Forming a hypothesis set from sentences across documents representative of different stances taken across the documents

A computer program product for extracting hypotheses from documents for a stance measurement, the computer program product comprising a computer readable storage medium having computer readable program code embodied therein that is executable to perform operations, the operations comprising:

• for N documents d1 . . . dN, perform for document di:
• for sentence sj of a plurality of sentences in di, determine a stance score between sentence sj and a sentence sk of a plurality of sentences in di+1, for i=1 to N, that satisfies a stance score criteria;
• forming a graph of nodes representing the plurality of sentences in the documents di and di+1 with edges between pairs of sentences having stance scores exceeding the stance score criteria;
• forming cluster groups comprised of the nodes interconnected by the edges in the graph;
• forming at least one similarity group of sentences in the clusters that are similar;
• and
• forming a hypothesis set of sentences in similarity groups to form a set of hypothesis across the documents that are dissimilar in that the sentences are from different similarity groups and indicate a threshold likelihood of agreement or disagreement with another sentence in the cluster.

A system for extracting hypotheses from documents for a stance measurement, comprising:

• a processor;
• and
• a computer readable storage medium having computer readable program code embodied therein that is executable to perform operations, the operations comprising:
• clustering sentences from the documents into a plurality of clusters, wherein the sentences in a cluster of the clusters have stance scores with respect to other sentences in the cluster that satisfy a stance criteria;
• forming at least one similarity group of sentences in the clusters having similarity scores satisfying a similarity criteria;
• selecting sentences from similarity groups in the clusters based on stance scores of the sentences in a similarity group;
• forming a hypothesis set of the selected sentences in the similarity groups;
• and
• determining the stance scores of sentences in the documents with the sentences in the hypothesis set to determine stances of the documents with respect to the sentences in the hypothesis set.

A system for extracting hypotheses from documents for a stance measurement, comprising:

• a processor;
• and
• a computer readable storage medium having computer readable program code embodied therein that is executable to perform operations, the operations comprising:
• for N documents di . . . dN, perform for document di:
• for sentence sj of a plurality of sentences in di, determine a stance score between sentence sj and a sentence sk of a plurality of sentences in di+1, for i=1 to N, that satisfies a stance score criteria;
• forming a graph of nodes representing the plurality of sentences in the documents di and di+1 with edges between pairs of sentences having stance scores exceeding the stance score criteria;
• forming cluster groups comprised of the nodes interconnected by the edges in the graph;
• forming at least one similarity group of sentences in the clusters that are similar;
• and
• forming a hypothesis set of sentences in similarity groups to form a set of hypothesis across the documents that are dissimilar in that the sentences are from different similarity groups and indicate a threshold likelihood of agreement or disagreement with another sentence in the cluster.

A method for extracting hypotheses from documents for a stance measurement, comprising:

• clustering sentences from the documents into a plurality of clusters, wherein the sentences in a cluster of the clusters have stance scores with respect to other sentences in the cluster that satisfy a stance criteria;
• forming at least one similarity group of sentences in the clusters having similarity scores satisfying a similarity criteria;
• selecting sentences from similarity groups in the clusters based on stance scores of the sentences in a similarity group;
• forming a hypothesis set of the selected sentences in the similarity groups;
• and
• determining the stance scores of sentences in the documents with the sentences in the hypothesis set to determine stances of the documents with respect to the sentences in the hypothesis set.