An Improvisational Approach to Acquire Social Interactions

To build agents that can engage users in more open-ended social contexts, research has increasingly been focused on data-driven approaches to reduce the requirement of extensive, hand-authored behavioral content creation. However, one fundamental challenge of data-driven approaches is acquiring the interaction data with sufficient variety that reflects the characteristics of open-ended social interactions. Previous work attempts to acquire social interaction data either from face-to-face interactions or human-agent interactions using a simulated environment. In this work, Active Analysis (AA), a theater rehearsal technique, was applied to collect diverse social strategies and interactions. In particular, this work integrated AA into a web-based crowdsourcing task that requires two crowd workers to conduct a bilateral multi-level multi-issue negotiation. Findings from a between-subject experiment with 200 crowd workers recruited from Amazon Mechanical Turk demonstrated that AA could facilitate the creativity of crowd workers and thus lead to social interaction data with greater variety. In addition, AA provides a means to control the diversity so that the coverage of the collected data is consistent with the goals of the application. The results presented in the paper lay a good foundation for future work on data-driven approaches to build socially interactive agents.

• Publication year

  2020

• Venue

  International Conference on Intelligent Virtual Agents

• Publication date

  2020-10-19

• Fields of study

  Computer Science

• Identifiers
  DOI 10.1145/3383652.3423903
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• BERT in Negotiations: Early Prediction of Buyer-Seller Negotiation Outcomes

  2020cited by this paper
• An Expert-Model & Machine Learning Hybrid Approach to Predicting Human-Agent Negotiation Outcomes

  2019cited by this paper
• Hierarchical Decision Making by Generating and Following Natural Language Instructions

  2019cited by this paper
• Exploring Improvisational Approaches to Social Knowledge Acquisition

  2019influential reference
• Learning Generative Models of Social Interactions with Humans-in-the-Loop

  2018cited by this paper
• Deal or No Deal? End-to-End Learning of Negotiation Dialogues

  2017influential reference
• Pinocchio : Answering Human-Agent Negotiation Questions through Realistic Agent Design

  2017influential reference
• Negative Feedback In Your Face: Examining the Effects of Proxemics and Gender on Learning

  2017cited by this paper
• Towards modeling agent negotiators by analyzing human negotiation behavior

  2017cited by this paper
• "Is It Just Me?": Evaluating Attribution of Negative Feedback as a Function of Virtual Instructor's Gender and Proxemics

  2017cited by this paper
• IAGO: Interactive Arbitration Guide Online

  2016cited by this paper
• Nanocrafter: Design and Evaluation of a DNA Nanotechnology Game

  2015cited by this paper
• Principles of Automated Negotiation

  2014cited by this paper
• NegoChat: a chat-based negotiation agent

  2014cited by this paper
• Generating Content for Scenario-Based Serious-Games Using CrowdSourcing

  2014cited by this paper
• Collective artificial intelligence: simulated role-playing from crowdsourced data

  2013cited by this paper
• Crowdsourcing Narrative Intelligence

  2012cited by this paper
• Cooks or cobblers?: crowd creativity through combination

  2011cited by this paper
• KissKissBan: a competitive human computation game for image annotation

  2010cited by this paper
• Can automated agents proficiently negotiate with humans?

  2010cited by this paper
• The impact of expectation of future negotiation interaction on bargaining processes and outcomes

  2010cited by this paper
• Getting More : How You Can Negotiate to Succeed in Work and Life

  2010cited by this paper
• Agent and Multi-Agent Systems: Technologies and Applications

  2009cited by this paper
• KissKissBan: a competitive human computation game for image annotation

  2009cited by this paper
• Facing the challenge of human-agent negotiations via effective general opponent modeling

  2009cited by this paper
• Multi-party, Multi-issue, Multi-strategy Negotiation for Multi-modal Virtual Agents

  2008cited by this paper
• Agent and Multi-Agent Systems: Technologies and Applications, Second KES International Symposium, KES-AMSTA 2008, Incheon, Korea, March 26-28, 2008. Proceedings

  2008cited by this paper
• Negotiating with bounded rational agents in environments with incomplete information using an automated agent

  2008cited by this paper
• An agent architecture for multi-attribute negotiation using incomplete preference information

  2007cited by this paper
• TagATune: A Game for Music and Sound Annotation

  2007cited by this paper
• Verbosity: a game for collecting common-sense facts

  2006cited by this paper
• An agenda-based framework for multi-issue negotiation

  2004cited by this paper
• Labeling images with a computer game

  2004cited by this paper
• The handbook of negotiation and culture

  2004cited by this paper
• Open Mind Common Sense: Knowledge Acquisition from the General Public

  2002cited by this paper
• Makebelieve: using commonsense knowledge to generate stories

  2002cited by this paper
• Modeling Negotiation Dialogs

  2000cited by this paper
• Stanislavsky in Focus: An Acting Master for the Twenty-First Century

  1998cited by this paper
• Cognition and Rationality in Negotiation

  1991cited by this paper
• Getting to Yes: Negotiating Agreement Without Giving in

  1981cited by this paper

• No citing papers are available for this paper.