How to get a general mood for several offers

How do you find the aggregated sense of several sentences / paragraph / large passage of text.

I have the following code below, which I based on the github Stanford CoreNLP tests and various examples, but everything I found completed the sentiment analysis, only calculates the mood for individual sentences. But I want the overall mood of the tweet to be independent of the number of sentences.

The only way I can do this is to create a separate thread for SentimentPipeline.main(String[])and load the text in stdinand collect a common opinion in sdout. I would rather just use my code to make it simpler / more efficient, but I did not find anything.

In addition, I don’t want to make a system call at the bank, as most people do, since I will make millions of tweets per day. The overhead will be too large, loading resources every time.

Annotation document = new Annotation(text);
pipeline.annotate(document);

List<CoreMap> sentences = document.get(SentencesAnnotation.class);
        String output;
        for (CoreMap sentence : sentences) {
            // traversing the words in the current sentence a CoreLabel is a CoreMap with additional token-specific methods
             output = "";
            for (CoreLabel token : sentence.get(TokensAnnotation.class)) {

                // this is the text of the token
                String word = token.get(TextAnnotation.class);

                // this is the Parts Of Speech tag of the token (noun, verb, adjective etc)
                // String pos = token.get(PartOfSpeechAnnotation.class);

                // this is the NER label of the token
                String ne = token.get(NamedEntityTagAnnotation.class);
                if (!ne.contentEquals("O")) {
                    output = output + (ne + " " + word + " ");
                }
            }

            //**************Sentiment Analysis 
            Tree tree = sentence.get(SentimentCoreAnnotations.AnnotatedTree.class);
             String sentiment = RNNCoreAnnotations.getPredictedClass(tree);