Publications
Search
541.
Pynadath, David V.; Rosenbloom, Paul S.; Marsella, Stacy C.
Reinforcement Learning for Adaptive Theory of Mind in the Sigma Cognitive Architecture Proceedings Article
In: Proceedings of the 7th Annual Conference on Artificial General Intelligence, pp. 143 – 154, Springer International Publishing, Quebec City, Canada, 2014, ISBN: 978-3-319-09273-7.
@inproceedings{pynadath_reinforcement_2014,
title = {Reinforcement Learning for Adaptive Theory of Mind in the Sigma Cognitive Architecture},
author = {David V. Pynadath and Paul S. Rosenbloom and Stacy C. Marsella},
url = {http://ict.usc.edu/pubs/Reinforcement%20learning%20for%20adaptive%20Theory%20of%20Mind%20in%20the%20Sigma%20cognitive%20architecture.pdf},
doi = {10.1007/978-3-319-09274-4_14},
isbn = {978-3-319-09273-7},
year = {2014},
date = {2014-08-01},
booktitle = {Proceedings of the 7th Annual Conference on Artificial General Intelligence},
pages = {143 – 154},
publisher = {Springer International Publishing},
address = {Quebec City, Canada},
abstract = {One of the most common applications of human intelligence is social interaction, where people must make effective decisions despite uncertainty about the potential behavior of others around them. Reinforcement learning (RL) provides one method for agents to acquire knowledge about such interactions. We investigate different methods of multiagent reinforcement learning within the Sigma cognitive architecture. We leverage Sigma’s architectural mechanism for gradient descent to realize four different approaches to multiagent learning: (1) with no explicit model of the other agent, (2) with a model of the other agent as following an unknown stationary policy, (3) with prior knowledge of the other agent’s possible reward functions, and (4) through inverse reinforcement learn- ing (IRL) of the other agent’s reward function. While the first three variations re-create existing approaches from the literature, the fourth represents a novel combination of RL and IRL for social decision-making. We show how all four styles of adaptive Theory of Mind are realized through Sigma’s same gradient descent algorithm, and we illustrate their behavior within an abstract negotiation task.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
One of the most common applications of human intelligence is social interaction, where people must make effective decisions despite uncertainty about the potential behavior of others around them. Reinforcement learning (RL) provides one method for agents to acquire knowledge about such interactions. We investigate different methods of multiagent reinforcement learning within the Sigma cognitive architecture. We leverage Sigma’s architectural mechanism for gradient descent to realize four different approaches to multiagent learning: (1) with no explicit model of the other agent, (2) with a model of the other agent as following an unknown stationary policy, (3) with prior knowledge of the other agent’s possible reward functions, and (4) through inverse reinforcement learn- ing (IRL) of the other agent’s reward function. While the first three variations re-create existing approaches from the literature, the fourth represents a novel combination of RL and IRL for social decision-making. We show how all four styles of adaptive Theory of Mind are realized through Sigma’s same gradient descent algorithm, and we illustrate their behavior within an abstract negotiation task.
542.
Nagano, Koki; Alexander, Oleg; Barbic, Jernej; Debevec, Paul
Measurement and Modeling of Microfacet Distributions under Deformation Proceedings Article
In: Proceedings of SIGDIAL 2014, ACM, Vancouver, British Columbia, Canada, 2014, ISBN: 978-1-4503-2960-6.
@inproceedings{nagano_measurement_2014,
title = {Measurement and Modeling of Microfacet Distributions under Deformation},
author = {Koki Nagano and Oleg Alexander and Jernej Barbic and Paul Debevec},
url = {http://ict.usc.edu/pubs/Measurement%20and%20Modeling%20of%20Microfacet%20Distribution%20under%20Deformation%20(abstract%20for%20talk).pdf},
doi = {10.1145/2614106.2614124},
isbn = {978-1-4503-2960-6},
year = {2014},
date = {2014-08-01},
booktitle = {Proceedings of SIGDIAL 2014},
publisher = {ACM},
address = {Vancouver, British Columbia, Canada},
abstract = {We endeavor to model dynamic microfacet distributions of rough surfaces such as skin to simulate the changes in surface BRDF under stretching and compression. We begin by measuring microfacet distributions at 5-micron scale of several surface patches under controlled deformation. Generally speaking, rough surfaces become flatter and thus shinier as they are pulled tighter, and become rougher under compression. From this data, we build a model of how surface reflectance changes as the material deforms. We then simulate dynamic surface reflectance by modifying the anisotropic roughness parameters of a microfacet distribution model in accordance with animated surface deformations. Furthermore, we directly render such dynamic appearance by driving dynamic micro geometries to demonstrate how they influence the meso-scale surface reflectance.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
We endeavor to model dynamic microfacet distributions of rough surfaces such as skin to simulate the changes in surface BRDF under stretching and compression. We begin by measuring microfacet distributions at 5-micron scale of several surface patches under controlled deformation. Generally speaking, rough surfaces become flatter and thus shinier as they are pulled tighter, and become rougher under compression. From this data, we build a model of how surface reflectance changes as the material deforms. We then simulate dynamic surface reflectance by modifying the anisotropic roughness parameters of a microfacet distribution model in accordance with animated surface deformations. Furthermore, we directly render such dynamic appearance by driving dynamic micro geometries to demonstrate how they influence the meso-scale surface reflectance.
543.
Nouri, Elnaz; Traum, David
Generative Models of Cultural Decision Making for Virtual Agents Based on User’s Reported Values Proceedings Article
In: Intelligent Virtual Agents, pp. 310–315, Springer International Publishing, Boston, MA, 2014, ISBN: 978-3-319-09766-4.
@inproceedings{nouri_generative_2014,
title = {Generative Models of Cultural Decision Making for Virtual Agents Based on User’s Reported Values},
author = {Elnaz Nouri and David Traum},
url = {http://link.springer.com/chapter/10.1007/978-3-319-09767-1_39},
doi = {10.1007/978-3-319-09767-1_39},
isbn = {978-3-319-09766-4},
year = {2014},
date = {2014-08-01},
booktitle = {Intelligent Virtual Agents},
pages = {310–315},
publisher = {Springer International Publishing},
address = {Boston, MA},
series = {8637},
abstract = {Building computational models of cultural decision making for virtual agents based on behavioral data is a challenge because finding a reasonable mapping between the statistical data and the computational model is a difficult task. This paper shows how the weights on a multi attribute utility based decision making model can be set according to the values held by people elicited through a survey. If survey data from different cultures is available then this can be done to simulate cultural decision making behavior. We used the survey data of two sets of players from US and India playing the Dictator Game and the Ultimatum Game on-line. Analyzing their reported values in the survey enabled us to set up our model’s parameters based on their culture and simulate their behavior in the Ultimatum Game.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Building computational models of cultural decision making for virtual agents based on behavioral data is a challenge because finding a reasonable mapping between the statistical data and the computational model is a difficult task. This paper shows how the weights on a multi attribute utility based decision making model can be set according to the values held by people elicited through a survey. If survey data from different cultures is available then this can be done to simulate cultural decision making behavior. We used the survey data of two sets of players from US and India playing the Dictator Game and the Ultimatum Game on-line. Analyzing their reported values in the survey enabled us to set up our model’s parameters based on their culture and simulate their behavior in the Ultimatum Game.
544.
Melo, Celso M.; Carnevale, Peter; Gratch, Jonathan
USING VIRTUAL CONFEDERATES TO RESEARCH INTERGROUP BIAS AND CONFLICT Proceedings Article
In: Best Paper Proceedings of the Annual Meeting of the Academy of Management (AOM’14), Philadelphia, PA, 2014.
@inproceedings{de_melo_using_2014,
title = {USING VIRTUAL CONFEDERATES TO RESEARCH INTERGROUP BIAS AND CONFLICT},
author = {Celso M. Melo and Peter Carnevale and Jonathan Gratch},
url = {http://ict.usc.edu/pubs/Using%20Virtual%20Confederates%20to%20Research%20Intergroup%20Bias%20and%20Conflict.pdf},
year = {2014},
date = {2014-08-01},
booktitle = {Best Paper Proceedings of the Annual Meeting of the Academy of Management (AOM’14)},
address = {Philadelphia, PA},
abstract = {Virtual confederates–i.e., three-dimensional virtual characters that look and act like humans–have been gaining in popularity as a research method in the social and medical sciences. Interest in this research method stems from the potential for increased experimental control, ease of replication, facilitated access to broader samples and lower costs. We argue that virtual confederates are also a promising research tool for the study of intergroup behavior. To support this claim we replicate and extend with virtual confederates key findings in the literature. In Experiment 1 we demonstrate that people apply racial stereotypes to virtual confederates, and show a corresponding bias in terms of money offered in the dictator game. In Experiment 2 we show that people also show an in-group bias when group membership is artificially created and based on interdependence through shared payoffs in a nested social dilemma. Our results further demonstrate that social categorization and bias can occur not only when people believe confederates are controlled by humans (i.e., they are avatars), but also when confederates are believed to be controlled by computer algorithms (i.e., they are agents). The results, nevertheless, show a basic bias in favor of avatars (the in-group in the “human category”) to agents (the out-group). Finally, our results (Experiments 2 and 3) establish that people can combine, in additive fashion, the effects of these social categories; a mechanism that, accordingly, can be used to reduce intergroup bias. We discuss implications for research in social categorization, intergroup bias and conflict.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Virtual confederates–i.e., three-dimensional virtual characters that look and act like humans–have been gaining in popularity as a research method in the social and medical sciences. Interest in this research method stems from the potential for increased experimental control, ease of replication, facilitated access to broader samples and lower costs. We argue that virtual confederates are also a promising research tool for the study of intergroup behavior. To support this claim we replicate and extend with virtual confederates key findings in the literature. In Experiment 1 we demonstrate that people apply racial stereotypes to virtual confederates, and show a corresponding bias in terms of money offered in the dictator game. In Experiment 2 we show that people also show an in-group bias when group membership is artificially created and based on interdependence through shared payoffs in a nested social dilemma. Our results further demonstrate that social categorization and bias can occur not only when people believe confederates are controlled by humans (i.e., they are avatars), but also when confederates are believed to be controlled by computer algorithms (i.e., they are agents). The results, nevertheless, show a basic bias in favor of avatars (the in-group in the “human category”) to agents (the out-group). Finally, our results (Experiments 2 and 3) establish that people can combine, in additive fashion, the effects of these social categories; a mechanism that, accordingly, can be used to reduce intergroup bias. We discuss implications for research in social categorization, intergroup bias and conflict.
545.
DeVault, David; Stone, Matthew
Pursuing and Demonstrating Understanding in Dialogue Book Section
In: Natural Language Generation in Interactive Systems, pp. 34–62, Cambridge University Press, 2014.
@incollection{devault_pursuing_2014,
title = {Pursuing and Demonstrating Understanding in Dialogue},
author = {David DeVault and Matthew Stone},
url = {http://www.cs.rutgers.edu/ mdstone/pubs/dialogue11.pdf},
year = {2014},
date = {2014-07-01},
booktitle = {Natural Language Generation in Interactive Systems},
pages = {34–62},
publisher = {Cambridge University Press},
abstract = {The appeal of dialogue as an interface modality is its ability to support open-nded mixed-initiative interaction. Many systems o⬚er rich and extensive capabilities, but must support infrequent and untrained users. In such cases, it's unreasonable to expect users to know the actions they need in advance, or to be able to specify them using a regimented scheme of commands or menu options. Dialogue o⬚ers the potential for the user to talk through their needs with the system and arrive collaboratively at a feasible solution.},
keywords = {},
pubstate = {published},
tppubtype = {incollection}
}
The appeal of dialogue as an interface modality is its ability to support open-nded mixed-initiative interaction. Many systems o⬚er rich and extensive capabilities, but must support infrequent and untrained users. In such cases, it's unreasonable to expect users to know the actions they need in advance, or to be able to specify them using a regimented scheme of commands or menu options. Dialogue o⬚ers the potential for the user to talk through their needs with the system and arrive collaboratively at a feasible solution.
546.
Rosenbloom, Paul S.
Deconstructing Episodic Memory and Learning in Sigma Proceedings Article
In: Proceedings of the 36th Annual Conference of the Cognitive Science Society, Cognitive Science Society, Quebec City, Canada, 2014.
@inproceedings{rosenbloom_deconstructing_2014,
title = {Deconstructing Episodic Memory and Learning in Sigma},
author = {Paul S. Rosenbloom},
url = {http://ict.usc.edu/pubs/Deconstructing%20Reinforcement%20Learning%20in%20Sigma.pdf},
year = {2014},
date = {2014-07-01},
booktitle = {Proceedings of the 36th Annual Conference of the Cognitive Science Society},
publisher = {Cognitive Science Society},
address = {Quebec City, Canada},
abstract = {In an experiment in functional elegance, episodic memory and learning have been deconstructed in the Sigma cognitive architecture in terms of pre-existing memory and learning mechanisms plus a template-based structure generator. As a side effect, base-level activation also becomes deconstructed in terms of a learned temporal prior.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
In an experiment in functional elegance, episodic memory and learning have been deconstructed in the Sigma cognitive architecture in terms of pre-existing memory and learning mechanisms plus a template-based structure generator. As a side effect, base-level activation also becomes deconstructed in terms of a learned temporal prior.
547.
Rizzo, Albert; Hartholt, Arno; Grimani, Mario; Leeds, Andrew; Liewer, Matt
Virtual Reality Exposure Therapy for Combat-Related Posttraumatic Stress Disorder Journal Article
In: IEEE Computer Society, vol. 47, Issue 7, no. 7, pp. 31–37, 2014.
@article{rizzo_virtual_2014,
title = {Virtual Reality Exposure Therapy for Combat-Related Posttraumatic Stress Disorder},
author = {Albert Rizzo and Arno Hartholt and Mario Grimani and Andrew Leeds and Matt Liewer},
url = {http://ict.usc.edu/pubs/Virtual%20Reality%20Exposure%20Therapy%20for%20Treating%20Combat-Related%20PTSD.pdf},
year = {2014},
date = {2014-07-01},
journal = {IEEE Computer Society},
volume = {47, Issue 7},
number = {7},
pages = {31–37},
abstract = {Virtual reality (VR) technology is rapidly evolving to support prolonged exposure (PE) therapy, a proven treatment for combat-related posttraumatic stress disorder. Building on the successful 2007 Virtual Iraq/Afghanistan VRET system, a team of behavioral scientists, software engineers, and virtual artists has created Bravemind, a flexible VR system that offers significantly enhanced PE treatment possibilities. The first Web extra at http://youtu.be/EiYg-kMNMtQ is a video demonstration of an original early virtual reality exposure therapy (VRET) prototype that shows a small section of an Iraqi city with a landing helicopter (2004). The second Web extra at http://youtu.be/_cS-ynWZmeQ is a video demonstration of virtual reality exposure therapy (VRET) that simulates driving a Humvee in a rural part of Iraq, showcasing several encounters, including IED and road-side attacks (2007). The third Web extra at http://youtu.be/78QXX_F4mc8 is a video demonstration of virtual reality exposure therapy (VRET) that simulates an overview of several Iraqi city areas (2007). The fourth Web extra at http://youtu.be/_AnixslkVLU is a video demonstration of virtual reality exposure therapy (VRET) that simulates a patrol entering interior buildings in Iraq (2007). The fifth Web extra at http://youtu.be/S22aQ-DqKKU is a video demonstration of an original virtual reality exposure therapy (VRET) tablet interface that allows the clinician to change virtual reality settings and trigger encounters (2007). The sixth Web extra at http://youtu.be/C-fspuLo4vw is a video demonstration of the Bravemind virtual reality exposure therapy (VRET) prototype showing a variety of driving and dismounted scenarios with encounters in Iraq and Afghanistan (2013). The sixth Web extra at http://youtu.be/HSPDomDAigg is a video collection of Iraqi and Afghanistan virtual reality exposure therapy (VRET) scenarios within the Bravemind prototype (2013).},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Virtual reality (VR) technology is rapidly evolving to support prolonged exposure (PE) therapy, a proven treatment for combat-related posttraumatic stress disorder. Building on the successful 2007 Virtual Iraq/Afghanistan VRET system, a team of behavioral scientists, software engineers, and virtual artists has created Bravemind, a flexible VR system that offers significantly enhanced PE treatment possibilities. The first Web extra at http://youtu.be/EiYg-kMNMtQ is a video demonstration of an original early virtual reality exposure therapy (VRET) prototype that shows a small section of an Iraqi city with a landing helicopter (2004). The second Web extra at http://youtu.be/_cS-ynWZmeQ is a video demonstration of virtual reality exposure therapy (VRET) that simulates driving a Humvee in a rural part of Iraq, showcasing several encounters, including IED and road-side attacks (2007). The third Web extra at http://youtu.be/78QXX_F4mc8 is a video demonstration of virtual reality exposure therapy (VRET) that simulates an overview of several Iraqi city areas (2007). The fourth Web extra at http://youtu.be/_AnixslkVLU is a video demonstration of virtual reality exposure therapy (VRET) that simulates a patrol entering interior buildings in Iraq (2007). The fifth Web extra at http://youtu.be/S22aQ-DqKKU is a video demonstration of an original virtual reality exposure therapy (VRET) tablet interface that allows the clinician to change virtual reality settings and trigger encounters (2007). The sixth Web extra at http://youtu.be/C-fspuLo4vw is a video demonstration of the Bravemind virtual reality exposure therapy (VRET) prototype showing a variety of driving and dismounted scenarios with encounters in Iraq and Afghanistan (2013). The sixth Web extra at http://youtu.be/HSPDomDAigg is a video collection of Iraqi and Afghanistan virtual reality exposure therapy (VRET) scenarios within the Bravemind prototype (2013).
548.
Gandhe, Sudeep; Traum, David
SAWDUST: a Semi-Automated Wizard Dialogue Utterance Selection Tool for domain-independent large-domain dialogue Proceedings Article
In: SIGDIAL 2014 Conference, Association for Computational Linguistics, Philadelphia, PA, 2014.
@inproceedings{gandhe_sawdust_2014,
title = {SAWDUST: a Semi-Automated Wizard Dialogue Utterance Selection Tool for domain-independent large-domain dialogue},
author = {Sudeep Gandhe and David Traum},
url = {http://ict.usc.edu/pubs/SAWDUST%20-%20a%20Semi-Automated%20Wizard%20Dialogue%20Utterance%20Selection%20Tool%20for%20domain-independent%20large-domain%20dialogue.pdf},
year = {2014},
date = {2014-06-01},
booktitle = {SIGDIAL 2014 Conference},
publisher = {Association for Computational Linguistics},
address = {Philadelphia, PA},
abstract = {We present a tool that allows human wizards to select appropriate response utterances for a given dialogue context from a set of utterances observed in a dialogue corpus. Such a tool can be used in Wizard-of-Oz studies and for collecting data which can be used for training and/or evaluating automatic dialogue models. We also propose to incorporate such automatic dialogue models back into the tool as an aid in selecting utterances from a large dialogue corpus. The tool allows a user to rank candidate utterances for selection according to these automatic models.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
We present a tool that allows human wizards to select appropriate response utterances for a given dialogue context from a set of utterances observed in a dialogue corpus. Such a tool can be used in Wizard-of-Oz studies and for collecting data which can be used for training and/or evaluating automatic dialogue models. We also propose to incorporate such automatic dialogue models back into the tool as an aid in selecting utterances from a large dialogue corpus. The tool allows a user to rank candidate utterances for selection according to these automatic models.
549.
Nouri, Elnaz; Traum, David
Initiative Taking in Negotiation Proceedings Article
In: Proceedings of the 15th Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL), pp. 186–193, 2014.
@inproceedings{nouri_initiative_2014,
title = {Initiative Taking in Negotiation},
author = {Elnaz Nouri and David Traum},
url = {http://ict.usc.edu/pubs/Initiative%20Taking%20in%20Negotiation.pdf},
year = {2014},
date = {2014-06-01},
booktitle = {Proceedings of the 15th Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL)},
pages = {186–193},
abstract = {We examine the relationship between initiative behavior in negotiation dialogues and the goals and outcomes of the negotiation. We propose a novel annotation scheme for dialogue initiative, including four labels for initiative and response behavior in a dialogue turn. We annotate an existing human-human negotiation dataset, and use initiative-based features to try to predict both negotiation goal and outcome, comparing our results to prior work using other (non-initiative) features sets. Results show that combining initiative features with other features leads to improvements over either set and a majority class baseline.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
We examine the relationship between initiative behavior in negotiation dialogues and the goals and outcomes of the negotiation. We propose a novel annotation scheme for dialogue initiative, including four labels for initiative and response behavior in a dialogue turn. We annotate an existing human-human negotiation dataset, and use initiative-based features to try to predict both negotiation goal and outcome, comparing our results to prior work using other (non-initiative) features sets. Results show that combining initiative features with other features leads to improvements over either set and a majority class baseline.
550.
Morbini, Fabrizio; DeVault, David; Georgila, Kallirroi; Artstein, Ron; Traum, David; Morency, Louis-Philippe
A Demonstration of Dialogue Processing in SimSensei Kiosk Proceedings Article
In: 15th Annual Meeting of the Special Interest Group on Discourse and Dialogue, pp. 254, 2014.
@inproceedings{morbini_demonstration_2014,
title = {A Demonstration of Dialogue Processing in SimSensei Kiosk},
author = {Fabrizio Morbini and David DeVault and Kallirroi Georgila and Ron Artstein and David Traum and Louis-Philippe Morency},
url = {http://ict.usc.edu/pubs/A%20Demonstration%20of%20Dialogue%20Processing%20in%20SimSensei%20Kiosk.pdf},
year = {2014},
date = {2014-06-01},
booktitle = {15th Annual Meeting of the Special Interest Group on Discourse and Dialogue},
pages = {254},
abstract = {This demonstration highlights the dialogue processing in SimSensei Kiosk, a virtual human dialogue system that con- ducts interviews related to psychological distress conditions such as depression, anxiety, and post-traumatic stress disorder (PTSD). The dialogue processing in SimSensei Kiosk allows the system to con- duct coherent spoken interviews of human users that are 15-25 minutes in length, and in which users feel comfortable talking and openly sharing information. We present the design of the individual dialogue components, and show examples of natural conversation flow between the sys- tem and users, including expressions of empathy, follow-up responses and continuation prompts, and turn-taking.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
This demonstration highlights the dialogue processing in SimSensei Kiosk, a virtual human dialogue system that con- ducts interviews related to psychological distress conditions such as depression, anxiety, and post-traumatic stress disorder (PTSD). The dialogue processing in SimSensei Kiosk allows the system to con- duct coherent spoken interviews of human users that are 15-25 minutes in length, and in which users feel comfortable talking and openly sharing information. We present the design of the individual dialogue components, and show examples of natural conversation flow between the sys- tem and users, including expressions of empathy, follow-up responses and continuation prompts, and turn-taking.
551.
Gordon, Andrew; Core, Mark; Kang, Sin-Hwa; Wang, Catherine; Wienberg, Christopher
Civilian Analogs of Army Tasks: Supporting Pedagogical Storytelling Across Domains Journal Article
In: Proceedings of the 11th International Conference of the Learning Sciences, 2014.
@article{gordon_civilian_2014,
title = {Civilian Analogs of Army Tasks: Supporting Pedagogical Storytelling Across Domains},
author = {Andrew Gordon and Mark Core and Sin-Hwa Kang and Catherine Wang and Christopher Wienberg},
url = {http://ict.usc.edu/pubs/Civilian%20Analogs%20of%20Army%20Tasks%20-%20Supporting%20Pedagogical%20Storytelling%20Across%20Domains.pdf},
year = {2014},
date = {2014-06-01},
journal = {Proceedings of the 11th International Conference of the Learning Sciences},
abstract = {Storytelling is the most basic means by which people learn from the experiences of others. Advances in educational technologies offer new opportunities and experiences for learners, but risk losing the natural forms of pedagogical storytelling afforded by face-to-face teacher-student discussion. In this paper, we present a technology-supported solution to the problem of curating and algorithmically delivering relevant stories to learners in computer-based learning environments. Our approach is to mine public weblogs for textual narratives related to specific activity contexts, both inside and outside the domain of the target skillset. These stories are then linked directly to task representations in the learner model of an intelligent tutoring system, and delivered to learners along with other tutoring guidance. We demonstrate our approach to curating stories by creating collections of narratives that are analogous to tactical tasks of the U.S. Army, and evaluate the difficulty of incorporating these stories into intelligent tutoring systems.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Storytelling is the most basic means by which people learn from the experiences of others. Advances in educational technologies offer new opportunities and experiences for learners, but risk losing the natural forms of pedagogical storytelling afforded by face-to-face teacher-student discussion. In this paper, we present a technology-supported solution to the problem of curating and algorithmically delivering relevant stories to learners in computer-based learning environments. Our approach is to mine public weblogs for textual narratives related to specific activity contexts, both inside and outside the domain of the target skillset. These stories are then linked directly to task representations in the learner model of an intelligent tutoring system, and delivered to learners along with other tutoring guidance. We demonstrate our approach to curating stories by creating collections of narratives that are analogous to tactical tasks of the U.S. Army, and evaluate the difficulty of incorporating these stories into intelligent tutoring systems.
552.
Core, Mark; Lane, H. Chad; Traum, David
Intelligent Tutoring Support for Learners Interacting with Virtual Humans Book Section
In: Design Recommendations for Intelligent Tutoring Systems, vol. 2, pp. 249 – 257, 2014, ISBN: 978-0-9893923-2-7.
@incollection{core_intelligent_2014,
title = {Intelligent Tutoring Support for Learners Interacting with Virtual Humans},
author = {Mark Core and H. Chad Lane and David Traum},
url = {http://books.google.com/books?hl=en&lr=&id=BNWEBAAAQBAJ&oi=fnd&pg=PR2&dq=+Design+Recommendations+for+Intelligent+Tutoring+Systems,+volume+2&ots=jIk3zyGi4M&sig=qb_hc4KKE3-rMh2mrs8WkxBicG4#v=onepage&q&f=false},
isbn = {978-0-9893923-2-7},
year = {2014},
date = {2014-06-01},
booktitle = {Design Recommendations for Intelligent Tutoring Systems},
volume = {2},
pages = {249 – 257},
keywords = {},
pubstate = {published},
tppubtype = {incollection}
}
553.
Morbini, Fabrizio; Forbell, Eric; Sagae, Kenji
Improving Classification-Based Natural Language Understanding with Non-Expert Annotation Proceedings Article
In: Proceedings of SIGDIAL 2014, pp. 69–73, Philadelphia, PA, 2014.
@inproceedings{morbini_improving_2014,
title = {Improving Classification-Based Natural Language Understanding with Non-Expert Annotation},
author = {Fabrizio Morbini and Eric Forbell and Kenji Sagae},
url = {http://ict.usc.edu/pubs/Improved%20Classification-based%20Natural%20Language%20Understanding%20with%20Non-Expert%20Annotation.pdf},
year = {2014},
date = {2014-06-01},
booktitle = {Proceedings of SIGDIAL 2014},
pages = {69–73},
address = {Philadelphia, PA},
abstract = {Although data-driven techniques are commonly used for Natural Language Understanding in dialogue systems, their efficacy is often hampered by the lack of appropriate annotated training data in sufficient amounts. We present an approach for rapid and cost-effective annotation of training data for classification-based language understanding in conversational dialogue systems. Experiments using a webaccessible conversational character that interacts with a varied user population show that a dramatic improvement in natural language understanding and a substantial reduction in expert annotation effort can be achieved by leveraging non-expert annotation.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Although data-driven techniques are commonly used for Natural Language Understanding in dialogue systems, their efficacy is often hampered by the lack of appropriate annotated training data in sufficient amounts. We present an approach for rapid and cost-effective annotation of training data for classification-based language understanding in conversational dialogue systems. Experiments using a webaccessible conversational character that interacts with a varied user population show that a dramatic improvement in natural language understanding and a substantial reduction in expert annotation effort can be achieved by leveraging non-expert annotation.
554.
Stratou, Giota; Scherer, Stefan; Gratch, Jonathan; Morency, Louis-Philippe
Automatic nonverbal behavior indicators of depression and PTSD: the effect of gender Journal Article
In: Journal on Multimodal User Interfaces, vol. 9, no. 1, pp. 17 –29, 2014, ISSN: 1783-7677, 1783-8738.
@article{stratou_automatic_2014,
title = {Automatic nonverbal behavior indicators of depression and PTSD: the effect of gender},
author = {Giota Stratou and Stefan Scherer and Jonathan Gratch and Louis-Philippe Morency},
url = {http://ict.usc.edu/pubs/Automatic%20Nonverbal%20Behavior%20Indicators%20of%20Depression%20and%20PTSD%20-%20The%20Effect%20of%20Gender.pdf},
doi = {10.1007/s12193-014-0161-4},
issn = {1783-7677, 1783-8738},
year = {2014},
date = {2014-06-01},
journal = {Journal on Multimodal User Interfaces},
volume = {9},
number = {1},
pages = {17 –29},
abstract = {Recently there has been arising interest in automatically recognizing nonverbal behaviors that are linked with psychological conditions. Work in this direction has shown great potential for cases such as depression and post-traumatic stress disorder (PTSD), however most of the times gender differences have not been explored. In this paper, we show that gender plays an important role in the automatic assessment of psychological conditions such as depression and PTSD. We identify a directly interpretable and intuitive set of predictive indicators, selected from three general categories of nonverbal behaviors: affect, expression variability and motor variability. For the analysis, we employ a semi-structured virtual human interview dataset which includes 53 video recorded interactions. Our experiments on automatic classification of psychological conditions show that a gender-dependent approach significantly improves the performance over a gender agnostic one.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Recently there has been arising interest in automatically recognizing nonverbal behaviors that are linked with psychological conditions. Work in this direction has shown great potential for cases such as depression and post-traumatic stress disorder (PTSD), however most of the times gender differences have not been explored. In this paper, we show that gender plays an important role in the automatic assessment of psychological conditions such as depression and PTSD. We identify a directly interpretable and intuitive set of predictive indicators, selected from three general categories of nonverbal behaviors: affect, expression variability and motor variability. For the analysis, we employ a semi-structured virtual human interview dataset which includes 53 video recorded interactions. Our experiments on automatic classification of psychological conditions show that a gender-dependent approach significantly improves the performance over a gender agnostic one.
555.
Vigil, Jesse; Tait, Asa Shumskas; Wienberg, Christopher; Gordon, Andrew S.
Friends You Haven’t Met Yet: A Documentary Short Film Proceedings Article
In: Proceedings of the 2014 ACM conference on Web science, pp. 176–176, ACM Press, Bloomington, IN, 2014, ISBN: 978-1-4503-2622-3.
@inproceedings{vigil_friends_2014,
title = {Friends You Haven’t Met Yet: A Documentary Short Film},
author = {Jesse Vigil and Asa Shumskas Tait and Christopher Wienberg and Andrew S. Gordon},
url = {http://dl.acm.org/citation.cfm?doid=2615569.2617797},
doi = {10.1145/2615569.2617797},
isbn = {978-1-4503-2622-3},
year = {2014},
date = {2014-06-01},
booktitle = {Proceedings of the 2014 ACM conference on Web science},
pages = {176–176},
publisher = {ACM Press},
address = {Bloomington, IN},
abstract = {"Friends You Haven't Met Yet" is a documentary short film that chronicles encounters between extremely prolific bloggers and a computer scientist who uses their personal narratives for research. It explores issues related to public sharing of personal stories, the ethical obligations of researchers who use web data, and the changing nature of online privacy. The film was conceived by Andrew Gordon and Christopher Wienberg at the University of Southern California, whose research involves the collection of millions of personal stories posted to internet weblogs. In analyzing their data, these researchers discovered an unusual population of extremely prolific bloggers, people who post personal stories about their daily lives everyday over the course of many years. They posed three questions about this population: 1. What motivates these people to post so frequently and publicly about their personal life? 2. To what degree do these people embellish their stories to make them more interesting than reality? 3. What expectations do these authors have about their readers, and what are the ethical implications for researchers like us who analyze their posts? To answer these questions, PhD Student Christopher Wienberg contacted many of these bloggers directly and set up face-to-face interviews at their homes. Accompanied by a documentary film crew, Christopher traveled to locations around California, in both urban and rural settings, to better understand the people whose contributions on the web serve as data in social media research.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
"Friends You Haven't Met Yet" is a documentary short film that chronicles encounters between extremely prolific bloggers and a computer scientist who uses their personal narratives for research. It explores issues related to public sharing of personal stories, the ethical obligations of researchers who use web data, and the changing nature of online privacy. The film was conceived by Andrew Gordon and Christopher Wienberg at the University of Southern California, whose research involves the collection of millions of personal stories posted to internet weblogs. In analyzing their data, these researchers discovered an unusual population of extremely prolific bloggers, people who post personal stories about their daily lives everyday over the course of many years. They posed three questions about this population: 1. What motivates these people to post so frequently and publicly about their personal life? 2. To what degree do these people embellish their stories to make them more interesting than reality? 3. What expectations do these authors have about their readers, and what are the ethical implications for researchers like us who analyze their posts? To answer these questions, PhD Student Christopher Wienberg contacted many of these bloggers directly and set up face-to-face interviews at their homes. Accompanied by a documentary film crew, Christopher traveled to locations around California, in both urban and rural settings, to better understand the people whose contributions on the web serve as data in social media research.
556.
DeVault, David; Artstein, Ron; Benn, Grace; Dey, Teresa; Fast, Edward; Gainer, Alesia; Georgila, Kallirroi; Gratch, Jonathan; Hartholt, Arno; Lhommet, Margaux; Lucas, Gale; Marsella, Stacy C.; Fabrizio, Morbini; Nazarian, Angela; Scherer, Stefan; Stratou, Giota; Suri, Apar; Traum, David; Wood, Rachel; Xu, Yuyu; Rizzo, Albert; Morency, Louis-Philippe
SimSensei Kiosk: A Virtual Human Interviewer for Healthcare Decision Support Proceedings Article
In: Proceedings of the 13th Inter-national Conference on Autonomous Agents and Multiagent Systems (AAMAS 2014), pp. 1061–1068, International Foundation for Autonomous Agents and Multiagent Systems, Paris, France, 2014.
@inproceedings{devault_simsensei_2014,
title = {SimSensei Kiosk: A Virtual Human Interviewer for Healthcare Decision Support},
author = {David DeVault and Ron Artstein and Grace Benn and Teresa Dey and Edward Fast and Alesia Gainer and Kallirroi Georgila and Jonathan Gratch and Arno Hartholt and Margaux Lhommet and Gale Lucas and Stacy C. Marsella and Morbini Fabrizio and Angela Nazarian and Stefan Scherer and Giota Stratou and Apar Suri and David Traum and Rachel Wood and Yuyu Xu and Albert Rizzo and Louis-Philippe Morency},
url = {https://dl.acm.org/citation.cfm?id=2617415},
year = {2014},
date = {2014-05-01},
booktitle = {Proceedings of the 13th Inter-national Conference on Autonomous Agents and Multiagent Systems (AAMAS 2014)},
pages = {1061–1068},
publisher = {International Foundation for Autonomous Agents and Multiagent Systems},
address = {Paris, France},
abstract = {We present SimSensei Kiosk, an implemented virtual human interviewer designed to create an engaging face-to-face inter-action where the user feels comfortable talking and sharing information. SimSensei Kiosk is also designed to create in- teractional situations favorable to the automatic assessment of distress indicators, de_ned as verbal and nonverbal behav- iors correlated with depression, anxiety or post-traumatic stress disorder (PTSD). In this paper, we summarize the de- sign methodology, performed over the past two years, which is based on three main development cycles: (1) analysis of face-to-face human interactions to identify potential distress indicators, dialogue policies and virtual human gestures, (2) development and analysis of a Wizard-of-Oz prototype sys- tem where two human operators were deciding the spoken and gestural responses, and (3) development of a fully au- tomatic virtual interviewer able to engage users in 15-25 minute interactions. We show the potential of our fully auto- matic virtual human interviewer in a user study, and situate its performance in relation to the Wizard-of-Oz prototype.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
We present SimSensei Kiosk, an implemented virtual human interviewer designed to create an engaging face-to-face inter-action where the user feels comfortable talking and sharing information. SimSensei Kiosk is also designed to create in- teractional situations favorable to the automatic assessment of distress indicators, de_ned as verbal and nonverbal behav- iors correlated with depression, anxiety or post-traumatic stress disorder (PTSD). In this paper, we summarize the de- sign methodology, performed over the past two years, which is based on three main development cycles: (1) analysis of face-to-face human interactions to identify potential distress indicators, dialogue policies and virtual human gestures, (2) development and analysis of a Wizard-of-Oz prototype sys- tem where two human operators were deciding the spoken and gestural responses, and (3) development of a fully au- tomatic virtual interviewer able to engage users in 15-25 minute interactions. We show the potential of our fully auto- matic virtual human interviewer in a user study, and situate its performance in relation to the Wizard-of-Oz prototype.
557.
Gratch, Jonathan; Artstein, Ron; Lucas, Gale; Stratou, Giota; Scherer, Stefan; Nazarian, Angela; Wood, Rachel; Boberg, Jill; DeVault, David; Marsella, Stacy; Traum, David; Rizzo, Albert; Morency, Louis-Philippe
The Distress Analysis Interview Corpus of human and computer interviews Proceedings Article
In: Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC 2014), pp. 3123–3128, LREC, Reykjavik, Iceland, 2014.
@inproceedings{gratch_distress_2014,
title = {The Distress Analysis Interview Corpus of human and computer interviews},
author = {Jonathan Gratch and Ron Artstein and Gale Lucas and Giota Stratou and Stefan Scherer and Angela Nazarian and Rachel Wood and Jill Boberg and David DeVault and Stacy Marsella and David Traum and Albert Rizzo and Louis-Philippe Morency},
url = {http://ict.usc.edu/pubs/The%20Distress%20Analysis%20Interview%20Corpus%20of%20human%20and%20computer%20interviews.pdf},
year = {2014},
date = {2014-05-01},
booktitle = {Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC 2014)},
pages = {3123–3128},
publisher = {LREC},
address = {Reykjavik, Iceland},
abstract = {The Distress Analysis Interview Corpus (DAIC) contains clinical interviews designed to support the diagnosis of psychological distress conditions such as anxiety, depression, and post traumatic stress disorder. The interviews are conducted by humans, human controlled agents and autonomous agents, and the participants include both distressed and non-distressed individuals. Data collected include audio and video recordings and extensive questionnaire responses; parts of the corpus have been transcribed and annotated for a variety of verbal and non-verbal features. The corpus has been used to support the creation of an automated interviewer agent, and for research on the automatic identification of psychological distress.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
The Distress Analysis Interview Corpus (DAIC) contains clinical interviews designed to support the diagnosis of psychological distress conditions such as anxiety, depression, and post traumatic stress disorder. The interviews are conducted by humans, human controlled agents and autonomous agents, and the participants include both distressed and non-distressed individuals. Data collected include audio and video recordings and extensive questionnaire responses; parts of the corpus have been transcribed and annotated for a variety of verbal and non-verbal features. The corpus has been used to support the creation of an automated interviewer agent, and for research on the automatic identification of psychological distress.
558.
Shapiro, Ari; Feng, Andrew; Wang, Ruizhe; Li, Hao; Bolas, Mark; Medioni, Gerard; Suma, Evan
Rapid avatar capture and simulation using commodity depth sensors Journal Article
In: Computer Animation and Virtual Worlds, vol. 25, no. 3-4, pp. 201–211, 2014, ISSN: 15464261.
@article{shapiro_rapid_2014,
title = {Rapid avatar capture and simulation using commodity depth sensors},
author = {Ari Shapiro and Andrew Feng and Ruizhe Wang and Hao Li and Mark Bolas and Gerard Medioni and Evan Suma},
url = {http://ict.usc.edu/pubs/Rapid%20Avatar%20Capture%20and%20Simulation%20Using%20Commodity%20Depth%20Sensors.pdf},
doi = {10.1002/cav.1579},
issn = {15464261},
year = {2014},
date = {2014-05-01},
journal = {Computer Animation and Virtual Worlds},
volume = {25},
number = {3-4},
pages = {201–211},
abstract = {We demonstrate a method of acquiring a 3D model of a human using commodity scanning hardware and then controlling that 3D figure in a simulated environment in only a few minutes. The model acquisition requires four static poses taken at 90 degree angles relative to each other. The 3D model is then given a skeleton and smooth binding information necessary for control and simulation. The 3D models that are captured are suitable for use in applications where recognition and distinction among characters by shape, form, or clothing is important, such as small group or crowd simulations or other socially oriented applications. Because of the speed at which a human figure can be captured and the low hardware requirements, this method can be used to capture, track, and model human figures as their appearances change over time.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
We demonstrate a method of acquiring a 3D model of a human using commodity scanning hardware and then controlling that 3D figure in a simulated environment in only a few minutes. The model acquisition requires four static poses taken at 90 degree angles relative to each other. The 3D model is then given a skeleton and smooth binding information necessary for control and simulation. The 3D models that are captured are suitable for use in applications where recognition and distinction among characters by shape, form, or clothing is important, such as small group or crowd simulations or other socially oriented applications. Because of the speed at which a human figure can be captured and the low hardware requirements, this method can be used to capture, track, and model human figures as their appearances change over time.
559.
Krum, David M.; Kang, Sin-Hwa; Bolas, Mark
Virtual Coaches over Mobile Video Proceedings Article
In: Proceedingsof International Conference on Computer Animation and Social Agents (CASA), 2014.
@inproceedings{krum_virtual_2014,
title = {Virtual Coaches over Mobile Video},
author = {David M. Krum and Sin-Hwa Kang and Mark Bolas},
url = {http://ict.usc.edu/pubs/Virtual%20Coaches%20over%20Mobile%20Video.pdf},
year = {2014},
date = {2014-05-01},
booktitle = {Proceedingsof International Conference on Computer Animation and Social Agents (CASA)},
abstract = {We hypothesize that the context of a smartphone, how a virtual human is presented within a smartphone app, and indeed, the nature of that app, can profoundly affect how the virtual human is perceived by a real human. We believe that virtual humans, presented over video chat services (such as Skype) and delivered using mobile phones, can be an effective way to deliver coaching applications. We propose to build a prototype system that allows virtual humans to initiate and receive Skype calls. This hardware will enable broadcast of the audio and video imagery of a character. Using this platform and a virtual human, we will conduct two user studies. The first study will examine factors involved in making a mobile video based character seem engaging and “real”. This study will examine how character appearance and the artifacts of the communication channel, such as video and audio quality, can affect rapport with a virtual human. The second study will examine ways to maintain a long-term relationship with a character, leveraging the character’s ability to call and interact with a real human over a longer period of time. These studies will help develop design guidelines for presenting virtual humans over mobile video.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
We hypothesize that the context of a smartphone, how a virtual human is presented within a smartphone app, and indeed, the nature of that app, can profoundly affect how the virtual human is perceived by a real human. We believe that virtual humans, presented over video chat services (such as Skype) and delivered using mobile phones, can be an effective way to deliver coaching applications. We propose to build a prototype system that allows virtual humans to initiate and receive Skype calls. This hardware will enable broadcast of the audio and video imagery of a character. Using this platform and a virtual human, we will conduct two user studies. The first study will examine factors involved in making a mobile video based character seem engaging and “real”. This study will examine how character appearance and the artifacts of the communication channel, such as video and audio quality, can affect rapport with a virtual human. The second study will examine ways to maintain a long-term relationship with a character, leveraging the character’s ability to call and interact with a real human over a longer period of time. These studies will help develop design guidelines for presenting virtual humans over mobile video.
560.
Kang, Sin-Hwa; Gratch, Jonathan
Exploring Users' Social Responses to Computer Counseling Interviewers' Behavior Journal Article
In: Journal of Computers in Human Behavior, vol. 34, pp. 120–130, 2014.
@article{kang_exploring_2014,
title = {Exploring Users' Social Responses to Computer Counseling Interviewers' Behavior},
author = {Sin-Hwa Kang and Jonathan Gratch},
url = {http://linkinghub.elsevier.com/retrieve/pii/S0747563214000119},
doi = {10.1016/j.chb.2014.01.006},
year = {2014},
date = {2014-05-01},
journal = {Journal of Computers in Human Behavior},
volume = {34},
pages = {120–130},
abstract = {We explore the effect of behavioral realism and reciprocal self-disclosure from computer interviewers on the social responses of human users in simulated psychotherapeutic counseling interactions. To investigate this subject, we designed a 3x3 factorial between-subjects experiment involving three conditions of behavioral realism: high realism, low realism, and audio-only (displaying no behavior at all) and three conditions of reciprocal self-disclosure: high disclosure, low disclosure, and no disclosure. We measured users' feelings of social presence (Copresence, Social Attraction, and Emotional Credibility), rapport, perception of the quality of users' own responses (Embarrassment and Self-Performance), emotional state (PANAS), perception of an interaction partner (Personal Perception), self-reported self-disclosure. We observed some contradictory outcomes in users' subjective reports. However, the results of objective data analysis demonstrated that users disclosed greater verbal self-disclosure (medium level of intimacy) when interacting with computer interviewers that displayed high behavioral realism and high self-disclosure. Users also delivered more fluent speech when interacting with computer interviewers that displayed high behaviorla realism. The results are described in detail and implications of the findings are discussed in this paper.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
We explore the effect of behavioral realism and reciprocal self-disclosure from computer interviewers on the social responses of human users in simulated psychotherapeutic counseling interactions. To investigate this subject, we designed a 3x3 factorial between-subjects experiment involving three conditions of behavioral realism: high realism, low realism, and audio-only (displaying no behavior at all) and three conditions of reciprocal self-disclosure: high disclosure, low disclosure, and no disclosure. We measured users' feelings of social presence (Copresence, Social Attraction, and Emotional Credibility), rapport, perception of the quality of users' own responses (Embarrassment and Self-Performance), emotional state (PANAS), perception of an interaction partner (Personal Perception), self-reported self-disclosure. We observed some contradictory outcomes in users' subjective reports. However, the results of objective data analysis demonstrated that users disclosed greater verbal self-disclosure (medium level of intimacy) when interacting with computer interviewers that displayed high behavioral realism and high self-disclosure. Users also delivered more fluent speech when interacting with computer interviewers that displayed high behaviorla realism. The results are described in detail and implications of the findings are discussed in this paper.
Filter
Sorry, no publications matched your criteria.