基于浏览记录的个性化新闻推荐实证分析

Personalized News Recommendations Based on Browsing History

通过构建基于物品的协同过滤推荐模型计算新闻之间的相似度,基于相似度矩阵向目标用户推荐与其喜欢的新闻相似度高的其他新闻,以满足用户获取心仪新闻的需求,提高用户浏览新闻时的体验感。结果表明,基于物品的协同过滤推荐算法能够有效提高推荐的精确率,且随着样本空间的增大,该算法会更有效。

The study constructs an item-based collaborative filtering recommendation model,calculates the similarity between news,and recommends other news with high similarity to their favorite news to target users based on the similarity matrix,so as to meet the needs of users to obtain the desired news and improve the experience of users when browsing news.The results show that the item-based collaborative filtering recommendation algorithm can effectively improve the accuracy rate of recommendation.With the increase of sample space,the algorithm will be more effective.