Student evaluations of teaching (SET) have become a popular approach to assess faculties’ teaching. Question‐score‐based questionnaire is the most common SET measure adopted in universities. However, it fails to cover important facets of teaching process that not mentioned in the predefined questionnaire, which can be substantially obtained from students’ short reviews. In this paper, we propose two lexical‐based methods, specifically knowledge‐based and machine learning‐based, to automatically extract opinions from short reviews. Furthermore, the diversity of reviews’ themes and styles of same sentiment polarity reviews can be observed from the extracted opinion results. The experimental results show that the proposed methods are able to achieve accuracies of 78.13 and 84.78%, respectively in the task of student review sentiment classification. Further investigation on linguistic features shows that reviews with same sentiment polarity shares similar language patterns. Finally, we present an application scenario in real SET process by utilizing aforementioned methods and discoveries.

No abstract

No abstract

No abstract

Predicting future academic rising stars provides a useful reference for research communities, such as offering decision support to recruit young researchers in research institutes. Academic rising stars prediction is considered to be a classification or regression task in the field of machine learning. Traditional methods of building label information for this task are only based on the increment of citation count, which cannot adequately reflect the evolution of a scholar's academic influence. In this paper, we first propose a non-iterative hierarchical weighted evaluation model based on the quality of citing papers and the influence of co-authors. Second, we label each young scholar by the increment of the impact score from our evaluation model in the classification task, aiming at better describing the change of a scholar's impact from more angles. Finally, different groups of features that can determine if a scholar will be a rising star are extracted, and various classification models are utilized to fit the classification relationships. The experimental results on the ArnetMiner dataset verify the feasibility of the prediction task based on our label construction method. We also find that the venue features are the best indicators for rising stars prediction in our experiments.