We implemented different modes of social gaze behavior in our companion robot, F-2, to evaluate the impression of the gaze behaviors on humans in three symmetric communicative situations: (a) the robot telling a story, (b) the person telling a story to the robot, and (c) both parties communicating about objects in the real world while solving a Tangram puzzle. In all the situations the robot localized the human’s eyes and directed its gaze between the human, the environment, and the object of interest in the problem space (if it existed). We examined the balance between different gaze directions as the novel key element to maintaining a feeling of social connection with the robot in humans. We extended the computer model of the robot in order to simulate realistic gaze behavior in the robot and create the impression of the robot changing its internal cognitive states. Other novel results include the implicit, rather than explicit, character of the robot gaze perception for many of our subjects and the role of individual differences, especially the level of emotional intelligence, in terms of human sensitivity to the robotic gaze. Therefore, in this study, we used an iterative approach, extending the applied cognitive architecture in order to simulate the balance between different behavioral reactions and to test it in the experiments. In such a way, we came to a description of the key behavioral cues that suggest to a person that the particular robot can be perceived as an emotional and even conscious creature.
The research paper focuses on the mechanism of semantic parser for automatic text analysis and represents some results of analyzing news with a total volume of 2.2 million clauses. This mechanism models the processes of text comprehension and in this paper it is applied to the evaluation of the text influence on the reader. The parser constructs a semantic representation of the text and maps the meaning of each clause to a particular frame belonging either to the set of 300 emotional or to the set of 4500 rational frames. Comparing the frames of pro-state (federal) and blocked sources in Russia, the authors show that the most frequent frames in federal news represent an interactive dialog between the media and the speaker (note, add, recall, etc.), while the most frequent frames in blocked news introduce the speaker’s utterance that has become known to the news agencies (report, write, say, etc.). This reflects the remoteness of the editors of blocked news from Russian speakers. The federal media more often report about funny or unexpected purchases, as well as about how federal employees rescue people, and this agenda should make a positive impression. The blocked media, on the other hand, are more likely to mention court sentencing and death, which should have a negative impact. The natural-language inference constructed via frame combinations is shown to enable the recognition of emotional situations in derived meanings that are not explicitly expressed in the text and, thus, it allows to analyze automatically more compound mechanisms of manipulation.