In this paper we describe the SpRL-CWW entry into SemEval 2015: Task 8 SpaceEval. It detects spatial and motion relations as defined by the ISO-Space specifications in two phases: (1) it detects spatial elements and spatial/motion signals with a Conditional Random Field model that uses a combination of distributed word representations and lexicosyntactic features; (2) given relation candidate tuples, it simultaneously detects relation types and labels the spatial roles of participating elements by using a combination of syntactic and semantic features in independent multi-class classification models for each relation type. In evaluation on the shared task data, our system performed particularly well on detection of elements and relations in unannotated data.

This is the accepted version of the paper.This version of the publication may differ from the final published version. Permanent repository link ABSTRACTMotivation is a key factor for introducing and maintaining healthy changes in behaviour. However, typical visualization methods (e.g., bar-, pie-, and line charts) hardly motivate individuals. We investigate how a plant-a living visualization-whose health relies on the plant owner's level of activity, can engage people in tracking and self-reflecting on their fitness data. To address this question, we designed, implemented, and studied Go & Grow, a living plant that receives water proportionally to its owner's activity. Our six-week qualitative study with ten participants suggests that living visualizations have qualities that their digital counterparts do not have. This includes people feeling: emotionally connected to their plant; sentiments such as pride and guilt; and responsibility towards their plant. Based on this study, we introduce the Goal Motivation Model, a model considering the diversity of individuals, thus supporting and encouraging a diversity of strategies for accomplishing goals.

No abstract