Retrieval and display of data objects using a cross-group ranking metric

A computer implemented method to rank and display a plurality of linked documents, the method comprising:

• identifying a plurality of linked documents;
• representing the interconnectivity of the linked documents as a graph;
• clustering the linked documents in accordance with a selected vector-space technique to obtain one or more eigenvectors and an equal number of eigenvalues, each eigenvector identifying a cluster whose non-zero elements identify those linked documents that are members of that cluster, each eigenvalue associated with a single eigenvector,
• obtaining a weighting factor;
• determining a scat strength score for at least some of the plurality of linked documents in accordance with
• ∑
• i
• =
• 1
• n
• ⁢
• 
• λ
• i
• 
• w
• ×
• 
• e
• →
• i
• 
• ,
• where “i” represents a value that runs from 1 to “n” where “n” is the number of clusters, “λi” represents the ith eigenvalue, “{right arrow over (e)}i” represents the ith eigenvector, and “w” represents the weighting factor;
• and
• displaying a selected number of the linked documents in the order of their strength score.

A computer program storage device, readable by a programmable control device, comprising instructions stored on the program storage device for causing the programmable control device to rank a data object wherein the data object is a member of a plurality of groups in accordance with the following acts:

• obtaining a group-value for each of the plurality of groups in which the data object is a member, the group-value representing a first relationship between a respective group with respect to a reminder of the plurality of groups;
• obtaining an object-value associated with the data object for each group in which the data object is a member, the object-value representing a second relationship between the data object with respect to a remainder of the data objects within each group;
• obtaining a weighting factor value associated with the data object;
• combining the group-values and the object-values and the weighting factor in group-by-group fashion to assign a scalar strength score to the data object, wherein the act of combining the group-values, the object-values and the weighing factor comprising generating a scalar strength as
• ∑
• i
• =
• 1
• n
• ⁢
• 
• gi
• 
• w
• ×
• 
• oi
• 
• ,
• where “g” represents a group-value, “o” represents an object-value, “w” represents the weighting factor, and “i” represents a value that runs from 1 to “n” where “n” is the number of groups in which the data object is a member;
• and
• Processing the data object according to the strength score.