在文本文件中查找与性别相关的词

Question

所以说，我有以下声明str = What recent discussions she has had with the Secretary of State for Work and Pensions on the effect of that Department’s welfare policies on women

在陈述中，你可以清楚地看到这个问题是用“她”这样的词向女人提出的。如何在给定的文本中找到特定于女性的词（例如，参见上面的文本）以及使用 python 使用它们的次数。 例如

maleWords = '[He, his]'
femaleWords = '[She,her]'

word="What recent discussions she has had with the Secretary of State for Work and Pensions on the effect of that Department’s welfare policies on women"

maleCount = sum(如果是maleWords中的单词则为1，否则对于maleWords中的单词为0) femaleCount = sum(1 if word in femaleWords else 0 for word in femaleWords)

target_gender = 'male' if maleCount >= femaleCount else 'female' print(f"文本的目标性别是{target_gender}")

但是结果显示目标性别是男性，而通过查看句子目标性别是女性。

Answer 1

您可以使用this page 获取特定性别的单词并将它们+他/她添加到相应的列表中。

maleWords = [mw0, m1, m2...]
femaleWords = [fm0, f1, f2...]

然后计算男性单词与女性单词中文本单词的出现次数，并将文本的目标性别设置为更高的计数。例如：

message = 'What recent discussions she has had with the Secretary of State for Work and Pensions on the effect of that Department’s welfare policies on women'

maleWords = ['he', 'his']
femaleWords = ['she', 'her']

maleCount = sum(1 if word in maleWords else 0 for word in message.lower().split())
femaleCount = sum(1 if word in femaleWords else 0 for word in message.lower().split())

target_gender = 'male' if maleCount >= femaleCount else 'female'
print(f"text's target gender is {target_gender}")

输出：

text's target gender is female

您首先将文本设为小写，因此 (He, HE, hE...) 也会被计算在内。