Fine-grained aspect-based opinion mining on online course reviews for feedback analysis

Online learning has developed rapidly and billions of learners have participated in various courses. However, the high dropout rate is universal and learning performance is not satisfactory. Fortunately, learners have posted a large number of reviews which express their feedback opinions. The fine-grained aspects and opinions existing in reviews provide valuable information for educators to improve learning performance. Thus, it is necessary to make fine-grained aspect-based opinion mining on course reviews for feedback analysis. First, the latent Dirichlet allocation is applied to generate topics and the topic related words from course reviews. Each word belongs to a topic and these words are considered as the core aspects. Second, a series of rules and an algorithm are designed based on dependency syntax analysis to extract the fine-grained aspects and opinions. The aspect-based opinion candidate set is generated. Then the corresponding opinions of the core aspects are selected from the candidate set. Third, the sentiment score of each opinion is calculated combining the dictionary-based and pointwise mutual information method to identify the polarity of the opinion. The extracted aspects and opinions with sentiment polarity provide fine-grained feedback information from several topic perspectives.

Automated summary

Online learning has grown rapidly with billions of participants, but the high dropout rate and unsatisfactory learning performance persist. However, learners' reviews provide valuable feedback for improvement. Hence, it is necessary to perform fine-grained aspect-based opinion mining on course reviews to analyze feedback.