People often remember parts of conversations that are important to them, such as something personal, useful, or emotionally engaging. These memories help shape relationships, guide decisions, and influence how we communicate in the future. While many computer systems can already track emotions or attention in group settings, no previous research has looked at how specific moments in conversations are stored in memory or how this process could be predicted using technology.

On the path towards training computer systems to predict such memorable moments, this dissertation first introduces a new dataset called the MeMo corpus (Chapter 2). It includes group video conversations along with direct reports from participants about which moments they remembered. The data was collected in a way that reflects real-life conversations, using repeated video calls and memory reports that are linked to specific moments in time.

The study in chapter 3 then asks whether affective signals, such as emotional tone or energy in a conversation, could help predict what people will remember. These kinds of emotional signals are often used in artificial intelligence systems. However, the results show that emotional signals alone are not enough to explain what people remember from a conversation.

Next, in chapter 4, the dissertation looks at other behavioural signs, such as where people were looking and who was speaking. These signals were found to be significantly linked with memory: for example, people tend to remember parts of a conversation where there was shared attention or dynamic speaking patterns. Using these signals, simple computer models were able to predict which parts of the conversation were more likely to be remembered. The study also looked at why people remembered certain moments and found that many of them were related to personal relevance or social connection.

This work shows that it is possible to build systems that recognise which parts of a conversation are more memorable. This can be useful for improving automatic meeting tools, personal assistants, and other technologies that support communication and augment memory.

Collaborating in a purposive group, whether face-to-face or virtually, involves continuously expressing emotions and interpreting those of other group members. As such, understanding group affect is essential to comprehending how groups interact and succeed in collaborative efforts. In this study, we move beyond individual-level affect and investigate group-level affect - a collective phenomenon that reflects the shared mood or emotions among group members at a particular moment. As the first in the literature, we gather annotations for group-level affective expressions in purposive group interactions using a fine-grained temporal approach (15 s windows) that also captures the inherent dynamics of this collective construct. To this end, we extensively train annotators and develop an annotation procedure specifically tuned to capture the entire scope of the group interaction from one interaction moment to the next. In addition, we model the ebb and flow of group affect by accounting for the underlying convergence (driven by emotional contagion) and divergence (resulting from emotional reactivity) of affective expressions among group members. To capture these interpersonal dynamics, we employ two approaches: (i) extracting synchrony-based handcrafted features from both audio and visual modalities, and (ii) introducing a novel, data-driven graph neural network to model interpersonal dynamics among group members. Our results highlight the advantages of the graph network over the handcrafted features in modeling group affect, while also emphasizing the importance of temporal modeling and incorporating multimodal cues. Additionally, our analysis of affective convergence and divergence reveals that groups tend to diverge in their social signals during neutral collective affect, while exhibiting convergence during more emotionally intense moments. These insights are drawn from comparative results across both modeling techniques.

In ongoing and consecutive conversations with persons, a social robot has to determine which aspects to remember and how to address them in the conversation. In the health domain, important aspects concern the health-related goals, the experienced progress (expressed sentiment) and the ongoing motivation to pursue them. Despite the progress in speech technology and conversational agents, most social robots lack a memory for such experience sharing. This paper presents the design and evaluation of a conversational memory for personalized behavior change support conversations on healthy nutrition via memory-based motivational rephrasing. The main hypothesis is that referring to previous sessions improves motivation and goal attainment, particularly when references vary. In addition, the paper explores how far motivational rephrasing affects user's perception of the conversational agent (the virtual Furhat). An experiment with 79 participants was conducted via Zoom, consisting of three conversation sessions. The results showed a significant increase in participants' change in motivation when multiple references to previous sessions were provided.

Human perception and behavior are affected by the situational context, in particular during social interactions. A recent study demonstrated that humans perceive visual stimuli differently depending on whether they do the task by themselves or together with a robot. Specifically, it was found that the central tendency effect is stronger in social than in non-social task settings. The particular nature of such behavioral changes induced by social interaction, and their underlying cognitive processes in the human brain are, however, still not well understood. In this paper, we address this question by training an artificial neural network inspired by the predictive coding theory on the above behavioral data set. Using this computational model, we investigate whether the change in behavior that was caused by the situational context in the human experiment could be explained by continuous modifications of a parameter expressing how strongly sensory and prior information affect perception. We demonstrate that it is possible to replicate human behavioral data in both individual and social task settings by modifying the precision of prior and sensory signals, indicating that social and non-social task settings might in fact exist on a continuum. At the same time, an analysis of the neural activation traces of the trained networks provides evidence that information is coded in fundamentally different ways in the network in the individual and in the social conditions. Our results emphasize the importance of computational replications of behavioral data for generating hypotheses on the underlying cognitive mechanisms of shared perception and may provide inspiration for follow-up studies in the field of neuroscience.

How human-like do conversational robots need to look to enable long-term human-robot conversation? One essential aspect of long-term interaction is a human's ability to adapt to the varying degrees of a conversational partner's engagement and emotions. Prosodically, this can be achieved through (dis)entrainment. While speech-synthesis has been a limiting factor for many years, restrictions in this regard are increasingly mitigated. These advancements now emphasise the importance of studying the effect of robot embodiment on human entrainment. In this study, we conducted a between-subjects online human-robot interaction experiment in an educational use-case scenario where a tutor was either embodied through a human or a robot face. 43 English-speaking participants took part in the study for whom we analysed the degree of acoustic-prosodic entrainment to the human or robot face, respectively. We found that the degree of subjective and objective perception of anthropomorphism positively correlates with acoustic-prosodic entrainment.