Entrepôts, Représentation et Ingénierie des Connaissances
Publications of the ERIC lab

Search

by Year
by Author
by Topic
by Type
--------------------
- Temporal Multinomial Mixture for Instance-oriented Evolutionary Clustering hal link

Author(s): Kim Y.-M., Velcin J., Bonnevay S., Rizoiu M.-A.

Conference: 37th European Conference on Information Retrieval (Vienna, AT, 2015-03-29)
Proceedings: , vol. p. ()


Ref HAL: hal-01134393_v1
Abstract:

Evolutionary clustering aims at capturing the temporal evolution of clusters. This issue is particularly important in the context of social media data that are naturally temporally driven. In this paper, we propose a new probabilistic model-based evolutionary clustering technique. The Temporal Multinomial Mixture (TMM) is an extension of classical mixture model that optimizes feature co-occurrences in the trade-off with temporal smoothness. Our model is evaluated for two recent case studies on opinion aggregation over time. We compare four different probabilistic clustering models and we show the superiority of our proposal in the task of instance-oriented clustering.