Peer reviews of academic articles contain reviewers’ overall impressions and specific comments on the contributed articles,which have a lot of sentimental information.By exploring the fine-grained sentiments in peer ...Peer reviews of academic articles contain reviewers’ overall impressions and specific comments on the contributed articles,which have a lot of sentimental information.By exploring the fine-grained sentiments in peer reviews,we can discover critical aspects of interest to the reviewers.The results can also assist editors and chairmen in making final decisions.However,current research on the aspects of peer reviews is coarse-grained,and mostly focuses on the overall evaluation of the review objects.Therefore,this paper constructs a multi-level fine-grained aspect set of peer reviews for further study.First,this paper uses the multi-level aspect extraction method to extract the aspects from peer reviews of ICLR conference papers.Comparative experiments confirm the validity of the method.Secondly,various Deep Learning models are used to classify aspects’ sentiments automatically,with LCFS-BERT performing best.By calculating the correlation between sentimental scores of the review aspects and the acceptance result of papers,we can find the important aspects affecting acceptance.Finally,this paper predicts acceptance results of papers(accepted/rejected) according to the peer reviews.The optimal acceptance prediction model is XGboost,achieving a Macro_F1 score of 87.43%.展开更多
There are learners who cannot solve practical problems in spite of mastering basic scientific knowledge and formula necessary for the solution. One of the reasons might be attributed to the lack in metacognitive abili...There are learners who cannot solve practical problems in spite of mastering basic scientific knowledge and formula necessary for the solution. One of the reasons might be attributed to the lack in metacognitive abilities. The aim of this study was to compare the metacognitive characteristics between non-major and major students in electric engineering and clarify the difference of metacognitive process between these two groups when solving basic problems of electronic circuit. In the experiment, the solving process was compared between non-major and major students in electric engineering using five basic problems. We found that the scores on prediction of result and confidence of own answer differed significantly between non-major and major students, and inferred that the difference of performance was due to the lack in metacognitive ability, especially the plan and the execution abilities. Both prediction of results and confidence of own answer were also found to play a significant role in effective problem solving as important components （subsystems） of metacognition.展开更多
基金This work is supported by Opening fund of Key Laboratory of Rich-media Knowledge Organization and Service of Digital Publishing Content(No.zd2022-10/02).
文摘Peer reviews of academic articles contain reviewers’ overall impressions and specific comments on the contributed articles,which have a lot of sentimental information.By exploring the fine-grained sentiments in peer reviews,we can discover critical aspects of interest to the reviewers.The results can also assist editors and chairmen in making final decisions.However,current research on the aspects of peer reviews is coarse-grained,and mostly focuses on the overall evaluation of the review objects.Therefore,this paper constructs a multi-level fine-grained aspect set of peer reviews for further study.First,this paper uses the multi-level aspect extraction method to extract the aspects from peer reviews of ICLR conference papers.Comparative experiments confirm the validity of the method.Secondly,various Deep Learning models are used to classify aspects’ sentiments automatically,with LCFS-BERT performing best.By calculating the correlation between sentimental scores of the review aspects and the acceptance result of papers,we can find the important aspects affecting acceptance.Finally,this paper predicts acceptance results of papers(accepted/rejected) according to the peer reviews.The optimal acceptance prediction model is XGboost,achieving a Macro_F1 score of 87.43%.
文摘There are learners who cannot solve practical problems in spite of mastering basic scientific knowledge and formula necessary for the solution. One of the reasons might be attributed to the lack in metacognitive abilities. The aim of this study was to compare the metacognitive characteristics between non-major and major students in electric engineering and clarify the difference of metacognitive process between these two groups when solving basic problems of electronic circuit. In the experiment, the solving process was compared between non-major and major students in electric engineering using five basic problems. We found that the scores on prediction of result and confidence of own answer differed significantly between non-major and major students, and inferred that the difference of performance was due to the lack in metacognitive ability, especially the plan and the execution abilities. Both prediction of results and confidence of own answer were also found to play a significant role in effective problem solving as important components （subsystems） of metacognition.
