A Course Recommender System of MOOC Based on Collaborative F
发布时间：2021-04-12 04:46
现阶段,越来越多的用户选择在大规模开放在线课程（Massive Open Online Course,MOOC）平台上学习课程。与传统的课堂教学不同,MOOC允许用户突破时间和空间的限制,在任何时间地点学习课程。同时,MOOC也打破了专业内容的限制,用户可以根据自己的喜好选择不同领域的课程,然而,由于MOOC上的课程众多,对MOOC平台和平台用户而言,MOOC系统如何帮助用户找到符合其个人兴趣的高质量课程成为一个亟待解决的问题。推荐系统是一种重要的内容过滤系统,系统可以基于用户的历史行为等信息为用户提供符合其个人偏好的优质内容。相比搜索引擎等信息获取方式,推荐系统可以更直接地分析用户的历史行为数据,挖掘用户的潜在个人偏好,为用户提供更加个性化的内容展现形式。作为MOOC平台的重要组成模块,课程推荐系统的好坏直接影响到了MOOC平台的使用体验,课程推荐系统的推荐质量也会对用户的学习效果产生直接的影响,是否能将符合用户偏好的高质量课程推荐给用户成为了衡量MOOC平台质量的重要指标。在MOOC平台上,推荐系统必须解决如下几个关键性问题:1.在MOOC系统中,存在着大量的不同领域的课程,如何将...
【文章来源】：华中师范大学湖北省 211工程院校 教育部直属院校
【文章页数】：63 页
【学位级别】：硕士
【文章目录】：
Abstract
1 Introduction
1.1 Research Background
1.2 Overseas and Domestic Research Status
1.3 Our Contribution
2 Literature Review on Recommendation Algorithms
2.1 Related Work of Recommendation Algorithms
2.1.1 Item-based Collaborative Filtering
2.1.2 User-based Collaborative Filtering
2.2 Performance Evaluation Indexes of Recommendation Algorithm
2.2.1 Prediction Accuracy Rate of Recommendation
2.2.2 Prediction Coverage Rate of Recommendation
2.2.3 Diversity of Recommendation
2.3 Summary of Existing Methods
2.4 Summary
3 A User-based Collaborative Filtering Algorithm with Improved PCC
3.1 The Procedure of User-based Collaborative Filtering with Improved PCC
3.1.1 Overview of User-CF Algorithm with Improved PCC
3.1.2 Improved Pearson Correlation Coefficient
3.1.3 Neighbor Set Construction Based on User Similarity
3.1.4 Rating Prediction Based on Neighbor Set
3.2 Experimental Results for User-CF with Improved PCC
3.2.1 Dataset Preparation for Experiment
3.2.2 Experimental Design
3.2.3 Experimental Results
3.3 Summary
4 Course Recommendation Based on Mixed Similarity with Improved PCC
4.1 Mixed Similarity Calculation with Multipliers of Improved PCC
4.1.1 Calculation of User Mixed Similarity
4.1.2 Similarity Optimization with Multipliers of Improved PCC
4.1.3 Recommendation Rating Correction Module Based on Quality Index
4.2 Experimental Results for Personalized Recommendation
4.2.1 Experimental Design
4.2.2 Experimental Results
4.3 Summary
5 Summary and Future Work
5.1 Summary
5.2 Future Work
References
Acknowledgements
Appendix A Abstract
本文编号：3132647
【文章来源】：华中师范大学湖北省 211工程院校 教育部直属院校
【文章页数】：63 页
【学位级别】：硕士
【文章目录】：
Abstract
1 Introduction
1.1 Research Background
1.2 Overseas and Domestic Research Status
1.3 Our Contribution
2 Literature Review on Recommendation Algorithms
2.1 Related Work of Recommendation Algorithms
2.1.1 Item-based Collaborative Filtering
2.1.2 User-based Collaborative Filtering
2.2 Performance Evaluation Indexes of Recommendation Algorithm
2.2.1 Prediction Accuracy Rate of Recommendation
2.2.2 Prediction Coverage Rate of Recommendation
2.2.3 Diversity of Recommendation
2.3 Summary of Existing Methods
2.4 Summary
3 A User-based Collaborative Filtering Algorithm with Improved PCC
3.1 The Procedure of User-based Collaborative Filtering with Improved PCC
3.1.1 Overview of User-CF Algorithm with Improved PCC
3.1.2 Improved Pearson Correlation Coefficient
3.1.3 Neighbor Set Construction Based on User Similarity
3.1.4 Rating Prediction Based on Neighbor Set
3.2 Experimental Results for User-CF with Improved PCC
3.2.1 Dataset Preparation for Experiment
3.2.2 Experimental Design
3.2.3 Experimental Results
3.3 Summary
4 Course Recommendation Based on Mixed Similarity with Improved PCC
4.1 Mixed Similarity Calculation with Multipliers of Improved PCC
4.1.1 Calculation of User Mixed Similarity
4.1.2 Similarity Optimization with Multipliers of Improved PCC
4.1.3 Recommendation Rating Correction Module Based on Quality Index
4.2 Experimental Results for Personalized Recommendation
4.2.1 Experimental Design
4.2.2 Experimental Results
4.3 Summary
5 Summary and Future Work
5.1 Summary
5.2 Future Work
References
Acknowledgements
Appendix A Abstract
本文编号：3132647
本文链接：https://www.wllwen.com/kejilunwen/ruanjiangongchenglunwen/3132647.html
