At the time of joining the laboratory we could have witnessed a dynamic and unprecedented growth of textual resources available in the Internet.
Both at the university and at work we set ourselves remote and ambitious goals. Sometimes, at the first sight we might feel unsure about our capability to achieve them. During my time at the laboratory I learned how important it is to divide those long-standing goals on a set of smaller, manageable tasks. Tasks that can be clearly defined, thus one can monitor their progress and evaluate the achieved results. Further, this approach requires, and at the same time supports, a systematic and focused work. The opportunity to consult one’s endeavor with professors and to cooperate with fellow students greatly helps in reaching the goals.
At the time of joining the laboratory we could have witnessed a dynamic and unprecedented growth of textual resources available in the Internet. This remarkable surge created challenges related with the efficient accessing of sought after information by humans and in the development of interfaces that could ease this task for a wide range of users, regardless of their proficiency with computer systems.
On the other hand the growth of computer readable resources created also an opportunity to automatically acquire commonsense knowledge usable by the computer systems, crucial for the development of the next generation ‘intelligent’ machines and interfaces. At that time, the Language Media Laboratory could offer not only the best scientific and technological expertise to exhaustively address these two tasks but also an inspiring passion in their pursuit.
My work is related with the creation of virtual agents that provide personalized assistance to their users. These agents represent a growing class of cooperative agents that do not have a physical presence, but nevertheless are equipped with major ingredients of cognition including situated correlates of physical embodiment to become adaptive, cooperative and self improving in a virtual environment, given certain tasks. The design of the agents is partially inspired by embodied cognition originating from interaction-based robotics, transferred to a virtual context.
The focus of my current research is on emotions and the integration of affect sensing capabilities into conversational systems, so called ‘Affect Listeners’. These systems, are used as a tool for studying affective interactions and collective emotions in the Cyberspace.