It is possible to do CountVectorizer matrix with more than one parameters?

Question

I am trying to count how many times a word in sentences is used by a particular users and role. This code is work as expected, but I dont have any idea what if I want to add one more criteria in my matrix.

My dataframe is:

Sentence_list=[['A', 'B','text1'],['C','D', 'text2'],['E','F', 'text3']]

Header names are:

col 0: index_name
col 1: role
col 2: text

And this is what I do with my code (that is work as expected):

matrix_means=vectorizer.fit_transform(df_train['text'])
count_array_means=matrix_means.toarray()
counts_means=pd.DataFrame(data=count_array_means, index=df_train.index_name, columns=vectorizer.get_feature_names())
print(counts_means)

The expected output should be like this:

   index_name               role             token1      token2      token3
0  A                        B                2           0           1
1  C                        D                0           1           1
2  E                        F                1           0           0

Is it possible to do something like that using CountVectorizer? I really appreciate for your help.