Abstract Purpose Opinion mining and sentiment analysis in Online Learning Community can truly reflect the students’ learning situation, which provides the necessary theoretical basis for following revision of teaching plans. To improve the accuracy of topic-sentiment analysis, a novel model for topic sentiment analysis is proposed that outperforms other state-of-art models. Methodology/approach We aim at highlighting the identification and visualization of topic sentiment based on learning topic mining and sentiment clustering at various granularity-levels. The proposed method comprised data preprocessing, topic detection, sentiment analysis, and visualization. Findings The proposed model can effectively perceive students’ sentiment tendencies on different topics, which provides powerful practical reference for improving the quality of information services in teaching practice. Research limitations The model obtains the topic-terminology hybrid matrix and the document-topic hybrid matrix by selecting the real user’s comment information on the basis of LDA topic detection approach, without considering the intensity of students’ sentiments and their evolutionary trends. Practical implications The implication and association rules to visualize the negative sentiment in comments or reviews enable teachers and administrators to access a certain plaint, which can be utilized as a reference for enhancing the accuracy of learning content recommendation, and evaluating the quality of their services. Originality/value The topic-sentiment analysis model can clarify the hierarchical dependencies between different topics, which lay the foundation for improving the accuracy of teaching content recommendation and optimizing the knowledge coherence of related courses.

中文翻译：

---

大学生在线学习社区中的主题情感分析

摘要目的在线学习社区中的观点挖掘和情感分析能够真实反映学生的学习状况，为后续的教学计划修订提供必要的理论基础。为了提高主题情感分析的准确性，提出了一种新颖的主题情感分析模型，该模型优于其他最新模型。方法论/方法我们旨在基于在各种粒度级别上学习主题挖掘和情感聚类的基础上，突出显示主题情感的识别和可视化。所提出的方法包括数据预处理，主题检测，情感分析和可视化。结果所提出的模型可以有效地感知学生在不同主题上的情绪倾向，为提高教学实践中信息服务质量提供了有力的实践参考。研究局限性该模型通过在LDA主题检测方法的基础上选择真实用户的评论信息来获得主题-术语混合矩阵和文档-主题混合矩阵，而无需考虑学生的情绪强度及其演变趋势。实际含义隐含和关联规则可以可视化评论或评论中的负面情绪，使教师和管理人员可以访问特定的原告，可以用作提高学习内容推荐的准确性和评估其服务质量的参考。