文本分类的神经网络

Question

I am trying to train a model on text classification. I have a large labeled dataset. I have tried scikit classifiers NaiveBayes, KNeighborsClassifier, RandomForest etc. But i cannot get an accuracy above 30%. How can i use the Neural Networks for text classification? Here is the algo i have used so far

   df = read_csv(filename, sep="|", na_values=[" "]).fillna(" ")
   le = preprocessing.LabelEncoder()
   target = le.fit_transform(df['label'])

   vectorizer = TfidfVectorizer(sublinear_tf=True, 
                           max_df=0.3,
                           min_df=100,
                           lowercase=True,
                           stop_words='english', 
                           max_features=20000,
                           tokenizer=tokenize,
                           ngram_range=(1,4)
                          )

   train = vectorizer.fit_transform(df['data'])
   X_train, X_test, y_train , y_test = cross_validation.train_test_split(train, target, test_size=5000, random_state=0)
   clf = MultinomialNB(alpha=.1)
   clf.fit(X_train, y_train)
   pred = clf.predict(X_test)

My dataset contains about 300k documents, and vectorizer can produce upto 50k features. I have even tried chisquare to reduce the number of features to 5k, but still accuracy does not improve much.

Nature of Data Documents are set of comments, notes on a incident. Labels are high level categories for the incidents. As expected, the comments and notes are subjected to human errors, misspellings.

Answer 1

You need to improve the quality of your features. I suggest you form a new question around how to design features for this problem before dealing with the classifier algorithm. From the bad accuracy you report using a few methods, and the description that should be the weakest point you address first.