【摘要】 文章以比较购物搜索中的商品数据自动分类为应用背景,探讨短文本数据的分类问题,比较了常用的文本分类算法的特点,在此基础上提出k-NN与NB相结合的多分类器方案,对于NB算法分类不可信的情况下改用k-NN算法进行再次分类,并充分利用NB的中间结果供k-NN剪枝时作参考。实验数据表明该方法在与NB相近的时间复杂度下可明显地提高短文本分类的正确率和召回率,达到实际应用的要求。更多还原

【Abstract】 On the basis of the application of the automatism in the comparison shopping,this paper has probe into the issue of text categorization.It has compared two popular algorithms for text categorization:Naive Bayes(NB) and k-Nearest Neighbor(k-NN).On this basis it proposed another suggestion-combining the two algorithms.In the situation that NB is unauthentic,K-NN arithmetic is suggested to be used to recategorize the result.And the k-NN algorithm can also make best use of the results from the NB algorithm during the process of re-categorization.The statistics from the experiment show that under the similar time complexity,the new algorithm can improve markedly the precision of the text categorization and the recall rate.It can reach the expected demand.更多还原