Search

Conversational agents (CAs) are gaining traction in both industry and academia, especially with the advent of generative AI and large language models. As these agents are used more broadly by members of the general public and take on a number of critical use cases and social roles, it becomes important to consider the values embedded in these systems. This consideration includes answering questions such as 'whose values get embedded in these agents?' and 'how do those values manifest in the agents being designed?' Accordingly, the aim of this paper is to present the Value-Sensitive Conversational Agent (VSCA) Framework for enabling the collaborative design (co-design) of value-sensitive CAs with relevant stakeholders. Firstly, requirements for co-designing value-sensitive CAs which were identified in previous works are summarised here. Secondly, the practical framework is presented and discussed, including its operationalisation into a design toolkit. The framework facilitates the co-design of three artefacts that elicit stakeholder values and have a technical utility to CA teams to guide CA implementation, enabling the creation of value-embodied CA prototypes. Finally, an evaluation protocol for the framework is proposed where the effects of the framework and toolkit are explored in a design workshop setting to evaluate both the process followed and the outcomes produced., Comment: 23 pages, 8 figures

In conversational analyses, humans manually weave multimodal information into the transcripts, which is significantly time-consuming. We introduce a system that automatically expands the verbatim transcripts of video-recorded conversations using multimodal data streams. This system uses a set of preprocessing rules to weave multimodal annotations into the verbatim transcripts and promote interpretability. Our feature engineering contributions are two-fold: firstly, we identify the range of multimodal features relevant to detect rapport-building; secondly, we expand the range of multimodal annotations and show that the expansion leads to statistically significant improvements in detecting rapport-building., Comment: 14 pages

Many professional services are provided through text and voice systems, from voice calls over the internet to messaging and emails. There is a growing need for both individuals and organizations to understand these online conversations better and find actionable insights. One method that allows the user to explore insights is to build intuitive and rich visualizations that illustrate the content of the conversation. In this paper, we present a systematic survey of the various methods of visualizing a conversation and research papers involving interactive visualizations and human participants. Findings from the survey show that there have been attempts to visualize most, if not all, of the types of conversation that are taking place digitally, from speech to messages and emails. Through this survey, we make two contributions. One, we summarize the current practices in the domain of visualizing dyadic conversations. Two, we provide suggestions for future dialogue visualization research., Comment: 19 pages, 26 figures

Automatic Speech Recognition (ASR) systems have proliferated over the recent years to the point that free platforms such as YouTube now provide speech recognition services. Given the wide selection of ASR systems, we contribute to the field of automatic speech recognition by comparing the relative performance of two sets of manual transcriptions and five sets of automatic transcriptions (Google Cloud, IBM Watson, Microsoft Azure, Trint, and YouTube) to help researchers to select accurate transcription services. In addition, we identify nonverbal behaviors that are associated with unintelligible speech, as indicated by high word error rates. We show that manual transcriptions remain superior to current automatic transcriptions. Amongst the automatic transcription services, YouTube offers the most accurate transcription service. For non-verbal behavioral involvement, we provide evidence that the variability of smile intensities from the listener is high (low) when the speaker is clear (unintelligible). These findings are derived from videoconferencing interactions between student doctors and simulated patients; therefore, we contribute towards both the ASR literature and the healthcare communication skills teaching community., Comment: 10 pages, 2 figures

We report a variation with temperature ($T$) of the effective interdimeric interaction $J^\prime_{\mathrm{eff}}$ in the antiferromagnetic (AFM) copper dimeric organic compound Cu$_2$[TzTs]$_4$ [N-thiazol-2-yl-toluenesulfonamidate Cu$^\mathrm{II}$]. This $T$ dependence was obtained from measurements of the effects in the electron paramagnetic resonance (EPR) spectra of the proposed quantum phase transition associated to the exchange narrowing processes. Cu$_2$[TzTs]$_4$ contains exchange coupled pairs of Cu$^\mathrm{II}$ spins $\mathbf{S_\mathrm{A}}$ and $\mathbf{S_\mathrm{B}}$ ($S$ = 1/2), with intradimeric AFM exchange coupling $J_0$ = (-115$\pm$1) cm$^{-1}$ ($\mathcal{H}_\mathrm{ex} = -J_\mathrm{0} \mathbf{S_\mathrm{A}}\cdot \mathbf{S_\mathrm{B}}$). The variation of the EPR line width of single crystals with field orientation around a "magic angle" where the transitions intersect, as well as the integrated signal intensity of the so-called "U-peak" of the powder spectrum were measured as a function of $T$. Modeling these data using arguments of exchange narrowing in the adiabatic regime considering the angular variation of the single crystal spectra and a geometric description, we find that $|J^\prime_{\mathrm{eff}}|$ associated with the exchange frequency $\omega_{ex}$ is negligible for $T<<|J_\mathrm{0}/k_\mathrm{B}|$, when the units are uncoupled, and $|J^\prime_{\mathrm{eff}}|$ = (0.080 $\pm$ 0.005) cm$^{-1}$ ($|J^\prime_{\mathrm{eff}}/J_0|$ = 7.0$\times$10$^{-4}$) at 298 K. Within this $T$-interval, two ranges of $J^\prime_{\mathrm{eff}}$ with linear temperature variation but different slopes, with a kink at $\sim$80 K, are observed and discussed. This $T$-dependence arises from the growing population of the triplet state and its relevance in the properties of various arrays of DUs is discussed. Our experimental procedures and results are compared with those of previous works., Comment: 7 pages, 4 figures, accepted for publication in Physical Review B

We study the spin chain behavior, a transition to 3D magnetic order and the magnitudes of the exchange interactions for the metal-amino acid complex Cu(D,L-alanine)2.H2O, a model compound to investigate exchange couplings supported by chemical paths characteristic of biomolecules. Thermal and magnetic data were obtained as a function of temperature (T) and magnetic field (B0). The magnetic contribution to the specific heat, measured between 0.48 and 30 K, displays above 1.8 K a 1D spin-chain behavior that can be fitted with an intrachain antiferromagnetic (AFM) exchange coupling constant 2J0 = (-2.12 $\pm$ 0.08) cm$^{-1}$, between neighbor coppers at 4.49 {\AA} along chains connected by non-covalent and H-bonds. We also observe a narrow specific heat peak at 0.89 K indicating a phase transition to a 3D magnetically ordered phase. Magnetization curves at fixed T = 2, 4 and 7 K with B0 between 0 and 9 T, and at T between 2 and 300 K with several fixed values of B0 were globally fitted by an intrachain AFM exchange coupling constant 2J0 = (-2.27 $\pm$ 0.02) cm$^{-1}$ and g = 2.091 $\pm$ 0.005. Interchain interactions J1 between coppers in neighbor chains connected through long chemical paths with total length of 9.51 {\AA} are estimated within the range 0.1 < |2J1| < 0.4 cm$^{-1}$, covering the predictions of various approximations. We analyze the magnitudes of 2J0 and 2J1 in terms of the structure of the corresponding chemical paths. The main contribution in supporting the intrachain interaction is assigned to H-bonds while the interchain interactions are supported by paths containing H-bonds and carboxylate bridges, with the role of the H-bonds being predominant. We compare the obtained intrachain coupling with studies of compounds showing similar behavior and discuss the validity of the approximations allowing to calculate the interchain interactions., Comment: 10 pages, 4 figures