DEvIANT: Discovering Significant Exceptional (Dis-)Agreement Within Groups

Abstract

We strive to find contexts (i.e., subgroups of entities) under which exceptional (dis-)agreement occurs among a group of individuals, in any type of data featuring individuals (e.g., parliamentarians, customers) performing observable actions (e.g., votes, ratings) on entities (e.g., legislative procedures, movies). To this end, we introduce the problem of discovering statistically significant exceptional contextual intra-group agreement patterns. To handle the sparsity inherent to voting and rating data, we use Krippendorff's Alpha measure for assessing the agreement among individuals. We devise a branch-and-bound algorithm, named DEvIANT, to discover such patterns. DEvIANT exploits both closure operators and tight optimistic estimates. We derive analytic approximations for the confidence intervals (CIs) associated with patterns for a computationally efficient significance assessment. We prove that these approximate CIs are nested along specialization of patterns. This allows to incorporate pruning properties in DEvIANT to quickly discard non-significant patterns. Empirical study on several datasets demonstrates the efficiency and the usefulness of DEvIANT.

Redescription Model Mining

“…A finding of Exceptional Model Mining for this setup can be: "While overall there is a positive correlation between the training time and the performance score ( Ω = 0.35), the subgroup of males that are older than 50 years exhibits a negative correlation ( = −0.1)". For Exceptional Model Mining, a wide range of different model classes have been studied in literature including correlation models [5], Bayesian Networks [9], Markov Chain models [19], agreement models [3] and regression models [6].…”

“…One dataset is on houses in the city of Melbourne, Australia, sold from Domain.com.au 2 . The second dataset is on housing data for the city of Beijing, China, sold via bj.lianjia.com 3 . We apply minimal preprocessing and removal of outliers.…”

“…For Exceptional Model Mining, a wide range of different model classes have been studied in literature including correlation models [5], Bayesian Networks [9], Markov Chain models [19], agreement models [3] and regression models [6].…”