Research on Personalized Recommendation Based on Semi--supervised Learning and Active Learning

目录

声明

Abstract

Table of contents

List of figures

List of tables

Chapter 1 INTRODUCTION

1．1 Research Background and Significance

1．2 Research Actuality

1．3 Article Content and Structure

Chapter 2 Basic Theory of Recommendation Algorithms

2．1 Common Recommendation Algorithm

2．1．2 Domain-based Recommendation

2．1．4 Hybrid Recommendation

2．2 Recommendation System Evaluation

2．2．1 Experimental Method

2．2．2 Recommended System Properties

2．3 Recommended System Challenge

Chapter 3 Research on Recommendation Algorithm Based on Semi-supervised Learning

3．1 Research Motivation

3．2 SSC-UF-CF Algorithm Framework

3．2．1 K-Means Algorithm

3．2．2 Analysis of Probability Matrix Based on LDA

3．3 Recommendation Algorithm Based on Semi-supervised Clustering and User Features

3．3．1 Cluster Analysis Based on User Feature

3．3．2 User-item Preference Probability Matrix

3．3．3 SSC-UF-CF Algorithm Implementation

3．4 Experiment

3．4．1 Experiment Design

3．4．2 Experiment Analysis

3．5 Chapter Summary

Chapter 4 Research on Recommendation Algorithm Based on Active Learning

4．1 Research Motivation

4．2 SSC-UF-CF Based on Active learning Algorithm Framework

4．2．1 Selection Strategy Based on Rating Uncertainty

4．2．2 Recommendation Algorithm Based on Rating Uncertainty

4．2．3 Algorithm Description

4．3 Experiment

4．3．1 Experiment Design

4．3．2 Experiment Result Analyse

4．4 Chapter Summary

Chapter 5 Implementation of Movie Recommendation System Based on Hybrid Recommendation Algorithm

5．1 Movie Recommendation System Design

5．1．1 Demand Analysis

5．1．2 System Structure

5．2 System Implementation

5．2．1 Database Design

5．2．2 Recommended Module Design

5．2．3 Recommended Display

5．3 Chapter Summary

Chapter 6 Summary and Outlook

6．1 Summary

6．2 Outlook

References

Appendix

Acknowledgements