A mobile sensing framework for audience emotion analysis

---

Tezin Türü: Yüksek Lisans

Tezin Yürütüldüğü Kurum: Orta Doğu Teknik Üniversitesi, Enformatik Enstitüsü, Modelleme ve Simülasyon Anabilim Dalı, Türkiye

Tezin Onay Tarihi: 2014

Öğrenci: ELDJON KEPUCKA

Danışman: ALPTEKİN TEMİZEL

Özet:

The main objective of this thesis is to develop a multi-modal framework which facilitates simple data collection using mobile sensing on smartphones from an audience, for the duration of an experimental study. Current solutions primarily rely on custom mobile sensing platforms which are expensive to develop and complicated to apply. While there are a number of mobile sensing platforms developed for smartphones targeting different domains, such as transportation and air pollution they are not designed to be used for simultaneous and synchronized data collection. The mobile sensing framework introduced in this study is focused primarily on addressing efficiency and reliability issues considering the limited resources of smartphone devices. The applicability of the framework spans cross research domains such as: emotion analysis, activity sensing, human body monitoring, and user-computer interaction. Moreover, as demonstrated in our pilot study, the introduced framework can find practical usage in industries such as advertisement and content evaluation. The applied design solution was based on the classical server-client architecture paradigm and the concrete implementation of the framework expresses high performance efficiency and comprehensive reach affirmed by our performance tests. The pilot study organized during FIFA World Cup 2014, where an audience of people was invited to watch two football matches, demonstrated the validity of our framework for real-life studies. Preliminary analysis exposes the potential of the acquired sensor data in targeted domains.