- Interpersonal interaction
- Intercultural communication
- Believable emotion and personality models
- Opinion mining/Lexical affect sensing
- Robotic applications of cognitive approaches
- Member of the program committee of 8th International Conference on Affective Computing and Intelligent Interaction (ACII2019);
- Reviewer of articles for the journal IEEE Transactions on Affective Computing;
- Member of the program committee of 7th International Conference on Affective Computing and Intelligent Interaction (ACII2017);
- Member of the program committee of 5th Workshop on Language Analysis for Social Media in conjunction with EACL 2014;
- Talk in the Usability Colloquium at Technical University of Berlin (22.04.2013), Humboldt University of Berlin (23.04.2013), Technical University of Vienna (17.06.2013);
- Member of the program committee of International Joint Conference on Natural Language Processing, (Nagoya, Oktober 2013);
- Member of the program committee for the 2013 Workshop on "Language Analysis in Social Media" on NAACL/HLT (Atlanta/Georgia, June 13);
- Member of the program committee of Workshop on Intelligent Approaches applied to Sentiment Mining and Emotion Analysis, 2012;
- Reviewer of articles for the journal Computational Intelligence;
- Member of the program committee of the workshop on the EACL workshop on Semantic Analysis in Social Networks, 2012;
- Member of the program committee of the workshop on Computational Approaches to Emotion Analysis and Generation in Text of NAACL 2010;
- Researcher in the European FP7 CALLAS project;
- PhD student in the HUMAINE project.
Alexander Osherenko. Implementing Social Smart Environments with a Large Number of Believable Inhabitants in the Context of Globalization. DOI: 10.1007/978-3-319-97550-4_13. 2019. In: Ferriera, Maria Isabel Aldinhas; Sequeira, Joao Silva; Ventura, Rodrigo: Cognitive architectures. Cham: Springer (Intelligent systems, control and automations: science and engineering, volume 94). ISBN: 978-3-319-97550-4. [link]
Abstract: This chapter discusses Social Smart Environments (SSEs) with a large number of believable Embodied Conversational Agents (ECAs) in the context of globalization. It focuses on SSE architecture, rapid prototyping and scalability with respect to size, geography, and administration. SSE is a software environment installed in a physical place representing, for example, a city inhabited by believable ECAs that interact comprehensibly with each other; believable ECAs are software agents that stand for humans from different cultures. To ensure believability, the ECAs maintain various determinants of processing, for instance, emotional, personal and cultural, identified through an analysis of 35 scenarios of intercultural interaction. This chapter shows implementation of these determinants and development of an SSE prototype on the basis of a specification defining interaction between ECAs. In conclusion, this contribution provides insight into future work addressing, for example, innovation in societies simulated by SSEs.
Alexander Osherenko. Opinion Mining and Lexical Affect Sensing. Computer-aided analysis of opinions and emotions in texts. Südwestdeutscher Verlag für Hochschulschriften. 2011. ISBN: 978-3838124889.
Review of the book by Marina Santini from RISE.
Alexander Osherenko. Social Interaction, Globalization and Computer-aided Analysis. A Practical Guide to Developing Social Simulation. London. 2014. ISBN: 978-1-4471-6259-9.[Author's cut]
- Social interaction: Overview This video presents an verview of social interaction, sciences studying it, its benefits, an example of how SocioFramework composes a population of ECAs simulating social interaction.
- Social interaction: Simulating scenarios For thorough exploration, an approach is necessary that sets up experiments on social interaction and creates experimental testbeds with particular interaction behavior. This video shows how own statistical framework, SocioFramework, composes such experimental testbeds.
- Social interaction: Dimensions of modeling Results of a pilot study of scenarios in social interaction. This video identifies dimensions of modeling that inuence social interaction, for example, an emotion model.
- Communities of emotional avatars (ECAs) This video shows how SocioFramework creates a community of emotional ECAs that can be used in many fields of study, for example, in experimentation with social systems and understanding interaction in human societies.
- Max - an emotional avatar (ECA) This video shows how SocioFramework creates an Embodied Conversational Agent (ECA) with a specific emotionality, a computer prototype, that relies on psychologically feasible model of affective behavior.
- SocioFramework - a statistical framework for experimentation and rapid prototyping SocioFramework implements means for processing statistical datasets including generating, evaluating, optimizing, fusing, as well as composing software prototypes based on the datasets.
- EmoText for opinion mining in long texts EmoText for opinion mining in long texts illustrates a domain-independent approach to opinion mining. Statistical EmoText formed a basis for SocioFramework. The approach was tested on the following English corpora: a Pang corpus with weblogs, Berardinelli movie review corpus with movie reviews, a corpus with spontaneous dialogues (the SAL corpus), and a corpus with product reviews.
- EmoText for affect sensing in short texts EmoText for affect sensing in short texts demonstrates an approach to semantic analysis. In contrast to the statistical approach, the semantic affect analyzer facilitates affect sensing in short texts using semantics and grammar of participating words.