Stanford nlp for python

Question

All I want to do is find the sentiment (positive/negative/neutral) of any given string. On researching I came across Stanford NLP. But sadly its in Java. Any ideas on how can I make it work for python?

Answer 1

Use stanfordcore-nlp python library

stanford-corenlp is a really good wrapper on top of the stanfordcore-nlp to use it in python.

wget http://nlp.stanford.edu/software/stanford-corenlp-full-2018-10-05.zip

Usage

# Simple usage
from stanfordcorenlp import StanfordCoreNLP

nlp = StanfordCoreNLP('/Users/name/stanford-corenlp-full-2018-10-05')

sentence = 'Guangdong University of Foreign Studies is located in Guangzhou.'
print('Tokenize:', nlp.word_tokenize(sentence))
print('Part of Speech:', nlp.pos_tag(sentence))
print('Named Entities:', nlp.ner(sentence))
print('Constituency Parsing:', nlp.parse(sentence))
print('Dependency Parsing:', nlp.dependency_parse(sentence))

nlp.close() # Do not forget to close! The backend server will consume a lot memory.

More info

Answer 2

I also faced similar situation. Most of my projects are in Python and sentiment part is Java. Luckily it's quite easy to lean how to use the stanford CoreNLP jar.

Here is one of my scripts and you can download jars and run it.

import java.util.List;
import java.util.Properties;
import edu.stanford.nlp.ling.CoreAnnotations;
import edu.stanford.nlp.neural.rnn.RNNCoreAnnotations;
import edu.stanford.nlp.pipeline.Annotation;
import edu.stanford.nlp.pipeline.StanfordCoreNLP;
import edu.stanford.nlp.sentiment.SentimentCoreAnnotations.SentimentAnnotatedTree;
import edu.stanford.nlp.trees.Tree;
import edu.stanford.nlp.util.ArrayCoreMap;
import edu.stanford.nlp.util.CoreMap;

public class Simple_NLP {
static StanfordCoreNLP pipeline;

    public static void init() {
        Properties props = new Properties();
        props.setProperty("annotators", "tokenize, ssplit, parse, sentiment");
        pipeline = new StanfordCoreNLP(props);
    }

    public static String findSentiment(String tweet) {
        String SentiReturn = "";
        String[] SentiClass ={"very negative", "negative", "neutral", "positive", "very positive"};

        //Sentiment is an integer, ranging from 0 to 4. 
        //0 is very negative, 1 negative, 2 neutral, 3 positive and 4 very positive.
        int sentiment = 2;

        if (tweet != null && tweet.length() > 0) {
            Annotation annotation = pipeline.process(tweet);

            List<CoreMap> sentences = annotation.get(CoreAnnotations.SentencesAnnotation.class);
            if (sentences != null && sentences.size() > 0) {

                ArrayCoreMap sentence = (ArrayCoreMap) sentences.get(0);                
                Tree tree = sentence.get(SentimentAnnotatedTree.class);  
                sentiment = RNNCoreAnnotations.getPredictedClass(tree);             
                SentiReturn = SentiClass[sentiment];
            }
        }
        return SentiReturn;
    }

}

Answer 3

Textblob is a great package for sentimental analysis written in Python. You can have the docs here . Sentimental analysis of any given sentence is carried out by inspecting words and their corresponding emotional score (sentiment). You can start with

$ pip install -U textblob
$ python -m textblob.download_corpora

First pip install command will give you latest version of textblob installed in your (virtualenv) system since you pass -U will upgrade the pip package its latest available version . And the next will download all the data required, thecorpus .

Answer 4

Use py-corenlp

Install Stanford CoreNLP

The latest version at this time (2018-10-23) is 3.9.2:

wget http://nlp.stanford.edu/software/stanford-corenlp-full-2018-10-05.zip
unzip stanford-corenlp-full-2018-10-05.zip

If you do not have wget, you probably have curl:

curl -O http://nlp.stanford.edu/software/stanford-corenlp-full-2018-10-05.zip

If all else fails, use the browser ;-)

Start the server

cd stanford-corenlp-full-2018-10-05
java -mx5g -cp "*" edu.stanford.nlp.pipeline.StanfordCoreNLPServer -timeout 10000

Notes:

1. timeout is in milliseconds, I set it to 10 sec above. You should increase it if you pass huge blobs to the server.
2. There are more options, you can list them with --help.
3. -mx5g should allocate enough memory, but YMMV and you may need to modify the option if your box is underpowered.

Install the python package

pip install pycorenlp

(See also the official list).

Use it

from pycorenlp import StanfordCoreNLP

nlp = StanfordCoreNLP('http://localhost:9000')
res = nlp.annotate("I love you. I hate him. You are nice. He is dumb",
                   properties={
                       'annotators': 'sentiment',
                       'outputFormat': 'json',
                       'timeout': 1000,
                   })
for s in res["sentences"]:
    print("%d: '%s': %s %s" % (
        s["index"],
        " ".join([t["word"] for t in s["tokens"]]),
        s["sentimentValue"], s["sentiment"]))

and you will get:

0: 'I love you .': 3 Positive
1: 'I hate him .': 1 Negative
2: 'You are nice .': 3 Positive
3: 'He is dumb': 1 Negative

Notes

1. You pass the whole text to the server and it splits it into sentences. It also splits sentences into tokens.
2. The sentiment is ascribed to each sentence, not the whole text. The mean sentimentValue across sentences can be used to estimate the sentiment of the whole text.
3. The average sentiment of a sentence is between Neutral (2) and Negative (1), the range is from VeryNegative (0) to VeryPositive (4) which appear to be quite rare.
4. You can stop the server either by typing Ctrl-C at the terminal you started it from or using the shell command kill $(lsof -ti tcp:9000). 9000 is the default port, you can change it using the -port option when starting the server.
5. Increase timeout (in milliseconds) in server or client if you get timeout errors.
6. sentiment is just one annotator, there are many more, and you can request several, separating them by comma: 'annotators': 'sentiment,lemma'.
7. Beware that the sentiment model is somewhat idiosyncratic (e.g., the result is different depending on whether you mention David or Bill).

PS. I cannot believe that I added a 9th answer, but, I guess, I had to, since none of the existing answers helped me (some of the 8 previous answers have now been deleted, some others have been converted to comments).

Answer 5

I would suggest using the TextBlob library. A sample implementation goes like this:

from textblob import TextBlob
def sentiment(message):
    # create TextBlob object of passed tweet text
    analysis = TextBlob(message)
    # set sentiment
    return (analysis.sentiment.polarity)

Answer 6

I am facing the same problem : maybe a solution with stanford_corenlp_py that uses Py4j as pointed out by @roopalgarg.

stanford_corenlp_py

This repo provides a Python interface for calling the "sentiment" and "entitymentions" annotators of Stanford's CoreNLP Java package, current as of v. 3.5.1. It uses py4j to interact with the JVM; as such, in order to run a script like scripts/runGateway.py, you must first compile and run the Java classes creating the JVM gateway.