Reza Moradinezhad | Drexel University (original) (raw)

Papers by Reza Moradinezhad

The Advanced Interaction Research Lab at Drexel conducts research on emerging human-computer inte... more The Advanced Interaction Research Lab at Drexel conducts research on emerging human-computer interaction techniques, with a focus on physiological computing and brain-computer interfaces, as well as human interaction with autonomous systems and vehicles. We see potential in the combination of brain sensing and autonomous vehicle research to better understand the user experience in autonomous vehicles.

Proceedings of the 2017 ACM SIGCHI Conference on Creativity and Cognition, 2017

Collaborative ideation systems can help people generate more creative ideas by exposing them to i... more Collaborative ideation systems can help people generate more creative ideas by exposing them to ideas different from their own. However, there are competing theoretical views on whether and when such exposure is helpful. Associationist theory suggests that exposing ideators to ideas that are semantically far from their own maximizes novel combinations of ideas. In contrast, SIAM theory cautions that systems should offer far ideas only when ideators reach an impasse (a cognitive state in which they have exhausted ideas within a particular category), and offer near ideas during productive ideation (a cognitive state in which they are actively exploring ideas within a category), which maximizes exploration within categories. Our research compares these theoretical recommendations. In an online experiment, 245 participants generated ideas for a themed wedding; we detected and validated participants' cognitive states using a combination of behavioral and neuroimaging data. Receiving far ideas during productive ideation resulted in slower ideation and less within-category exploration, without significant benefits for novelty, compared to receiving no inspirations. Participants were also more likely to hit an impasse when receiving far ideas during productive ideation. These findings suggest that far inspirational ideas can harm creativity if received during productive ideation.

International Journal of Engineering, Sep 1, 2017

In this research, Artificial Neural Networks (ANNs) have been used as a powerful tool to solve th... more In this research, Artificial Neural Networks (ANNs) have been used as a powerful tool to solve the inverse kinematic equations of a parallel robot. For this purpose, we have developed the kinematic equations of a Tricept parallel kinematic mechanism with two rotational and one translational degrees of freedom (DoF). Using the analytical method, the inverse kinematic equations are solved for specific trajectory, and used as inputs for the applied ANNs. The results of both applied networks (Multi-Layer Perceptron and Redial Basis Function) satisfied the required performance in solving complex inverse kinematics with proper accuracy and speed.

Frontiers in Human Neuroscience, 2018

We explore the interaction between humans and Embodied Virtual Agents (EVAs) which are a specific... more We explore the interaction between humans and Embodied Virtual Agents (EVAs) which are a specific type of intelligent agents. We design an EVA as an assistant in a general-knowledge Question and Answer (Q&A) task. The EVA provides feedback to the user about each of the possible answers by expressing different facial expressions. Two types of agents are used in this study: cooperative and uncooperative. The research question that we are exploring is: "Would a human's trust towards an agent be affected by their previous interaction with another agent?". The four hypotheses are presented in table 1. To determine the difficulty of the questions, in a preliminary online survey, we asked 187 participants to answer 25 questions online, without interacting with any agent. Then, we ask them to see a video of the agent performing six different facial expressions and rate their positiveness/negativeness and intensity (Slightly-Positive, Moderately-Positive, Highly-Positive, Slightly-Negative, Moderately-Negative, Highly-Negative). The main system includes a Q&A page with the agent's face visible on the same screen. Participants answer two sets of 50 multiplechoice questions. While hovering over each answer, they see a facial feedback from the agent. The first 30 questions are easy to medium in difficulty to ensure that the participants have a good level of certainty about the correctness of the answers so that they can judge the behavior of the agent as cooperative or uncooperative. The last 20 questions are difficult, requiring participants to rely more on the agent. Figure 1 shows the system interface. About Submit Journals Research Topics Search for articles, people, events and more.

2015 7th Conference on Information and Knowledge Technology (IKT), 2015

The growth of internet attacks is a major problem for today's computer networks. Hence, imple... more The growth of internet attacks is a major problem for today's computer networks. Hence, implementing security methods to prevent such attacks is crucial for any computer network. With the help of Machine Learning and Data Mining techniques, Intrusion Detection Systems (IDS) are able to diagnose attacks and system anomalies more effectively. Though, most of the studied methods in this field, including Rule-based expert systems, are not able to successfully identify the attacks which have different patterns from expected ones. By using Artificial Neural Networks (ANNs), it is possible to identify the attacks and classify the data, even when the dataset is nonlinear, limited, or incomplete. In this paper, a method based on the combination of Decision Tree (DT) algorithm and Multi-Layer Perceptron (MLP) ANN is proposed which is able to identify attacks with high accuracy and reliability.

International Journal of Social Robotics

Embodied Virtual Agents (EVAs) are used today as interfaces for social robots, educational tutors... more Embodied Virtual Agents (EVAs) are used today as interfaces for social robots, educational tutors, game counterparts, medical assistants, as well as companions for the elderly and individuals with psychological or behavioral conditions. Forming a reliable and trustworthy interaction is critical to the success and acceptability of this new form of interaction. In this paper, we report on a study investigating how trust is influenced by the cooperativeness of an EVA as well as an individuals prior experience with other agents. Participants answered two sets of multiple choice questions, working with a different agent in each set. Two types of agent behaviors were possible: Cooperative and Uncooperative. In addition to participants achieving significantly higher performance and having higher trust for the cooperative agent, we found that participants' trust for the cooperative agent was significantly higher if they interacted with an uncooperative agent in one of the sets, compared to working with cooperative agents in both sets. Furthermore, we found that participants may still decide to choose agent's suggested answer (which can be incorrect) over theirs, even if they are fairly certain their own answer is the correct one. The results suggest that trust for an EVA is relative and it is dependent on user's history of interaction with different agents in addition to current agent's behavior. The findings provide insight into important considerations for creating trustworthy EVAs.

Proceedings of the CHI 2017 Workshop on Amplification and Augmentation of Human Perception, May 0... more Proceedings of the CHI 2017 Workshop on Amplification and Augmentation of Human Perception, May 07, 2017, Denver, CO, USA. Copyright is held by the owner/author(s). Abstract Virtual agents are used in different fields such as games, education, and rehabilitation. They make the interaction feel more natural and can even be integrated with sensing platforms to perform tasks (such as biometric identification, eye tracking, etc. [5]) that a normal human cannot do. The Advanced Interaction Research Lab at Drexel University conducts research on emerging human-computer interaction techniques, with a focus on physiological computing and brain-computer interfaces. Some current projects investigate the effectiveness of virtual assistants in improving human performance during learning and creative tasks. In this workshop, in particular, we would like to discuss the role of an embodied virtual agent in amplifying a person’s perceptions of the surrounding world by integrating it with physiologic...

Proceedings of the CHI 2020 Workshop on Mapping Grand Challenges for the Conversational User Inte... more Proceedings of the CHI 2020 Workshop on Mapping Grand Challenges for the Conversational User Interface Community, April 25, 2020, Honolulu, Hawaii, USA. Copyright is held by the owner/author(s). Abstract Although it takes longer to build trust toward embodied conversational agents (ECAs), once built, this trust is more resilient to errors than conventional (e.g. WIMP) user interfaces [5]. In our work, we are exploring factors that influence the process of building trust in an ECA through interaction, as well as how the behavior of one ECA can influence perceptions of trust in other ECAs.

—The growth of internet attacks is a major problem for today's computer networks. Hence, implemen... more —The growth of internet attacks is a major problem for today's computer networks. Hence, implementing security methods to prevent such attacks is crucial for any computer network. With the help of Machine Learning and Data Mining techniques, Intrusion Detection Systems (IDS) are able to diagnose attacks and system anomalies more effectively. Though, most of the studied methods in this field, including Rule-based expert systems, are not able to successfully identify the attacks which have different patterns from expected ones. By using Artificial Neural Networks (ANNs), it is possible to identify the attacks and classify the data, even when the dataset is nonlinear, limited, or incomplete. In this paper, a method based on the combination of Decision Tree (DT) algorithm and Multi-Layer Perceptron (MLP) ANN is proposed which is able to identify attacks with high accuracy and reliability.

The Advanced Interaction Research Lab at Drexel conducts research on emerging human-computer inte... more The Advanced Interaction Research Lab at Drexel conducts research on emerging human-computer interaction techniques, with a focus on physiological computing and brain-computer interfaces, as well as human interaction with autonomous systems and vehicles. We see potential in the combination of brain sensing and autonomous vehicle research to better understand the user experience in autonomous vehicles.

Virtual agents are used in different fields such as games, education, and rehabilitation. They ma... more Virtual agents are used in different fields such as games, education, and rehabilitation. They make the interaction feel more natural and can even be integrated with sensing platforms to perform tasks (such as biometric identification, eye tracking, etc. [5]) that a normal human cannot do. The Advanced Interaction Research Lab at Drexel University conducts research on emerging human-computer interaction techniques, with a focus on physiological computing and brain-computer interfaces. Some current projects investigate the effectiveness of virtual assistants in improving human performance during learning and creative tasks. In this workshop, in particular, we would like to discuss the role of an embodied virtual agent in amplifying a person's perceptions of the surrounding world by integrating it with physiological and brain data.

Collaborative ideation systems can help people generate more creative ideas by exposing them to i... more Collaborative ideation systems can help people generate more creative ideas by exposing them to ideas different from their own. However, there are competing theoretical views on whether and when such exposure is helpful. Associationist theory suggests that exposing ideators to ideas that are semantically far from their own maximizes novel combinations of ideas. In contrast, SIAM theory cautions that systems should offer far ideas only when ideators reach an impasse (a cognitive state in which they have exhausted ideas within a particular category), and offer near ideas during productive ideation (a cognitive state in which they are actively exploring ideas within a category), which maximizes exploration within categories. Our research compares these theoretical recommendations. In an online experiment, 245 participants generated ideas for a themed wedding; we detected and validated participants' cognitive states using a combination of behavioral and neuroimaging data. Receiving far ideas during productive ideation resulted in slower ideation and less within-category exploration, without significant benefits for novelty, compared to receiving no inspirations. Participants were also more likely to hit an impasse when receiving far ideas during productive ideation. These findings suggest that far inspirational ideas can harm creativity if received during productive ideation.

In this research, Artificial Neural Networks (ANNs) have been used as a powerful tool to solve th... more In this research, Artificial Neural Networks (ANNs) have been used as a powerful tool to solve the inverse kinematic equations of a parallel robot. For this purpose, we have developed the kinematic equations of a Tricept parallel kinematic mechanism with two rotational and one translational degrees of freedom (DoF). Using the analytical method, the inverse kinematic equations are solved for specific trajectory, and used as inputs for the applied ANNs. The results of both applied networks (Multi-Layer Perceptron and Redial Basis Function) satisfied the required performance in solving complex inverse kinematics with proper accuracy and speed.

We explore the interaction between humans and Embodied Virtual Agents (EVAs) which are a specific... more We explore the interaction between humans and Embodied Virtual Agents (EVAs) which are a specific type of intelligent agents. We design an EVA as an assistant in a general-knowledge Question and Answer (Q&A) task. The EVA provides feedback to the user about each of the possible answers by expressing different facial expressions. Two types of agents are used in this study: cooperative and uncooperative. The research question that we are exploring is: " Would a human's trust towards an agent be affected by their previous interaction with another agent? ". The four hypotheses are presented in table 1. To determine the difficulty of the questions, in a preliminary online survey, we asked 187 participants to answer 25 questions online, without interacting with any agent. Then, we ask them to see a video of the agent performing six different facial expressions and rate their positiveness/negativeness and intensity (Slightly-Positive, Moderately-Positive, Highly-Positive, Slightly-Negative, Moderately-Negative, Highly-Negative). The main system includes a Q&A page with the agent's face visible on the same screen. Participants answer two sets of 50 multiple-choice questions. While hovering over each answer, they see a facial feedback from the agent. The first 30 questions are easy to medium in difficulty to ensure that the participants have a good level of certainty about the correctness of the answers so that they can judge the behavior of the agent as cooperative or uncooperative. The last 20 questions are difficult, requiring participants to rely more on the agent. Figure 1 shows the system interface. The facial expressions and some random movements (e.g. blinking, moving the head, looking sideways) are created based on previous works which investigated the role of different facial expression on positive/negative implications of the face (Rehm & Andre, 2005), (Elkins & Derrick, 2013), (Hyde, Carter, Kiesler & Hodgins, 2016). Figure 2 shows the six different facial expressions on both agents. This is a between-subjects study, meaning each participant does only one of the four experimental conditions. The independent variable is the agent behavior pattern over two sessions. There are four levels, depending on whether the agent is cooperative or uncooperative in each of two sessions. Thus, the four levels are 1) cooperative first-uncooperative second (CN), 2) uncooperative first-cooperative second (NC), 3) both cooperative (CC), and 4) both uncooperative (NN). Dependent variables would be time to answer each individual question, time to answer each set of 50 questions in a condition, percentage of correct answers in each set, and the amount of trust towards the agent. The trust towards the agent would be assessed by the questionnaire introduced by Jian et al. (Jian, Bisantz &

2015 7th Conference on Information and Knowledge Technology (IKT), 2015

The Advanced Interaction Research Lab at Drexel conducts research on emerging human-computer inte... more The Advanced Interaction Research Lab at Drexel conducts research on emerging human-computer interaction techniques, with a focus on physiological computing and brain-computer interfaces, as well as human interaction with autonomous systems and vehicles. We see potential in the combination of brain sensing and autonomous vehicle research to better understand the user experience in autonomous vehicles.

Proceedings of the 2017 ACM SIGCHI Conference on Creativity and Cognition, 2017

Collaborative ideation systems can help people generate more creative ideas by exposing them to i... more Collaborative ideation systems can help people generate more creative ideas by exposing them to ideas different from their own. However, there are competing theoretical views on whether and when such exposure is helpful. Associationist theory suggests that exposing ideators to ideas that are semantically far from their own maximizes novel combinations of ideas. In contrast, SIAM theory cautions that systems should offer far ideas only when ideators reach an impasse (a cognitive state in which they have exhausted ideas within a particular category), and offer near ideas during productive ideation (a cognitive state in which they are actively exploring ideas within a category), which maximizes exploration within categories. Our research compares these theoretical recommendations. In an online experiment, 245 participants generated ideas for a themed wedding; we detected and validated participants' cognitive states using a combination of behavioral and neuroimaging data. Receiving far ideas during productive ideation resulted in slower ideation and less within-category exploration, without significant benefits for novelty, compared to receiving no inspirations. Participants were also more likely to hit an impasse when receiving far ideas during productive ideation. These findings suggest that far inspirational ideas can harm creativity if received during productive ideation.

International Journal of Engineering, Sep 1, 2017

In this research, Artificial Neural Networks (ANNs) have been used as a powerful tool to solve th... more In this research, Artificial Neural Networks (ANNs) have been used as a powerful tool to solve the inverse kinematic equations of a parallel robot. For this purpose, we have developed the kinematic equations of a Tricept parallel kinematic mechanism with two rotational and one translational degrees of freedom (DoF). Using the analytical method, the inverse kinematic equations are solved for specific trajectory, and used as inputs for the applied ANNs. The results of both applied networks (Multi-Layer Perceptron and Redial Basis Function) satisfied the required performance in solving complex inverse kinematics with proper accuracy and speed.

Frontiers in Human Neuroscience, 2018

We explore the interaction between humans and Embodied Virtual Agents (EVAs) which are a specific... more We explore the interaction between humans and Embodied Virtual Agents (EVAs) which are a specific type of intelligent agents. We design an EVA as an assistant in a general-knowledge Question and Answer (Q&A) task. The EVA provides feedback to the user about each of the possible answers by expressing different facial expressions. Two types of agents are used in this study: cooperative and uncooperative. The research question that we are exploring is: "Would a human's trust towards an agent be affected by their previous interaction with another agent?". The four hypotheses are presented in table 1. To determine the difficulty of the questions, in a preliminary online survey, we asked 187 participants to answer 25 questions online, without interacting with any agent. Then, we ask them to see a video of the agent performing six different facial expressions and rate their positiveness/negativeness and intensity (Slightly-Positive, Moderately-Positive, Highly-Positive, Slightly-Negative, Moderately-Negative, Highly-Negative). The main system includes a Q&A page with the agent's face visible on the same screen. Participants answer two sets of 50 multiplechoice questions. While hovering over each answer, they see a facial feedback from the agent. The first 30 questions are easy to medium in difficulty to ensure that the participants have a good level of certainty about the correctness of the answers so that they can judge the behavior of the agent as cooperative or uncooperative. The last 20 questions are difficult, requiring participants to rely more on the agent. Figure 1 shows the system interface. About Submit Journals Research Topics Search for articles, people, events and more.

2015 7th Conference on Information and Knowledge Technology (IKT), 2015

The growth of internet attacks is a major problem for today's computer networks. Hence, imple... more The growth of internet attacks is a major problem for today's computer networks. Hence, implementing security methods to prevent such attacks is crucial for any computer network. With the help of Machine Learning and Data Mining techniques, Intrusion Detection Systems (IDS) are able to diagnose attacks and system anomalies more effectively. Though, most of the studied methods in this field, including Rule-based expert systems, are not able to successfully identify the attacks which have different patterns from expected ones. By using Artificial Neural Networks (ANNs), it is possible to identify the attacks and classify the data, even when the dataset is nonlinear, limited, or incomplete. In this paper, a method based on the combination of Decision Tree (DT) algorithm and Multi-Layer Perceptron (MLP) ANN is proposed which is able to identify attacks with high accuracy and reliability.

International Journal of Social Robotics

Embodied Virtual Agents (EVAs) are used today as interfaces for social robots, educational tutors... more Embodied Virtual Agents (EVAs) are used today as interfaces for social robots, educational tutors, game counterparts, medical assistants, as well as companions for the elderly and individuals with psychological or behavioral conditions. Forming a reliable and trustworthy interaction is critical to the success and acceptability of this new form of interaction. In this paper, we report on a study investigating how trust is influenced by the cooperativeness of an EVA as well as an individuals prior experience with other agents. Participants answered two sets of multiple choice questions, working with a different agent in each set. Two types of agent behaviors were possible: Cooperative and Uncooperative. In addition to participants achieving significantly higher performance and having higher trust for the cooperative agent, we found that participants' trust for the cooperative agent was significantly higher if they interacted with an uncooperative agent in one of the sets, compared to working with cooperative agents in both sets. Furthermore, we found that participants may still decide to choose agent's suggested answer (which can be incorrect) over theirs, even if they are fairly certain their own answer is the correct one. The results suggest that trust for an EVA is relative and it is dependent on user's history of interaction with different agents in addition to current agent's behavior. The findings provide insight into important considerations for creating trustworthy EVAs.

Proceedings of the CHI 2017 Workshop on Amplification and Augmentation of Human Perception, May 0... more Proceedings of the CHI 2017 Workshop on Amplification and Augmentation of Human Perception, May 07, 2017, Denver, CO, USA. Copyright is held by the owner/author(s). Abstract Virtual agents are used in different fields such as games, education, and rehabilitation. They make the interaction feel more natural and can even be integrated with sensing platforms to perform tasks (such as biometric identification, eye tracking, etc. [5]) that a normal human cannot do. The Advanced Interaction Research Lab at Drexel University conducts research on emerging human-computer interaction techniques, with a focus on physiological computing and brain-computer interfaces. Some current projects investigate the effectiveness of virtual assistants in improving human performance during learning and creative tasks. In this workshop, in particular, we would like to discuss the role of an embodied virtual agent in amplifying a person’s perceptions of the surrounding world by integrating it with physiologic...

Proceedings of the CHI 2020 Workshop on Mapping Grand Challenges for the Conversational User Inte... more Proceedings of the CHI 2020 Workshop on Mapping Grand Challenges for the Conversational User Interface Community, April 25, 2020, Honolulu, Hawaii, USA. Copyright is held by the owner/author(s). Abstract Although it takes longer to build trust toward embodied conversational agents (ECAs), once built, this trust is more resilient to errors than conventional (e.g. WIMP) user interfaces [5]. In our work, we are exploring factors that influence the process of building trust in an ECA through interaction, as well as how the behavior of one ECA can influence perceptions of trust in other ECAs.

—The growth of internet attacks is a major problem for today's computer networks. Hence, implemen... more —The growth of internet attacks is a major problem for today's computer networks. Hence, implementing security methods to prevent such attacks is crucial for any computer network. With the help of Machine Learning and Data Mining techniques, Intrusion Detection Systems (IDS) are able to diagnose attacks and system anomalies more effectively. Though, most of the studied methods in this field, including Rule-based expert systems, are not able to successfully identify the attacks which have different patterns from expected ones. By using Artificial Neural Networks (ANNs), it is possible to identify the attacks and classify the data, even when the dataset is nonlinear, limited, or incomplete. In this paper, a method based on the combination of Decision Tree (DT) algorithm and Multi-Layer Perceptron (MLP) ANN is proposed which is able to identify attacks with high accuracy and reliability.

The Advanced Interaction Research Lab at Drexel conducts research on emerging human-computer inte... more The Advanced Interaction Research Lab at Drexel conducts research on emerging human-computer interaction techniques, with a focus on physiological computing and brain-computer interfaces, as well as human interaction with autonomous systems and vehicles. We see potential in the combination of brain sensing and autonomous vehicle research to better understand the user experience in autonomous vehicles.

Virtual agents are used in different fields such as games, education, and rehabilitation. They ma... more Virtual agents are used in different fields such as games, education, and rehabilitation. They make the interaction feel more natural and can even be integrated with sensing platforms to perform tasks (such as biometric identification, eye tracking, etc. [5]) that a normal human cannot do. The Advanced Interaction Research Lab at Drexel University conducts research on emerging human-computer interaction techniques, with a focus on physiological computing and brain-computer interfaces. Some current projects investigate the effectiveness of virtual assistants in improving human performance during learning and creative tasks. In this workshop, in particular, we would like to discuss the role of an embodied virtual agent in amplifying a person's perceptions of the surrounding world by integrating it with physiological and brain data.

Collaborative ideation systems can help people generate more creative ideas by exposing them to i... more Collaborative ideation systems can help people generate more creative ideas by exposing them to ideas different from their own. However, there are competing theoretical views on whether and when such exposure is helpful. Associationist theory suggests that exposing ideators to ideas that are semantically far from their own maximizes novel combinations of ideas. In contrast, SIAM theory cautions that systems should offer far ideas only when ideators reach an impasse (a cognitive state in which they have exhausted ideas within a particular category), and offer near ideas during productive ideation (a cognitive state in which they are actively exploring ideas within a category), which maximizes exploration within categories. Our research compares these theoretical recommendations. In an online experiment, 245 participants generated ideas for a themed wedding; we detected and validated participants' cognitive states using a combination of behavioral and neuroimaging data. Receiving far ideas during productive ideation resulted in slower ideation and less within-category exploration, without significant benefits for novelty, compared to receiving no inspirations. Participants were also more likely to hit an impasse when receiving far ideas during productive ideation. These findings suggest that far inspirational ideas can harm creativity if received during productive ideation.

In this research, Artificial Neural Networks (ANNs) have been used as a powerful tool to solve th... more In this research, Artificial Neural Networks (ANNs) have been used as a powerful tool to solve the inverse kinematic equations of a parallel robot. For this purpose, we have developed the kinematic equations of a Tricept parallel kinematic mechanism with two rotational and one translational degrees of freedom (DoF). Using the analytical method, the inverse kinematic equations are solved for specific trajectory, and used as inputs for the applied ANNs. The results of both applied networks (Multi-Layer Perceptron and Redial Basis Function) satisfied the required performance in solving complex inverse kinematics with proper accuracy and speed.

We explore the interaction between humans and Embodied Virtual Agents (EVAs) which are a specific... more We explore the interaction between humans and Embodied Virtual Agents (EVAs) which are a specific type of intelligent agents. We design an EVA as an assistant in a general-knowledge Question and Answer (Q&A) task. The EVA provides feedback to the user about each of the possible answers by expressing different facial expressions. Two types of agents are used in this study: cooperative and uncooperative. The research question that we are exploring is: " Would a human's trust towards an agent be affected by their previous interaction with another agent? ". The four hypotheses are presented in table 1. To determine the difficulty of the questions, in a preliminary online survey, we asked 187 participants to answer 25 questions online, without interacting with any agent. Then, we ask them to see a video of the agent performing six different facial expressions and rate their positiveness/negativeness and intensity (Slightly-Positive, Moderately-Positive, Highly-Positive, Slightly-Negative, Moderately-Negative, Highly-Negative). The main system includes a Q&A page with the agent's face visible on the same screen. Participants answer two sets of 50 multiple-choice questions. While hovering over each answer, they see a facial feedback from the agent. The first 30 questions are easy to medium in difficulty to ensure that the participants have a good level of certainty about the correctness of the answers so that they can judge the behavior of the agent as cooperative or uncooperative. The last 20 questions are difficult, requiring participants to rely more on the agent. Figure 1 shows the system interface. The facial expressions and some random movements (e.g. blinking, moving the head, looking sideways) are created based on previous works which investigated the role of different facial expression on positive/negative implications of the face (Rehm & Andre, 2005), (Elkins & Derrick, 2013), (Hyde, Carter, Kiesler & Hodgins, 2016). Figure 2 shows the six different facial expressions on both agents. This is a between-subjects study, meaning each participant does only one of the four experimental conditions. The independent variable is the agent behavior pattern over two sessions. There are four levels, depending on whether the agent is cooperative or uncooperative in each of two sessions. Thus, the four levels are 1) cooperative first-uncooperative second (CN), 2) uncooperative first-cooperative second (NC), 3) both cooperative (CC), and 4) both uncooperative (NN). Dependent variables would be time to answer each individual question, time to answer each set of 50 questions in a condition, percentage of correct answers in each set, and the amount of trust towards the agent. The trust towards the agent would be assessed by the questionnaire introduced by Jian et al. (Jian, Bisantz &

2015 7th Conference on Information and Knowledge Technology (IKT), 2015