@article{compensis2026_115359,
  title = {Using AI-Generated Avatar Interactions To Study Socio-Affective Functions of Feedback Signals in Language : an Exploratory Experimental Study on Head Nods},
  author = {Compensis, Paul},
  year = {2026},
  pages = {117-136},
  publisher = {Otto-Friedrich-Universität},
  address = {Bamberg},
  urn = {urn:nbn:de:bvb:473-irb-115359x},
  url = {https://fis.uni-bamberg.de/handle/uniba/115359},
  language = {eng},
  abstract = {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.},
  keywords = {Feedback in interaction, Backchannels, Head nods, Verbal continuers, Affiliation, Empathy, Virtual avatars}
}

@article{compensis2026_115358,
  title = {Using AI-Generated Avatar Interactions To Study Socio-Affective Functions of Feedback Signals in Language : an Exploratory Experimental Study on Head Nods},
  author = {Compensis, Paul},
  year = {2026},
  journal = {Journal of nonverbal behavior},
  volume = {50},
  number = {1},
  pages = {117-136},
  publisher = {Springer},
  address = {New York, NY},
  issn = {1573-3653},
  doi = {10.1007/s10919-026-00500-y},
  url = {https://fis.uni-bamberg.de/handle/uniba/115358},
  language = {eng},
  abstract = {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.},
  keywords = {Feedback in interaction, Backchannels, Head nods, Verbal continuers, Affiliation, Empathy, Virtual avatars}
}

@inproceedings{compensis2026_114968,
  title = {Information Overload in Information Seeking with Conversational Agents : A Survey and Design Considerations},
  author = {Compensis, Paul},
  year = {2026},
  pages = {474-479},
  publisher = {Otto-Friedrich-Universität},
  address = {Bamberg},
  urn = {urn:nbn:de:bvb:473-irb-114968x},
  url = {https://fis.uni-bamberg.de/handle/uniba/114968},
  language = {eng},
  abstract = {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.},
  keywords = {conversational information seeking, information overload, humanagent interaction, conversational agent, afect}
}

@inproceedings{compensis2026_114902,
  title = {Information Overload in Information Seeking with Conversational Agents : A Survey and Design Considerations},
  author = {Compensis, Paul},
  year = {2026},
  booktitle = {Proceedings of the 2026 Conference on Human Information Interaction and Retrieval},
  pages = {474-479},
  publisher = {ACM},
  address = {New York, NY},
  isbn = {979-8-4007-2414-5},
  doi = {10.1145/3786304.3787886},
  url = {https://fis.uni-bamberg.de/handle/uniba/114902},
  language = {eng},
  abstract = {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.},
  keywords = {conversational information seeking, information overload, humanagent interaction, conversational agent, afect}
}

@article{compensis2026_113136,
  title = {Assessing the integration of social information using AI-generated videos : a brief research report},
  author = {Compensis, Paul},
  year = {2026},
  pages = {1-9},
  publisher = {Otto-Friedrich-Universität},
  address = {Bamberg},
  urn = {urn:nbn:de:bvb:473-irb-113136x},
  url = {https://fis.uni-bamberg.de/handle/uniba/113136},
  language = {eng},
  abstract = {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.},
  keywords = {AI-generated stimuli, facial emotion expressions, social categories, social cues, social expectation violations}
}

@article{compensis2026_113104,
  title = {Assessing the integration of social information using AI-generated videos : a brief research report},
  author = {Compensis, Paul},
  year = {2026},
  journal = {Frontiers in psychology},
  volume = {16},
  number = {1505843},
  pages = {1-9},
  publisher = {Frontiers Research Foundation},
  address = {Lausanne},
  issn = {1664-1078},
  doi = {10.3389/fpsyg.2025.1505843},
  url = {https://fis.uni-bamberg.de/handle/uniba/113104},
  language = {eng},
  abstract = {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.},
  keywords = {AI-generated stimuli, facial emotion expressions, social categories, social cues, social expectation violations}
}

