如何在不同类别下对输入文本进行分类

Question

文本= "my dog is a rice eater", "I want to buy an a new","my cat prefers chocolate milk"

我如何从这些文本（或文本语料库）中提取关键字并将它们分类为不同的类别（即狗、猫被归类为宠物和米饭、巧克力牛奶被归类为食物）

Answer 1

你被否决了，因为这个问题没有提供足够的细节来说明你的意思"classify"，也因为你没有显示你希望达到的目标结果。

这里有一个基本的答案，但是：您可以创建一个字典并根据字典计算命中率。在 quanteda 中，它是这样工作的：

text <- c("my dog is a rice eater", 
          "I want to buy an a new",
          "my cat prefers chocolate milk")

library("quanteda")

fooddict <- dictionary(list(pet = c("cat", "dog"),
                            food = c("rice", "chocolate milk")))

dfm(text, dictionary = fooddict)
# Document-feature matrix of: 3 documents, 2 features (33.3% sparse).
# 3 x 2 sparse Matrix of class "dfmSparse"
#        features
# docs    pet food
#   text1   1    1
#   text2   0    0
#   text3   1    1

如何在不同类别下对输入文本进行分类

how to classify input text under different categories

r

text-classification