/**
* Calculate the similarity between a sentence Vj and all the sentences Vk where Vj has an
* outgoing edge to Vk.
*
* @param sentence_j Current sentence node Vj.
* @param language Language the text to be compared
* @return sum of all the similarity calculations between sentence Vj and all other sentences Vk,
* Vj has outgoing edges to.
*/
private double getSumWjk(Node sentence_j, Language language) {
double sumWjk = 0;
if (language.equals(Language.ICELANDIC)) {
for (Node sentence_k : sentence_j.edgesOUT) {
sumWjk += sentence_j.similarity(sentence_k);
}
} else if (language.equals(Language.ENGLISH)) {
for (Node sentence_k : sentence_j.edgesOUT) {
sumWjk += sentence_j.similarityEN(sentence_k);
}
}
return sumWjk;
}
/**
* Calculates the rank weighting scores for all the nodes in the graph. Iterative calculates over
* the graph until convergence at the standard error threshold or until max iterations.
*
* @param maxIterations Max number of iterations allowed for calculating rank scores
* @param language Language of the text to calculate rank weighting scores for Available
* languages: Icelandic and English
*/
public void weigthingScore(int maxIterations, Language language) {
LinkedList<Node> nodes = new LinkedList<Node>();
// Add nodes to LinkedList, we need them to stay in order
for (int i = 0; i < nodeList.length; i++) {
nodes.add(nodeList[i]);
}
/*
WS(Vi) = ( 1 - d) + d * Sum(VjIn) ________Wij________ * WS(Vj)
Sum(Vk outVj) Wjk
*/
for (int k = 0; k < maxIterations; k++) {
distStats.clear();
// Use dynamic programming to calculate the scores
double previousWSScore[] = new double[nodes.size()];
// Read in scores already calculated for nodes
for (Node s : nodeList) {
previousWSScore[nodes.indexOf(s)] = s.rank;
}
// For all nodes in the graph
for (Node sentence_i : nodes) {
double resultSumVji = 0;
// For all in-coming edges of Vi
for (Node sentence_j : sentence_i.edgesIN) {
// Do not compare a sentence to it self, we do not allow self voting here
if (!sentence_j.value.text.equalsIgnoreCase(sentence_i.value.text)) {
// Calculate the sum of all similarity measurements
// from all Vj nodes with outgoing edges to Vk nodes, see Wjk in equation
double sumWjk = getSumWjk(sentence_j, language);
if (sumWjk != 0) {
double Wji = 0.0;
if (language.equals(Language.ICELANDIC)) {
// Calculate Wij, similarity between two sentences
Wji = sentence_i.similarity(sentence_j);
} else if (language.equals(Language.ENGLISH)) {
// Calculate Wij, similarity between two sentences
Wji = sentence_i.similarityEN(sentence_j);
}
// Get the score for the previous node
double WSVj = previousWSScore[nodes.indexOf(sentence_j)];
// Sum all (j in Vj)
resultSumVji += ((Wji / sumWjk) * WSVj);
}
}
}
// Calculate weighting score WS(Vi)
double WSVi = (1.0 - TEXTRANK_DAMPING_FACTOR) + TEXTRANK_DAMPING_FACTOR * resultSumVji;
distStats.addValue(Math.abs(sentence_i.rank - WSVi));
sentence_i.rank = WSVi;
}
// Calculate the Standard Error of the Mean
final double standard_error =
distStats.getStandardDeviation() / Math.sqrt((double) distStats.getN());
// if std error of the mean is less than threshold
// the graph has converged and we break
if (standard_error < STANDARD_ERROR_THRESHOLD) {
break;
}
}
}