I'm doing some sentiment analysis using SentiWordNet and I referred to the post here How to use SentiWordNet . However, I'm getting a score of 0.0 despite trying out various inputs. Is there anything I'm doing wrong here? Thanks!
import java.io.BufferedReader;
import java.io.File;
import java.io.FileReader;
import java.util.HashMap;
import java.util.Iterator;
import java.util.Set;
import java.util.Vector;
public class SWN3 {
private String pathToSWN = "C:\\Users\\Malcolm\\Desktop\\SentiWordNet_3.0.0\\home\\swn\\www\\admin\\dump\\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 = (String) 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 > 0.25 && 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) {
SWN3 test = new SWN3();
String sentence="Hello have a Super awesome great day";
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);
}
System.out.println(totalScore);
}
}
Here's the first 10 lines of SentiWordNet.txt
a 00001740 0.125 0 able#1 (usually followed by `to') having the necessary means or skill or know-how or authority to do something; "able to swim"; "she was able to program her computer"; "we were at last able to buy a car"; "able to get a grant for the project"
a 00002098 0 0.75 unable#1 (usually followed by `to') not having the necessary means or skill or know-how; "unable to get to town without a car"; "unable to obtain funds"
a 00002312 0 0 dorsal#2 abaxial#1 facing away from the axis of an organ or organism; "the abaxial surface of a leaf is the underside or side facing away from the stem"
a 00002527 0 0 ventral#2 adaxial#1 nearest to or facing toward the axis of an organ or organism; "the upper side of a leaf is known as the adaxial surface"
a 00002730 0 0 acroscopic#1 facing or on the side toward the apex
a 00002843 0 0 basiscopic#1 facing or on the side toward the base
a 00002956 0 0 abducting#1 abducent#1 especially of muscles; drawing away from the midline of the body or from an adjacent part
a 00003131 0 0 adductive#1 adducting#1 adducent#1 especially of muscles; bringing together or drawing toward the midline of the body or toward an adjacent part
a 00003356 0 0 nascent#1 being born or beginning; "the nascent chicks"; "a nascent insurgency"
a 00003553 0 0 emerging#2 emergent#2 coming into existence; "an emergent republic"
Usually the SentiWord.txt file comes with a weird format.
You need to remove the first part of it (which includes comments and instructions) and the last two lines:
#
EMPTY LINE
The parser doesn't know how to handle these situations, if you delete these extra two lines you'll be fine.
来源：https://stackoverflow.com/questions/15847025/getting-incorrect-score-using-sentiwordnet