学习资料:
https://www.youtube.com/watch?v=si8zZHkufRY&list=PL2-dafEMk2A7YdKv4XfKpfbTH5z6rEEj3&index=5
情感分析,
就是要识别出用户对一件事一个物或一个人的看法、态度,比如一个电影的评论,一个商品的评价,一次体验的感想等等。根据对带有情感色彩的主观性文本进行分析,识别出用户的态度,是喜欢,讨厌,还是中立。
关于情感分析,之前有一篇 cs224d 的小项目:
里面用 skipgram 学习出 word vector,然后用 softmax regression 进行识别:
今天的方法是用 20 行代码实现这个过程:
用 tflearn.data_utils 的 pad_sequences 将 strings 转化成向量,用 tflearn.embedding 得到 word vector,再传递给 LSTM 得到 feature vector,经过全联接层后,再用一个分类器,loss 为 categorical_crossentropy
from __future__ import division, print_function, absolute_import
import tflearn
from tflearn.data_utils import to_categorical, pad_sequences
from tflearn.datasets import imdb
# IMDB Dataset loading
train, test, _ = imdb.load_data(path='imdb.pkl', n_words=10000,
valid_portion=0.1)
trainX, trainY = train
testX, testY = test
# Data preprocessing
# Sequence padding
trainX = pad_sequences(trainX, maxlen=100, value=0.)
testX = pad_sequences(testX, maxlen=100, value=0.)
# Converting labels to binary vectors
trainY = to_categorical(trainY, nb_classes=2)
testY = to_categorical(testY, nb_classes=2)
# Network building
net = tflearn.input_data([None, 100])
net = tflearn.embedding(net, input_dim=10000, output_dim=128)
net = tflearn.lstm(net, 128, dropout=0.8)
net = tflearn.fully_connected(net, 2, activation='softmax')
net = tflearn.regression(net, optimizer='adam', learning_rate=0.001,
loss='categorical_crossentropy')
# Training
# 模型初始化
model = tflearn.DNN(net, tensorboard_verbose=0)
# show_metric=True 可以看到过程中的准确率
model.fit(trainX, trainY, validation_set=(testX, testY), show_metric=True,
batch_size=32)