opinionTokenizer.py 文件源码

def tokenize_into_opinion_units(text):
    output = []
    for str in sent_tokenize(text):
        for output_str in str.split(' but '):
            output.append(output_str)
    return output

#Take positive.csv and negative.csv and mix them into
#positiveandnegative.csv
#This has each unit tagged with its booking.com sentiment
#This is the data I tagged with Mechanical Turk