我需要对一些包含电影评论的 csv 文件进行情感分析。我正在使用 SentiWordNet 进行情感分析。我面临的主要问题是 main() 函数。在这里我可以找到单个句子的极性。(String sentence="我爱你但讨厌当前的政治气候。”）但我想使用一个完整的 csv 文件并找到每个评论的极性。sentiwordnet 的路径是“C:\Users\INTEL\Desktop\Sentiment Final\FINALSENTIMENT.txt”
package swn3;
import java.io.BufferedReader;
import java.io.File;
import java.io.FileInputStream;
import java.io.FileReader;
import java.io.InputStreamReader;
import java.util.Arrays;
import java.util.HashMap;
import java.util.Iterator;
import java.util.Scanner;
import java.util.Set;
import java.util.Vector;
public class SWN3 {
private String pathToSWN = "C:\\Users\\INTEL\\Desktop\\Sentiment FInal\\FINALSENTIMENT.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]);// Calculate synset score as score = PosS - NegS
String[] words = data[4].split(" ");// Get all Synset terms
for(String w:words)//Go through all terms of current synset.
{ // Get synterm and synterm rank
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 = (String) iterator.next();
Vector<Double> v = _temp.get(word);
// Calculate weighted average. Weigh the synsets according to their rank.
// Score= 1/2*first + 1/3*second + 1/4*third ..... etc.
// Sum = 1/1 + 1/2 + 1/3 ...
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 > 0.25 && score<=0.5)
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<=-0.75)
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 void main(String[] args) throws Exception {
SWN3 test = new SWN3();
String sentence="I love you but hate the current political climate.";
String[] words = sentence.split("\\s+"); //splits the sentence and put it into an array.
double totalScore = 0;
int review=0;
for(String word : words) {
word = word.replaceAll("([^a-zA-Z\\s])", "");//^ means not and a-zA-Z means all upper and lower case characters.overall means all but not letters
if (test.extract(word) == null)
continue;
totalScore += test.extract(word);
}
if(totalScore>=0.75)
review= 5;
else
if(totalScore> 0.25 && totalScore<=0.5)
review = 4;
else
if(totalScore > 0 && totalScore<=0.25)
review = 3;
else
if(totalScore< 0 && totalScore>=-0.25)
review= 2;
else
if(totalScore< -0.25 && totalScore>=-0.5)
review= 1;
else
if(totalScore<=-0.75)
review= 0;
System.out.println(review);
System.out.println(totalScore);
}
}