数据集下载探索模块:IMDB数据集(英文)和THUCNews数据集(中文)
THUCNews中文数据集:https://pan.baidu.com/s/1hugrfRu 密码:qfud
下载后为四个文件,cnews.train.txt
、cnews.val.txt
、cnews.test.txt
、cnews.vocab.txt
IMDB英文数据集: IMDB数据集 Sentiment Analysis
或者使用keras
IMDB Movie reviews sentiment classification
- Dataset of 25,000 movies reviews from IMDB, labeled by sentiment (positive/negative). Reviews have been preprocessed, and each review is encoded as a sequence of word indexes (integers). For convenience, words are indexed by overall frequency in the dataset, so th