Afia Akhter Lipi

From observation to simulation: generating culture-specific behavior for interactive systems

In this article we present a parameterized model for generating multimodal behavior based on cultural heuristics. To this end, a multimodal corpus analysis of human interactions in two cultures serves as the empirical basis for the modeling endeavor. Integrating the results from this empirical study with a well-established theory of cultural dimensions, it becomes feasible to generate culture-specific multimodal behavior in embodied agents by giving evidence for the cultural background of the agent. Two sample applications are presented that make use of the model and are designed to be applied in the area of coaching intercultural communication.

Creating standardized video recordings of multimodal interactions across cultures

Trying to adapt the behavior of an interactive system to the cultural background of the user requires information on how relevant behaviors differ as a function of the users cultural background. To gain such insights in the interrelation of culture and behavior patterns, the information from the literature is often too anecdotal to serve as the basis for modeling a systems behavior, making it necessary to collect multimodal corpora in a standardized fashion in different cultures. In this chapter, the challenges of such an endeavor are introduced and solutions are presented by examples from a German-Japanese project that aims at modeling culture-specific behaviors for Embodied Conversational Agents.

Culture-related topic selection in small talk conversations across Germany and Japan

Small talk can be used in order to build a positive relationship towards a virtual character. However the choice of topics in a conversation can be dependent on social background. In this paper, we explore culture-related differences in small talk for the German and Japanese cultures. Based on findings from the literature and verified by a corpus analysis, we integrated prototypical German and Japanese small talk conversations into a multiagent system. In evaluation studies conducted in the two target cultures, we investigated whether participants prefer agent dialogs that were designed to reflect their own cultural background.

A Parameter-Based Model for Generating Culturally Adaptive Nonverbal Behaviors in Embodied Conversational Agents

The goal of this paper is to integrate culture as a computational term in embodied conversational agents by employing an empirical data-driven approach as well as a theoretical model-driven approach. We propose a parameter-based model that predicts nonverbal expressions appropriate for specific cultures. First, we introduce the Hofstede theory to describe socio-cultural characteristics of each country. Then, based on the previous studies in cultural differences of nonverbal behaviors, we propose expressive parameters to characterize nonverbal behaviors. Finally, by integrating socio-cultural characteristics and nonverbal expressive characteristics, we establish a Bayesian network model that predicts posture expressiveness from a country name, and vice versa.

A socio-cultural model based on empirical data of cultural and social relationships

The goal of this paper is to integrate culture and social relationship as a computational term in an embodied conversational agent system by employing empirical and theoretical approach. We propose a parameter-based model that predicts nonverbal expressions appropriate for specific cultures in different social relationship. So, first, we introduce the theories of social and cultural characteristics. Then, we did corpus analysis of human interaction of two cultures in two different social situations and extracted empirical data and finally, by integrating socio-cultural characteristics with empirical data, we establish a parameterized network model that generates culture specific nonverbal expressions in different social relationships.

Cultural difference in nonverbal behaviors in negotiation conversations: towards a model for culture-adapted conversational agents

As the basis of generating nonverbal expressions in animated agents, this paper proposes factors that account for cultural difference in nonverbal behaviors in negotiation interaction. First, we introduce theories of negotiation and cultural characteristics. Then, our analysis of human interaction in negotiation conversations in CUBE-G corpus is described. Finally, by integrating cultural and negotiation parameters with empirical data obtained in the corpus analysis, we design a parameterized network model that generates culture specific nonverbal expressions in negotiation conversations.

How culture and social relationship affect performing and perceiving of postures

With the goal of designing culturally appropriate conversational agents, this study (1) collects comparative German and Japanese corpus, namely CUBE-G corpus, (2) by analyzing the corpus, investigates how nonverbal behaviors are different depending on the culture and the social relationship, then, (3) conducts a perception study to examine whether people prefer agents behaviors which are consistent with their own culture and matched with a conversation context in a given social relationship. As the result, we found some aspects that characterize preferable postures, and results of perception study showed that, Japanese participants preferred behavioral aspects that are in-line with their own culture under a specified social relationship. This suggests that empirical study of comparative multicultural corpus is useful in determining appropriate nonverbal behaviors in culturally adaptive virtual agents.

Enculturating Conversational Agents Based on a Comparative Corpus Study

When encountering people who have a different cultural background from our own, many of us feel uncomfortable because gestures and facial expressions may not be familiar to us. Thus, to enhance the believability of conversational agents, culture-specific nonverbal behaviors should be implemented into the agents. In our previous study [1], with the goal of building a user interface that incorporates a users cultural background, we have collected comparative conversation corpus in Germany and Japan, and investigated the differences in gestures and posture shifts between these two countries. Based on [1], this paper reports a more detailed analysis about posture shifts, and proposes a chat system with an embodied conversational agent (ECA) that can act as a language trainer.