The Development of Conversational Behavior

In 1950, Alan Turing proposed his concept of universal machines, emphasizing their abilities to learn, think, and behave in a human-like manner. Today, the existence of intelligent agents imitating human characteristics is more relevant than ever. They have expanded to numerous aspects of daily life. Yet, while they are often seen as work simplifiers, their interactions usually lack social competence. In particular, they miss what one may call authenticity. In the study presented in this paper, we explore how characteristics of social intelligence may enhance future agent implementations. Interviews and an open question survey with experts from different fields have led to a shared understanding of what it would take to make intelligent virtual agents, in particular messaging agents (i.e., chat bots), more authentic. Results suggest that showcasing a transparent purpose, learning from experience, anthropomorphizing, human-like conversational behavior, and coherence, are guiding characteristics for agent authenticity and should consequently allow for and support a better coexistence of artificial intelligence technology with its respective users.

Download Full-text

Impoliteness as a Model for Virtual Speech Community Building

Handbook of Research on Discourse Behavior and Digital Communication ◽

10.4018/978-1-61520-773-2.ch034 ◽

2010 ◽

pp. 523-539 ◽

Cited By ~ 1

Author(s):

Tracy R. LeBlanc

Keyword(s):

Community Building ◽

Relevant Literature ◽

Speech Community ◽

Virtual Communication ◽

Ongoing Research ◽

Face To Face ◽

Linguistic Strategies ◽

Starting Point ◽

Conversational Behavior ◽

Place And Identity

The aim of this chapter is to account for linguistic strategies of breaking into a virtual speech community, particularly the community the author refers to here as the Pen community. Virtual communication necessitates accommodations not otherwise engaged in face-to-face conversation, and the Pen community is both virtual and leet. Being leet necessitates interactional behavior consisting of techie knowledge, leet speak fluency, and a shared interest in the venture of building and maintaining a leet identity online. The goal for this ongoing research is to understand virtual conversational behavior and its role in leet speech community building. With a brief discussion of the literature on sociolinguistic perspectives as well as pragmatic theories pertaining to conversational behavior (Watts, Ide, & Ehlich 2005; Culpeper, 1996), exchanges from three threads of discourse from the Pen virtual speech community are accounted for. The notable features of discourse are the strategies employed by participants in order to create, build, foster a sense of place and identity, and strengthen said communities. The Pen community’s discourse permits examples of strategies undertaken for this collective effort through attempting to enter into the community and become a member, topic shifting behavior, and flaming. The author operationalizes each of these examples via Culpeper’s Impoliteness model. Included here are a brief review of relevant literature, a discourse analytical approach to the interactional behavior found in The Pen community, and conclusions about how a leet speech community is built virtually. The Impoliteness model serves well here as a starting point for further research on virtual speech community building.

Download Full-text

Human conversational behavior

Human Nature ◽

10.1007/bf02912493 ◽

1997 ◽

Vol 8 (3) ◽

pp. 231-246 ◽

Cited By ~ 143

Author(s):

R. I. M. Dunbar ◽

Anna Marriott ◽

N. D. C. Duncan

Keyword(s):

Conversational Behavior

Download Full-text

Conversational Behavior Reflecting Interpersonal Attitudes in Small Group Interactions

Intelligent Virtual Agents - Lecture Notes in Computer Science ◽

10.1007/978-3-319-21996-7_41 ◽

2015 ◽

pp. 375-388 ◽

Cited By ~ 8

Author(s):

Brian Ravenet ◽

Angelo Cafaro ◽

Beatrice Biancardi ◽

Magalie Ochs ◽

Catherine Pelachaud

Keyword(s):

Small Group ◽

Group Interactions ◽

Conversational Behavior ◽

Small Group Interactions

Download Full-text

Combining heterogeneous inputs for the development of adaptive and multimodal interaction systems

ADCAIJ ADVANCES IN DISTRIBUTED COMPUTING AND ARTIFICIAL INTELLIGENCE JOURNAL ◽

10.14201/adcaij2014263753 ◽

2013 ◽

Vol 2 (3) ◽

pp. 37-53 ◽

Cited By ~ 2

Author(s):

David Griol ◽

Jesús García-Herrero ◽

José Manuel Molina

Keyword(s):

Language Processing ◽

Autonomous Agents ◽

Multimodal Interaction ◽

Multimodal Fusion ◽

Reference Architecture ◽

Conversational Agents ◽

Visual Sensor ◽

Conversational Behavior ◽

Speech Interaction ◽

Multi Agent

In this paper we present a novel framework for the integration of visual sensor networks and speech-based interfaces. Our proposal follows the standard reference architecture in fusion systems (JDL), and combines different techniques related to Artificial Intelligence, Natural Language Processing and User Modeling to provide an enhanced interaction with their users. Firstly, the framework integrates a Cooperative Surveillance Multi-Agent System (CS-MAS), which includes several types of autonomous agents working in a coalition to track and make inferences on the positions of the targets. Secondly, enhanced conversational agents facilitate human-computer interaction by means of speech interaction. Thirdly, a statistical methodology allows modeling the user conversational behavior, which is learned from an initial corpus and improved with the knowledge acquired from the successive interactions. A technique is proposed to facilitate the multimodal fusion of these information sources and consider the result for the decision of the next system action.

Download Full-text

Gender and Interruptions

Psychology of Women Quarterly ◽

10.1111/j.1471-6402.1992.tb00271.x ◽

1992 ◽

Vol 16 (4) ◽

pp. 497-512 ◽

Cited By ~ 25

Author(s):

Marianne LaFrance

Keyword(s):

Power Relations ◽

Gender Composition ◽

Same Sex ◽

Audio Recordings ◽

Conversational Behavior

Does gender affect reactions to violations of expected conversational behavior? This study examined ratings of interactants involved in interruptive exchanges. Audio recordings of two-person interactions that varied in gender composition but were identical in script features were rated by judges on several scales, including the degree to which participants were seen to be argumentative, rude, and assertive. Results showed that interrupter sex did not affect ratings even though interrupters were evaluated differently than those they interrupted. However, gender composition significantly affected two of three derived factors, disrespect and assertiveness, such that when a woman interrupted a man, the pair was rated significantly more disrespectful and assertive than either of the two same-sex pairs. Conversational interruptions that occur among mixed-sex pairs are often interpreted not merely as individual infractions but as an assault on the established power relations.

Download Full-text