Dataset Description
The task is to do a mini-research for solving a sentiment analysis task. In this sentiment analysis task, you need to classify whether the sentiment of a text is positive (labeled as 1) or negative (labeled as 0).
train.csv
contains 8544 rows, where each row has three columns:
ID
: a positive integer that represents the sentence identifier
Sentence
: the raw text to be analyzed
Label
: an integer number between [0, 1] represent the label of the corresponding text.
0
means the text has a negative sentiment
1
means the text has a positive sentiment
test.csv
contains 2,000 rows, where each row has 2 columns, same as the
train.csv
but without the
Label
column.