and Gate Recurrent Unit (GRU), the FA-BiGRU-attention model achieves the best prediction effect and performs equally well in different multi-step predictions. Previously, problems with students' grades were only detected when they had already appeared. However, the methods presented in this paper enable the prediction of students' learning in advance and the identification of factors affecting their grades. Therefore, this study has great potential to provide data support for the improvement of educational programs, transform the traditional education industry, and ensure the sustainable development of national talents.

Efficacy and safety of immunochemotherapy, immunotherapy, chemotherapy, and targeted therapy as first-line treatment for advanced and metastatic esophageal cancer: a systematic review and network meta-analysis.

Background: The treatment of esophageal cancer has entered a new phase with the development of immunotherapy. The current investigation purpose is to investigate and contrast the efficacy and safety of immunotherapy, immunochemotherapy, chemotherapy, and targeted therapy as first-line treatment for individuals suffering from advanced and metastatic esophageal cancer. Methods: Within the framework of this systematic review and network meta-analysis, clinical trials published or reported in English up until 01 May, 2022, were retrieved from Embase, PubMed, Cochrane Central Register of Controlled Trials, the ClinicalTrials.gov databases, ESMO, and ASCO. The analysis incorporated randomized controlled trials (RCTs) from phase 2 to 3 that evaluated a minimum of two first-line therapeutic regimens for metastatic esophageal cancer were included in the analysis. The primary outcomes were overall survival (OS) and progression-free survival (PFS). Secondary clinical outcomes included the incidence of objective response rate (ORR), and adverse events (AEs) of any grade and ≥3 grade. Relative summary data were extracted from included studies by GZ, HS, WS, and TD. For clear statistical analysis, chemotherapy was divided into two categories of fluorouracil-based chemotherapy (FbCT) and fluorouracil-free chemotherapy (FfCT). Bayesian frequentist approach was employed to conduct the network meta-analysis. The indirect intercomparison between regimens was presented with league tables (HRs and 95% CI for OS and PFS, ORs and 95% CI for ORR and AEs). A greater surface value under the cumulative ranking (SUCRA) indicates a higher potential ranking for the corresponding treatment. A further calculation of relative results about esophageal squamous cell cancer was performed in the subgroup analysis. The current protocol for the systematic review has been properly registered on PROSPERO (registration number: CRD42021241145). Findings: The final analysis comprised 17 trials that involved 9128 patients and 19 distinct treatment regimens. Within the scope of investigated immunotherapy (IO) combinations, toripalimab + FfCT (tori + FfCT) demonstrated the best OS advantages (tori + FfCT vs. FbCT, HR 0.57, 95% CI 0.38-0.85; tori + FfCT vs. FfCT, HR 0.58, 95% CI 0.43-0.78). In terms of PFS, camrelizumab + FfCT (cam + FfCT) demonstrated the best PFS advantages (FbCT vs. cam + FfCT, HR 1.79, 95% CI 1.22-2.63; FfCT vs. cam + FfCT, HR 1.79, 95% CI 1.47-2.17). Nivolumab + FbCT (nivo + FbCT vs. FfCT, OR 3.29, 95% CI 1.43-7.56) showed the best objective responses. Compared to the conventional chemotherapy regimen, the toxicity was observed to be the slightest for the tori + FfCT (FbCT vs. tori + FfCT, OR 3.07, 95% CI 1.22-7.7) and sintilimab + FfCT (FbCT vs. sin + FfCT, OR 2.93, 95% CI 1.16-7.37). The results in this study were evaluated as having a low heterogeneity since the I2 value was ≤25% in all analyses. Interpretation: Compared to foreign IO combinations, sin + FfCT, tori + FfCT, cam + FfCT, and tisle + FbCT are superior first-line treatment options for patients with advanced and metastatic esophageal cancer. Although foreign IO combinations, such as pembro + FbCT and nivo + FbCT obtained better objective response rates than other IO combinations, the addition of chemotherapy to IO worsens the safety profiles. Our findings could provide complementary evidence for current guideline recommendations. Funding: This work was supported by a grant from the Science and Technology Program of Guangzhou, China (202206010103); and Natural Science Foundation of Guangdong Province (2022A1515012469).

Extractive text summarization model based on advantage actor-critic and graph matrix methodology.

The automatic text summarization task faces great challenges. The main issue in the area is to identify the most informative segments in the input text. Establishing an effective evaluation mechanism has also been identified as a major challenge in the area. Currently, the mainstream solution is to use deep learning for training. However, a serious exposure bias in training prevents them from achieving better results. Therefore, this paper introduces an extractive text summarization model based on a graph matrix and advantage actor-critic (GA2C) method. The articles were pre-processed to generate a graph matrix. Based on the states provided by the graph matrix, the decision-making network made decisions and sent the results to the evaluation network for scoring. The evaluation network got the decision results of the decision-making network and then scored them. The decision-making network modified the probability of the action based on the scores of the evaluation network. Specifically, compared with the baseline reinforcement learning-based extractive summarization (Refresh) model, experimental results on the CNN/Daily Mail dataset showed that the GA2C model led on Rouge-1, Rouge-2 and Rouge-A by 0.70, 9.01 and 2.73, respectively. Moreover, we conducted multiple ablation experiments to verify the GA2C model from different perspectives. Different activation functions and evaluation networks were used in the GA2C model to obtain the best activation function and evaluation network. Two different reward functions (Set fixed reward value for accumulation (ADD), Rouge) and two different similarity matrices (cosine, Jaccard) were combined for the experiments.

Sentiment Classification of Chinese Tourism Reviews Based on ERNIE-Gram+GCN.

Nowadays, tourists increasingly prefer to check the reviews of attractions before traveling to decide whether to visit them or not. To respond to the change in the way tourists choose attractions, it is important to classify the reviews of attractions with high precision. In addition, more and more tourists like to use emojis to express their satisfaction or dissatisfaction with the attractions. In this paper, we built a dataset for Chinese attraction evaluation incorporating emojis (CAEIE) and proposed an explicitly n-gram masking method to enhance the integration of coarse-grained information into a pre-training (ERNIE-Gram) and Text Graph Convolutional Network (textGCN) (E2G) model to classify the dataset with a high accuracy. The E2G preprocesses the text and feeds it to ERNIE-Gram and TextGCN. ERNIE-Gram was trained using its unique mask mechanism to obtain the final probabilities. TextGCN used the dataset to construct heterogeneous graphs with comment text and words, which were trained to obtain a representation of the document output category probabilities. The two probabilities were calculated to obtain the final results. To demonstrate the validity of the E2G model, this paper was compared with advanced models. After experiments, it was shown that E2G had a good classification effect on the CAEIE dataset, and the accuracy of classification was up to 97.37%. Furthermore, the accuracy of E2G was 1.37% and 1.35% ahead of ERNIE-Gram and TextGCN, respectively. In addition, two sets of comparison experiments were conducted to verify the performance of TextGCN and TextGAT on the CAEIE dataset. The final results showed that ERNIE and ERNIE-Gram combined TextGCN and TextGAT, respectively, and TextGCN performed 1.6% and 2.15% ahead. This paper compared the effects of eight activation functions on the second layer of the TextGCN and the activation-function-rectified linear unit 6 (RELU6) with the best results based on experiments.