com.lbarriosh.sentimentanalyzer.SentimentAnalyzer.java Source code

Introduction

Here is the source code for com.lbarriosh.sentimentanalyzer.SentimentAnalyzer.java

Source

/*******************************************************************************
 * Copyright (c) 2014 Luis Barrios Hernndez, Adrin Fernndez Hernndez
 * All rights reserved. This program and the accompanying materials
 * are made available under the terms of the Eclipse Public License v1.0
 * which accompanies this distribution, and is available at
 * http://www.eclipse.org/legal/epl-v10.html
 *
 * Contributors:
 *    Luis Barrios Hernndez, Adrin Fernndez Hernndez - initial API and implementation
 *******************************************************************************/
package com.lbarriosh.sentimentanalyzer;

import java.util.List;
import java.util.StringTokenizer;

import twitter4j.Status;

import com.lbarriosh.sentimentanalyzer.downloads.TweetsDownloader;
import com.lbarriosh.sentimentanalyzer.lexicons.LemmaValoration;
import com.lbarriosh.sentimentanalyzer.lexicons.Lexicon;
import com.lbarriosh.sentimentanalyzer.lexicons.LexiconFactory;
import com.lbarriosh.sentimentanalyzer.stopwords.StopWordsDetectorFactory;
import com.lbarriosh.sentimentanalyzer.stopwords.TwitterStopWordsDetector;
import com.lbarriosh.sentimentanalyzer.utils.DocumentClassifier;
import com.lbarriosh.sentimentanalyzer.utils.TwitterLocale;

public class SentimentAnalyzer {

    public static final String API_KEY = "***";
    public static final String API_SECRET = "***";
    public static final String ACCESS_TOKEN = "***";
    public static final String ACCESS_TOKEN_SECRET = "***";

    public DocumentClassifier<Status> generateStatistics(String[] query, int maxResults, TwitterLocale locale,
            double neutralEpsilon) {
        try {
            TweetsDownloader downloader = new TweetsDownloader(API_KEY, API_SECRET, ACCESS_TOKEN,
                    ACCESS_TOKEN_SECRET);
            List<Status> retrievedTweets = downloader.downloadTweets(query, locale, maxResults);
            TwitterStopWordsDetector sw_detector = StopWordsDetectorFactory.buildStopWordsDetector(locale);
            sw_detector.loadStopWordsFile();
            Lexicon lexicon = LexiconFactory.buildLexicon(locale);
            lexicon.loadData();
            DocumentClassifier<Status> docClassifier = new DocumentClassifier<Status>(neutralEpsilon);
            docClassifier.resetAllCounters();

            for (Status tweet : retrievedTweets) {
                StringTokenizer tok = new StringTokenizer(tweet.getText(), " ");
                docClassifier.resetWeightCounters();
                while (tok.hasMoreTokens()) {
                    String preProcessedWord = sw_detector.processToken(tok.nextToken());
                    if (preProcessedWord != null) {
                        LemmaValoration valoration = lexicon.getWordValoration(preProcessedWord);
                        docClassifier.processWordValoration(valoration);
                    } // if
                } // while
                docClassifier.classifyDocument(tweet);
            } // for
            return docClassifier;
        } catch (Exception e) {
            e.printStackTrace();
            return null;
        }
    }
}