TY - JOUR TI - Using AI-Generated Avatar Interactions To Study Socio-Affective Functions of Feedback Signals in Language : an Exploratory Experimental Study on Head Nods AU - Compensis, Paul PY - 2026 SP - 117-136 PB - Otto-Friedrich-Universität CY - Bamberg UR - https://fis.uni-bamberg.de/handle/uniba/115359 LA - eng AB - Feedback signals are a central aspect of human interaction that often fulfil not only an interaction-structuring function (e.g., prompting a speaker to continue his story) but also serve socio-affective purposes. While both head nods and verbal continuers are used to signal affirmation, approval and continuation in a given interaction, head nods are also claimed to index social affiliation and stance-taking – in contrast to verbal continuers where this function is less clear. To investigate this potential functional difference further, I present the results of a pilot study that used AI-generated videos of dyadic interactions in which one avatar narrates a positive or negative life event while another avatar (the recipient) simply listens and occasionally provides feedback in the form of head nods, verbal continuers, a combination of both, or no feedback. While watching the videos, participants continuously rated how affiliative they perceived the behaviour of recipients in response to narrators and afterwards rated how socially adequate and empathic the recipient was. While recipients displaying head nods only or both feedback signals were rated as behaving more affiliative, more socially adequate and more empathic, avatars using verbal continuers only received lower ratings, with these ratings varying also depending on the story’s valence. The results of this study support the idea that head nods and verbal continuers differ in their socio-affective function and illustrate that using AI-generated avatars is a useful addition to interactional research, particularly to shed light on specific functions underlying different feedback signals. KW - Feedback in interaction KW - Backchannels KW - Head nods KW - Verbal continuers KW - Affiliation KW - Empathy KW - Virtual avatars ER - TY - JOUR TI - Using AI-Generated Avatar Interactions To Study Socio-Affective Functions of Feedback Signals in Language : an Exploratory Experimental Study on Head Nods AU - Compensis, Paul PY - 2026 JO - Journal of nonverbal behavior VL - 50 IS - 1 SP - 117-136 PB - Springer CY - New York, NY SN - 1573-3653 DO - 10.1007/s10919-026-00500-y UR - https://fis.uni-bamberg.de/handle/uniba/115358 LA - eng AB - Feedback signals are a central aspect of human interaction that often fulfil not only an interaction-structuring function (e.g., prompting a speaker to continue his story) but also serve socio-affective purposes. While both head nods and verbal continuers are used to signal affirmation, approval and continuation in a given interaction, head nods are also claimed to index social affiliation and stance-taking – in contrast to verbal continuers where this function is less clear. To investigate this potential functional difference further, I present the results of a pilot study that used AI-generated videos of dyadic interactions in which one avatar narrates a positive or negative life event while another avatar (the recipient) simply listens and occasionally provides feedback in the form of head nods, verbal continuers, a combination of both, or no feedback. While watching the videos, participants continuously rated how affiliative they perceived the behaviour of recipients in response to narrators and afterwards rated how socially adequate and empathic the recipient was. While recipients displaying head nods only or both feedback signals were rated as behaving more affiliative, more socially adequate and more empathic, avatars using verbal continuers only received lower ratings, with these ratings varying also depending on the story’s valence. The results of this study support the idea that head nods and verbal continuers differ in their socio-affective function and illustrate that using AI-generated avatars is a useful addition to interactional research, particularly to shed light on specific functions underlying different feedback signals. KW - Feedback in interaction KW - Backchannels KW - Head nods KW - Verbal continuers KW - Affiliation KW - Empathy KW - Virtual avatars ER - TY - CPAPER TI - Information Overload in Information Seeking with Conversational Agents : A Survey and Design Considerations AU - Compensis, Paul PY - 2026 SP - 474-479 PB - Otto-Friedrich-Universität CY - Bamberg UR - https://fis.uni-bamberg.de/handle/uniba/114968 LA - eng AB - Conversational agents and related systems enable more flexible and elaborate information seeking and retrieval than earlier search strategies, such as conventional web search engines. However, these systems sometimes produce responses that are excessively long or complex, not always aligning with the needs of their human interaction partners and potentially leading to information overload (IO). IO is associated with negative affect in humans and is known to reduce information effectiveness, thereby limiting the usability of information-seeking systems. In this paper, I briefly discuss psychological effects of IO and present the results of a survey examining self-reported experiences of IO when using conversational agents for information seeking in a German sample (n = 50). The paper concludes with suggestions for how conversational agents could be adapted and modified to become more sensitive to humans’ affective experiences, with the goal of mitigating the effects of IO. KW - conversational information seeking KW - information overload KW - humanagent interaction KW - conversational agent KW - afect ER - TY - CPAPER TI - Information Overload in Information Seeking with Conversational Agents : A Survey and Design Considerations AU - Compensis, Paul PY - 2026 T2 - Proceedings of the 2026 Conference on Human Information Interaction and Retrieval SP - 474-479 PB - ACM CY - New York, NY SN - 979-8-4007-2414-5 DO - 10.1145/3786304.3787886 UR - https://fis.uni-bamberg.de/handle/uniba/114902 LA - eng AB - Conversational agents and related systems enable more flexible and elaborate information seeking and retrieval than earlier search strategies, such as conventional web search engines. However, these systems sometimes produce responses that are excessively long or complex, not always aligning with the needs of their human interaction partners and potentially leading to information overload (IO). IO is associated with negative affect in humans and is known to reduce information effectiveness, thereby limiting the usability of information-seeking systems. In this paper, I briefly discuss psychological effects of IO and present the results of a survey examining self-reported experiences of IO when using conversational agents for information seeking in a German sample (n = 50). The paper concludes with suggestions for how conversational agents could be adapted and modified to become more sensitive to humans’ affective experiences, with the goal of mitigating the effects of IO. KW - conversational information seeking KW - information overload KW - humanagent interaction KW - conversational agent KW - afect ER - TY - JOUR TI - Assessing the integration of social information using AI-generated videos : a brief research report AU - Compensis, Paul PY - 2026 SP - 1-9 PB - Otto-Friedrich-Universität CY - Bamberg UR - https://fis.uni-bamberg.de/handle/uniba/113136 LA - eng AB - Integrating social information from different cues and modalities is a central feature of social functioning and humans respond sensitively to incongruences between different social information types (e.g., smiling while uttering a negative statement about oneself). To investigate the processing of these integration processes, researchers frequently draw on the simultaneous or consecutive presentation of static stimuli, such as written text and images, which often exhibit a relatively low naturalness of these stimuli. In this brief research report, I illustrate how AI-generated videos can successfully be used to overcome some of these limitations. Videos were generated by combining different avatar images (that were also generated with an AI tool) with text messages that either presented statements that were congruent or incongruent with expectations based on the age, gender, or facial emotion expressions of the avatar. In this pilot study, 47 participants watched these videos and rated the plausibility and emotional intensity of each utterance. Despite being fully generated artificially, videos elicited different responses depending on the condition. Incongruences based on social categories (age, gender) engendered lower plausibility ratings while intensity ratings were relatively unaffected. In contrast, intensity ratings for emotion expressions were expectedly higher (irrespective of congruence) but sensitivity to plausibility was affected by the congruence of the facial expression and the statement of the avatar. This pilot study illustrates the potential of AI-generated stimuli for investigating socio-cognitive processes, particularly in research on the integration of social information. KW - AI-generated stimuli KW - facial emotion expressions KW - social categories KW - social cues KW - social expectation violations ER - TY - JOUR TI - Assessing the integration of social information using AI-generated videos : a brief research report AU - Compensis, Paul PY - 2026 JO - Frontiers in psychology VL - 16 IS - 1505843 SP - 1-9 PB - Frontiers Research Foundation CY - Lausanne SN - 1664-1078 DO - 10.3389/fpsyg.2025.1505843 UR - https://fis.uni-bamberg.de/handle/uniba/113104 LA - eng AB - Integrating social information from different cues and modalities is a central feature of social functioning and humans respond sensitively to incongruences between different social information types (e.g., smiling while uttering a negative statement about oneself). To investigate the processing of these integration processes, researchers frequently draw on the simultaneous or consecutive presentation of static stimuli, such as written text and images, which often exhibit a relatively low naturalness of these stimuli. In this brief research report, I illustrate how AI-generated videos can successfully be used to overcome some of these limitations. Videos were generated by combining different avatar images (that were also generated with an AI tool) with text messages that either presented statements that were congruent or incongruent with expectations based on the age, gender, or facial emotion expressions of the avatar. In this pilot study, 47 participants watched these videos and rated the plausibility and emotional intensity of each utterance. Despite being fully generated artificially, videos elicited different responses depending on the condition. Incongruences based on social categories (age, gender) engendered lower plausibility ratings while intensity ratings were relatively unaffected. In contrast, intensity ratings for emotion expressions were expectedly higher (irrespective of congruence) but sensitivity to plausibility was affected by the congruence of the facial expression and the statement of the avatar. This pilot study illustrates the potential of AI-generated stimuli for investigating socio-cognitive processes, particularly in research on the integration of social information. KW - AI-generated stimuli KW - facial emotion expressions KW - social categories KW - social cues KW - social expectation violations ER -