Effects of conversational agents on human communication in thought-evoking multi-party dialogues

Dohsaka, Kohji; Asai, Ryota; Higashinaka, Ryuichiro; Minami, Yasuhiro; Maeda, Eriko

doi:10.3115/1708376.1708408

Cited by 18 publications

(13 citation statements)

References 20 publications

(14 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similarly, self-disclosure increased when users had positive preferences for discussion topics and the system's agreement was effective for inducing agreement from users. A study focused on linguistic behavior, i.e., empathic and self-oriented emotional expression in a text-based game-setup, had similar results [26]. In particular, empathic expression significantly improved user satisfaction, raised ratings of a peer agent and increased the number of user utterances emitted in the game.…”

Section: Relevant Researchmentioning

confidence: 76%

Affect and Social Processes in Online Communication--Experiments with an Affective Dialog System

Skowron

Theunis

Rank

et al. 2013

IEEE Trans. Affective Comput.

View full text Add to dashboard Cite

Abstract-This paper presents an integrated view on a series of experiments conducted with an affective dialog system, applied as a tool in studies of emotions and social processes in online communication. The different realizations of the system are evaluated in three experimental setups in order to verify effects of affective profiles, as well as of fine-grained communication scenarios on users' expressions of affective states, experienced emotional changes, and interaction patterns. Results demonstrate that the system applied in virtual reality settings matches a Wizard-of-Oz in terms of chatting enjoyment, dialog coherence and realism. Variants of the system's affective profile significantly influence the rating of chatting enjoyment and an emotional connection. Self-reported emotional changes experienced by participants during an interaction with the system are in line with the type of applied profile. Analysis of interaction patterns, i.e., usage of particular dialog act classes, word categories, and textual expressions of affective states for different scenarios, demonstrates that a communication scenario for social sharing of emotions was successfully established. The experimental evidence provides valuable input for applications of affective dialog systems and strengthens them as valid tools for studying affect and social aspects in online communication.Index Terms-Affective dialog system, human-computer interaction, affect sensing and analysis, structuring affective interactions.

show abstract

Section: Relevant Researchmentioning

confidence: 76%

Affect and Social Processes in Online Communication--Experiments with an Affective Dialog System

Skowron

Theunis

Rank

et al. 2013

IEEE Trans. Affective Comput.

View full text Add to dashboard Cite

show abstract

“…Dohsaka et al (2009) developed a thought-evoking dialogue system for multiparty conversations with a quiz-game task. They reported that the existence of agents and empathic expressions is effective for user satisfaction and can increase the number of user utterances.…”

Section: Introductionmentioning

confidence: 99%

Four-participant group conversation: A facilitation robot controlling engagement density as the fourth participant

Matsuyama

Akiba

Fujie

et al. 2015

Computer Speech & Language

View full text Add to dashboard Cite

In this paper, we present a framework for facilitation robots that regulate imbalanced engagement density in a four-participant conversation as the forth participant with proper procedures for obtaining initiatives. Four is the special number in multiparty conversations. In three-participant conversations, the minimum unit for multiparty conversations, social imbalance, in which a participant is left behind in the current conversation, sometimes occurs. In such scenarios, a conversational robot has the potential to objectively observe and control situations as the fourth participant. Consequently, we present model procedures for obtaining conversational initiatives in incremental steps to harmonize such four-participant conversations. During the procedures, a facilitator must be aware of both the presence of dominant participants leading the current conversation and the status of any participant that is left behind. We model and optimize these situations and procedures as a partially observable Markov decision process (POMDP), which is suitable for real-world sequential decision processes. The results of experiments conducted to evaluate the proposed procedures show evidence of their acceptability and feeling of groupness.

show abstract

“…Our prior work [Kumar et al 2010a;Kumar et al 2007a] has shown that social behavior motivated from empirical research in small group communication [Bales 1950] can help in effectively supporting students in collaborative learning settings. The use of social interaction in other applications of CAs besides education has been investigated [Bickmore et al 2009;Dybala et al 2009;Dohsaka et al 2009], and in this article, we also demonstrate generality of positive effect from the collaborative learning domain to a collaborative decision-making task. The experiments presented here bridge these two tracks of research, specifically proposing a solution to the challenge of timing social behavior in the context of supporting collaborative learning.…”

Section: Discussionmentioning

confidence: 55%

“…Work in the area of affective computing and its application to tutorial dialog has focused on identification of student's emotional states [D'Mello et al 2008] and using those to improve choice of task-related behavior by tutors. However, recently CAs have been used to support multiparty activities such as collaborative learning [Kumar et al 2007b], communication [Isbell et al 2001], information assistance [Zheng et al 2005;Bohus and Horvitz 2009], and games [Dohsaka et al 2009]. Specifically in the application area of collaborative learning, systematic evaluations of the use of CAs to support small groups of students have shown improvements of more than a letter grade in learning attributed to the support offered by these automated agents [Kumar et al 2007b].…”

Section: Introductionmentioning

confidence: 98%

Triggering effective social support for online groups

Kumar

Rosé

2014

ACM Trans. Interact. Intell. Syst.

View full text Add to dashboard Cite

Conversational agent technology is an emerging paradigm for creating a social environment in online groups that is conducive to effective teamwork. Prior work has demonstrated advantages in terms of learning gains and satisfaction scores when groups learning together online have been supported by conversational agents that employ Balesian social strategies. This prior work raises two important questions that are addressed in this article. The first question is one of generality. Specifically, are the positive effects of the designed support specific to learning contexts? Or are they in evidence in other collaborative task domains as well? We present a study conducted within a collaborative decision-making task where we see that the positive effects of the Balesian social strategies extend to this new context. The second question is whether it is possible to increase the effectiveness of the Balesian social strategies by increasing the context sensitivity with which the social strategies are triggered. To this end, we present technical work that increases the sensitivity of the triggering. Next, we present a user study that demonstrates an improvement in performance of the support agent with the new, more sensitive triggering policy over the baseline approach from prior work.The technical contribution of this article is that we extend prior work where such support agents were modeled using a composition of conversational behaviors integrated within an event-driven framework. Within the present approach, conversation is orchestrated through context-sensitive triggering of the composed behaviors. The core effort involved in applying this approach involves building a set of triggering policies that achieve this orchestration in a time-sensitive and coherent manner. In line with recent developments in data-driven approaches for building dialog systems, we present a novel technique for learning behaviorspecific triggering policies, deploying it as part of our efforts to improve a socially capable conversational tutor agent that supports collaborative learning.

show abstract

Effects of conversational agents on human communication in thought-evoking multi-party dialogues

Cited by 18 publications

References 20 publications

Affect and Social Processes in Online Communication--Experiments with an Affective Dialog System

Affect and Social Processes in Online Communication--Experiments with an Affective Dialog System

Four-participant group conversation: A facilitation robot controlling engagement density as the fourth participant

Triggering effective social support for online groups

Contact Info

Product

Resources

About