While significant progress has been achieved for Opinion Mining in Arabic (OMA), very limited efforts have been put towards the task of Emotion mining in Arabic. In fact, businesses are interested in learning a fine-grained representation of how users are feeling towards their products or services. In this work, we describe the methods used by the team Emotion Mining in Arabic (EMA), as part of the SemEval-2018 Task 1 for Affect Mining for Arabic tweets. EMA participated in all 5 subtasks. For the five tasks, several preprocessing steps were evaluated and eventually the best system included diacritics removal, elongation adjustment, replacement of emojis by the corresponding Arabic word, character normalization and light stemming. Moreover, several features were evaluated along with different classification and regression techniques. For the 5 subtasks, word embeddings feature turned out to perform best along with Ensemble technique. EMA achieved the 1 st place in subtask 5, and 3 rd place in subtasks 1 and 3.

No abstract

No abstract

Mobile devices and sensors have limited battery lifespans, limiting their feasibility for context recognition applications. As a result, there is a need to provide mechanisms for energy-efficient operation of sensors in settings where multiple contexts are monitored simultaneously. Past methods for efficient sensing operation have been hierarchical by first selecting the sensors with the least energy consumption, and then devising individual sensing schedules that trade-off energy and delays. The main limitation of the hierarchical approach is that it does not consider the combined impact of sensor scheduling and sensor selection. We aimed at addressing this limitation by considering the problem holistically and devising an optimization formulation that can simultaneously select the group of sensors while also considering the impact of their triggering schedule. The optimization solution is framed as a Viterbi algorithm that includes mathematical representations for multi-sensor reward functions and modeling of user behavior. Experiment results showed an average improvement of 31% compared to a hierarchical approach.