Abstract. Sentiment analysis programs are now sometimes used to detect patterns of sentiment use over time in online communication and to help automated systems interact better with users. Nevertheless, it seems that no previous published study has assessed whether the position of individual texts within ongoing communication can be exploited to help detect their sentiments. This article assesses apparent sentiment anomalies in on-going communication -texts assigned significantly different sentiment strength to the average of previous texts -to see whether their classification can be improved. The results suggest that a damping procedure to reduce sudden large changes in sentiment can improve classification accuracy but that the optimal procedure will depend on the type of texts processed.

No abstract

This article describes a method for modeling the propagation of cracks on any 3D surface. This method allows almost any type of cracks on any type of triangulated 3D object. Our model's main advantage is that it proposes a semi-physical solution, making it both user controllable and easily extensible. We first introduce the general development of cracks. We then present our original model of spectrum stress, followed by a description of the mutual interaction between cracks and stresses. Then, we describe special rendering techniques including the multi-thickness anti-aliasing linkedsegment method and the crack mirror special effect. The final section presents intermediate graphical results that review the entire model as well as a set of different crack patterns using various types of material such as concrete, ceramic, mud, and glaze.

No abstract

No abstract