Here is my SentiWorNet Algo:
public class SWN3 {
private String pathToSWN = "C:/Users/RAHUL/Desktop/SWN/SentiWordNet_3.0.0.txt";
private HashMap<String, Double>_dict;
public SWN3(){
_dict = new HashMap<String, Double>();
HashMap<String, Vector<Double>> _temp = new HashMap<String, Vector<Double>>();
try{
BufferedReader csv = new BufferedReader(new FileReader(pathToSWN));
String line = "";
while((line = csv.readLine()) != null)
{
String[] data = line.split("\t");
Double score = Double.parseDouble(data[2])-Double.parseDouble(data[3]);
String[] words = data[4].split(" ");
for(String w:words)
{
String[] w_n = w.split("#");
w_n[0] += "#"+data[0];
int index = Integer.parseInt(w_n[1])-1;
if(_temp.containsKey(w_n[0]))
{
Vector<Double> v = _temp.get(w_n[0]);
if(index>v.size())
for(int i = v.size();i<index; i++)
v.add(0.0);
v.add(index, score);
_temp.put(w_n[0], v);
}
else
{
Vector<Double> v = new Vector<Double>();
for(int i = 0;i<index; i++)
v.add(0.0);
v.add(index, score);
_temp.put(w_n[0], v);
}
}
}
Set<String> temp = _temp.keySet();
for (Iterator<String> iterator = temp.iterator(); iterator.hasNext();) {
String word = iterator.next();
Vector<Double> v = _temp.get(word);
double score = 0.0;
double sum = 0.0;
for(int i = 0; i < v.size(); i++)
score += ((double)1/(double)(i+1))*v.get(i);
for(int i = 1; i<=v.size(); i++)
sum += (double)1/(double)i;
score /= sum;
String sent = "";
if(score>=0.75)
sent = "strong_positive";
else
if(score > 0.50 && score<0.75)
sent = "moderately_positive";
else
if(score > 0.25 && score>=0.50)
sent = "positive";
else
if(score > 0 && score>=0.25)
sent = "weak_positive";
else
if(score < 0 && score>=-0.25)
sent = "weak_negative";
else
if(score < -0.25 && score>=-0.5)
sent = "negative";
else
if(score < -0.50 && score>-0.75)
sent = "moderately_negative";
else
if(score<=-0.75)
sent = "strong_negative";
_dict.put(word, score);
}
}
catch(Exception e){e.printStackTrace();}
}
public Double extract(String word)
{
Double total = new Double(0);
if(_dict.get(word+"#n") != null)
total = _dict.get(word+"#n") + total;
if(_dict.get(word+"#a") != null)
total = _dict.get(word+"#a") + total;
if(_dict.get(word+"#r") != null)
total = _dict.get(word+"#r") + total;
if(_dict.get(word+"#v") != null)
total = _dict.get(word+"#v") + total;
return total;
}
public static String SentiWord(String stri) {
SWN3 test = new SWN3();
String sentence=stri;
String[] words = sentence.split("\\s+");
double totalScore = 0;
for(String word : words) {
word = word.replaceAll("([^a-zA-Z\\s])", "");
if (test.extract(word) == null)
continue;
totalScore += test.extract(word);
}
String sent = "";
if(totalScore>=0.75)
sent = "strong_positive";
else
if(totalScore > 0.25 && totalScore<0.75)
sent = "positive";
....
....
return sent;
}
}
这是我的 Pos Tagger 方法:
public class TagText {
public static void main(String[] args) throws IOException,
ClassNotFoundException {
// Initialize the tagger
MaxentTagger tagger = new MaxentTagger("taggers/english-left3words-distsim.tagger");
// The sample string
String sample = "This is a sample text";
// The tagged string
String tagged = tagger.tagString(sample);
//output the tagged sample string onto your console
System.out.println("Input: " + sample);
System.out.println("Output: "+ tagged);
}
}
我需要 POS Tagger 与 SentiwordNet 集成。我正在尝试制作一个用于情感分析的系统。现在这个 SentiwordNet 代码在没有 pos 标记的情况下工作正常,但没有给出好的结果。我就是想不通。请帮忙。