Measuring Group Cohesion in Document Collections

Exploring document collections remains a focus of research. This task can be tackled using various techniques, typically ranking documents according to a relevance index or grouping documents based on various clustering algorithms. The task complexity produces results of varying quality that inevitably carry noise. Users must be careful when interpreting document relevance or groupings. We address this problem by computing cohesion measures for a group of documents confirming/infirming whether it can be trusted to form a semantically cohesive unit. The index is inspired from past work in social network analysis (SNA) and illustrates how document exploration can benefit from SNA techniques.