This paper presents findings from a thinking-aloud protocol exploring mental models in 28 elementary school math teachers during their initial attempt at composing and testing trigger-action rules for a smart tangible educational device. In the study, two sets of event-driven primitives were implemented in an End-User Development platform for guiding teachers with no programming experience in defining new functions of the device: "concrete", based on actual actions performed on the device, and "abstract", based on general definitions of events/actions. With a thematic analysis, we identified three different metaphors that drive participants’ interaction with the device. We discuss how the metaphors influenced performance and how the order of exposition to the two primitive sets impacted their grasping of the trigger-action logic. Our findings suggest the importance of guiding teachers in assuming effective metaphors for performing End-User Development tasks, to empower them to adopt an active role toward digital devices in education.

In this paper, we describe an empirical evaluation of the user's perceived usefulness of recommendations for configuration tasks in a smart home scenario. Our results suggest that while overall recommendations help improve the performance in the task, the psychological traits of Self-efficacy and Need for Cognition play an important role in determining the perceived usefulness of the recommendations. These effects are somehow different from those reported in other studies where recommendations are provided for a choice task rather than a constructive task. Thus, our results offer evidence regarding the importance of incorporating the evaluation of personality traits into the design of configuration constructive tasks in order to make informed decisions on whether and how to provide users with recommendations. Additionally, they show that it is crucial to take into account the nature of the task and, where possible, individual competencies.

Trigger-Action Programming is a commonly used paradigm in End-User Development interfaces, allowing users without programming experience to create new automation systems. Even if considered easy to grasp, this approach poses some challenges: non-programmers often confuse events (instantaneous occurrences) and states (prolonged occurrences), leading to critical errors in the definition of triggers. Although past research has already questioned the effectiveness of the typical if-then structure, there is a limited exploration of which specific linguistic cues might help or hinder users from distinguishing between events and states. Our study, involving 85 non-programmers, examines a broader pool of linguistic aspects, investigating (i) preferences for conjunctions and verbs when describing events and states and (ii) which conjunctions help users accurately differentiate these occurrences. Our results indicate that while participants tended to prefer temporally specific language, such as ” when ” for events and ” while ” for states, some of these conjunctions, like ” when ”, may not support users in accurately identifying and differentiating events from states, similar to the generic ” if ”. These findings underscore the role of specific language on non-programmers’ comprehension and mental representations of triggers. Designing interfaces with more easily graspable linguistic cues and mapping them at the system level may help guide non-programmer users in correctly structuring trigger-action rules.

Gamification has been widely applied in educational contexts to enhance students' motivation and engagement. Its effectiveness has been shown to vary based on individual user preferences, such as age, gender, and player type. This study investigates the relationship between player types and user experience in StandByMe, a gamified educational platform designed to raise awareness about gender-based violence. A total of 61 high school students used the platform for about 35 minutes and completed a user experience questionnaire and the Hexad scale for player types. Results indicate that Free spirits reported higher motivation and overall user experience, while Achievers exhibited lower engagement, possibly due to a lack of clearly structured challenges. Socializers and Disruptors showed no significant relation with user experience. Additionally, demographic factors such as age and gender were related to participants' fun levels and perception of challenge. These findings highlight how users' player type predicts the user experience of a gameful system and should be considered during the design phase. Future research should explore adaptive gamification approaches and specific design modifications to enhance user experience across all player types, both within the StandByMe platform and, more broadly, in gameful systems for the education of sensitive topics.

Personalized learning methods have revolutionized education by allowing tailored teaching approaches to meet individual students’ needs. This approach, supported by educational technologies, aims to engage learners with diverse expertise levels by adapting content and methods accordingly. This demo introduces an End-User Development system that empowers teachers to create and define interactive behaviors of educational tools using Trigger-Action Programming (TAP). The system facilitates the creation of "vocabularies" specific to each learning subject and translates them into verbal primitives for trigger-action rule definition. These rules are then used in the customization of interfaces. This demo presents examples using a tangible device and a web-based educational game aimed to enrich education activities in elementary schools. Future directions include studying teachers’ appropriation of the use of TAP to customize learning material as well as adaptation in new domains and with different devices.

In this paper, we present a study aimed at evaluating how ChatGPT-4 understands end-users’ natural language instructions to express automation rules for smart home applications and how it translates them into Python code ready to be deployed. Our study used 34 natural language instructions written by end users who were asked to automate scenarios presented as visual animations. The results show that ChatGPT-4 can produce coherent and effective code even if the instructions present ambiguities or unclear elements, understanding natural language instructions and autonomously resolving 94% of them. However, the generated code still contains numerous ambiguities that could potentially affect safety and security aspects. Nevertheless, when appropriately prompted, ChatGPT-4 can subsequently identify those ambiguities. This prompts a discussion about prospective interaction paradigms that may significantly improve the immediate usability of the generated code.

Gamification and tangible user interfaces have been shown to enhance pupils’ engagement and their learning experiences. This study presents an evaluation of a simple gamified version of a tangible Internet of Things device (SMARTER) to support math learning. Twenty-one elementary school children participated in a workshop, interacting with the system and providing feedback. Results indicate good usability and a positive attitude toward the system. Children generally liked all the aspects, although the focus on mathematics was slightly lower appreciated. The study highlights the potential of integrating tangible user interfaces and gamified systems to enhance pupils’ engagement in education.

Gender-based violence is widely recognized as a significant societal issue, necessitating a concerted effort to raise awareness about its manifestations and consequences. Serious games have been often used to address the topic, particularly among the younger population. On the other hand, the use of gamification (i.e., integrating game elements to enhance user engagement with the subject) to raise awareness of gender-based violence remains unexplored. To address this gap, we developed a gamified platform aimed at raising awareness of gender-based violence and in particular of the role of gender stereotypes, in young adults. This paper presents the findings of our preliminary mixed-methods evaluation and a comparison between two versions of the platform: one employing cooperative gamification, and the other one based on an individual game modality. While the quantitative results indicate that the current platform may not be sufficient to have a positive effect in participants’ awareness of gender-based violence and attitudes toward bystander behavior, qualitative analyses yield crucial insights into participants’ positive evaluation of the cooperative mode. These analyses provide valuable information for future developments of the platform, and contribute to the exploration of gamification applied to sensitive topics.

In this paper, we propose a new annotation scheme to classify different types of clauses in Terms-and-Conditions contracts with the ultimate goal of supporting legal experts to quickly identify and assess problematic issues in this type of legal documents. To this end, we built a small corpus of Terms-and-Conditions contracts and finalized an annotation scheme of 14 categories, eventually reaching an inter-annotator agreement of 0.92. Then, for 11 of them, we experimented with binary classification tasks using few-shot prompting with a multilingual T5 and two fine-tuned versions of two BERT-based LLMs for Italian. Our experiments showed the feasibility of automatic classification of our categories by reaching accuracies ranging from .79 to .95 on validation tasks.

Algorithmic Recourse aims to provide actionable explanations, or recourse plans, to overturn potentially unfavourable decisions taken by automated machine learning models. In this paper, we propose an interaction paradigm based on a guided interaction pattern aimed at both eliciting the users’ preferences and heading them toward effective recourse interventions. In a fictional task of money lending, we compare this approach with an exploratory interaction pattern based on a combination of alternative plans and the possibility of freely changing the configurations by the users themselves. Our results suggest that users may recognize that the guided interaction paradigm improves efficiency. However, they also feel less freedom to experiment with “what-if” scenarios. Nevertheless, the time spent on the purely exploratory interface tends to be perceived as a lack of efficiency, which reduces attractiveness, perspicuity, and dependability. Conversely, for the guided interface, more time on the interface seems to increase its attractiveness, perspicuity, and dependability while not impacting the perceived efficiency. That might suggest that this type of interfaces should combine these two approaches by trying to support exploratory behavior while gently pushing toward a guided effective solution.

This article explores Human-Centered Artificial Intelligence (HCAI) in medical cytology, with a focus on enhancing the interaction with AI. It presents a Human-AI interaction paradigm that emphasizes explainability and user control of AI systems. It is an iterative negotiation process based on three interaction strategies aimed to (i) elaborate the system outcomes through iterative steps (Iterative Exploration), (ii) explain the AI system's behavior or decisions (Clarification), and (iii) allow non-expert users to trigger simple retraining of the AI model (Reconfiguration). This interaction paradigm is exploited in the redesign of an existing AI-based tool for microscopic analysis of the nasal mucosa. The resulting tool is tested with rhinocytologists. The article discusses the analysis of the results of the conducted evaluation and outlines lessons learned that are relevant for AI in medicine.

In Cooperative Learning (CL), students work together in small groups to achieve shared learning goals.Several studies have proved that CL promotes active learning, social skills development, inclusion, and well-being in the classroom.Technology can support CL-based interventions, providing different tools to increase learners' participation and communication.However, few studies investigated the use of technology-based CL in lower schools.We present a new digital platform, K-DAD, to support CL strategies in Italian primary and lower secondary schools.To develop K-DAD, we used the learning management system Moodle, customizing appearance, interactions, and content architecture to provide a child-friendly e-learning environment.In the platform, several CL activities and tasks were structured to promote environmental awareness as well as diversity, equity, and inclusion.A prototype has been developed and further experimental investigations are needed to estimate the usability and effectiveness of the K-DAD platform.

In this work, we explore the idea of designing a tool to augment the practice of closed-reading a literary text by employing end-user programming practices. The ultimate goal is to help young humanities students learn and appreciate computational thinking skills. The proposed approach is aligned with other methods of applying computer science techniques to explore literary texts (as in digital humanities) but with original goals and means. An initial design concept has been realised as a probe to prompt the discussion among humanities students and teachers. This short paper discusses the design ideas and the feedback from interviews and focus groups involving 25 participants (10 teachers in different humanities fields and 15 university students in humanities as prospective teachers and scholars).

This paper presents a pilot study for an initial assessment of a tangible tool to support end-user programming (EUP) by teachers to facilitate learning mathematics in primary school. The study aimed to explore teachers’ reasoning strategies and mental representations during trigger-action rules composition. The pilot study provided initial insight into the strengths and weaknesses of this approach and useful hints for designing a larger and more robust study

In this paper, we present the preliminary implementation of SMARTER, a tangible tool for supporting children in learning the basics of mathematics, which has been loosely inspired by the Cuisenaire rods. The tool exploits the power of tangible manipulation offered by physical materials coupled with the possibility of providing contextual and engaging feedback provided by digital tools. An original and important goal of the SMARTER tool is to allow teachers to fully customize the experience of use by exploiting end-user development.

This work explores how comic-based digital storytelling can support primary school children in reflecting on situations involving conflict in the classroom. In particular, we focus on investigating three specific aspects: (1) the potential of digital story composition conducted collaboratively or individually, (2) the children's perception on the use of digital storytelling for reflecting on conflicts that might arise in class and, (3) the teachers' experience of introducing a digital tool for collaborative storytelling and comics composition in an educational context. In this paper, we explored these aspects by developing a case study. A class of 12 children and 2 teachers explore the use of a digital tool, named Communics, aimed at creating digital narratives individually and collaboratively. The results show that digital narratives created from collaborative storytelling are longer, more structured, and richer with meaning compared to stories from individual work. Moreover, it emerged that children prefer to work collaboratively, even if it meant compromising, going slower and waiting for their turn. Finally, teachers appreciated the collaborative use of Communics, and in particular, the turn-based feature as children can practice the narrative re-elaboration with a peer while waiting for their turn.

In this paper, we introduce a tool aimed at supporting deep qualitative analysis of digital comics. The tool exploits language-based technologies to facilitate the exploration of relatively large sets of comics. The core idea is that the specific words used in the comics are both an important element of the analysis and an index to navigate and explore the dataset. The design concept has been validated in a pilot study and the findings provide evidence that the approach meets the needs of qualitative analysts with the potential of improving their practices.

Joint narratives are often used in the context of reconciliation interventions for people in social conflict situations, which arise, for example, due to ethnic or religious differences. The interventions aim to encourage a change in attitudes of the participants towards each other. Typically, a human mediator is fundamental for achieving a successful intervention. In this work, we present an automated approach to support remote interactions between pairs of participants as they contribute to a shared story in their own language. A key component is an automated cognitive tutor that guides the participants through a controlled escalation/de-escalation process during the development of a joint narrative. We performed a controlled study comparing a trained human mediator to the automated mediator. The results demonstrate that an automated mediator, although simple at this stage, effectively supports interactions and helps to achieve positive outcomes comparable to those attained by the trained human mediator.

In this paper, we describe a pilot study of a digital storytelling project conducted with primary school children. The study investigates how comic-based storytelling supported by a digital tool, named Communics, can facilitate primary school children in creating stories and in reflecting on situations involving discrimination within the classroom context. In a first stage, two teachers have been involved to negotiate the intervention, as well as define graphical and textual content on which to base the narrations in Communics. In a second stage, we piloted an intervention within a class of 12 children to investigate the scaffolding opportunities offered by Communics as well as different aspects of storytelling, as engagement and motivation, and explore the use of the storytelling practice as a reflective process. Finally, we discuss preliminary insights and suggestions for future studies.

This paper presents a literature review of human- computer interaction works on wearable systems for sports. We selected a corpus of 57 papers and analyzed them through the grounded theory for literature review approach. We identified five themes across the papers: the different research perspectives, the type of sports and sportspeople, the roles of wearables in sports, their wearability, and the different types of feedback. These themes helped us in delineating opportunities for future research: the investigation of different form factors and types of feedback; the consideration of different sportspeople and collaborative tasks; the need of pushing the boundaries of the sports domain; the exploration of the evolution of sports; the interconnection of different devices; and the increase of methodological rigor.

In this paper, we present a playful digital activity for primary school classrooms that promotes sustainable and active mobility by leveraging the daily journey to school into a collaborative educational experience. In the class game, stretches of distance travelled in a sustainable way by each child contributes to the advancement of the whole school on a collective virtual trip. During the trip, several virtual stops are associated with the discovery of playful learning material. The approach has been evaluated in a primary school with 87 pupils and 6 teachers actively involved in the learning activity for 12 continuous weeks. The findings from the questionnaires with parents and the interviews with teachers show a positive effect in terms of children's behavioural change as well as educational value. Indications on the use of class and school collaborative gamification activities for supporting sustainable behavioural change are discussed.

Crowdsourcing for addressing environmental challenges is a promising area in HCI research. This work investigates participation in a crowdsourcing initiative that combined a social-purpose activity with the interest of a company to crowdsource a labour-intensive task. The initiative was based on the deployment of a mobile application for pro-environmental data collection, namely collecting data about weight and type of product packaging. We report the results of a 9-month study conducted within a living lab that involved 96 customers of a large retail store. The analysis of usage logs and patterns of behaviour show different user categories: constant, sprinter and casual users. A survey was conducted to compare those categories as far as demographics, personality traits and usability metrics are concerned. Ten follow-up interviews further investigated motivations behind different usage patterns. The results provide insights on different types of contributors, reporting evidence on what motivated committed and less committed participants.

It is of paramount importance that cultural heritage professionals are directly involved in the design of digitally augmented experiences in their museum spaces. We propose an approach based on a catalogue of reusable narrative and interaction strategies with step-by-step instructions on how to adapt and instantiate them for a specific museum and type of visitors. This work is conducted in the context of the European-funded project meSch.

Drawing on concepts from theories on persuasion, social psychology, and philosophy of language, this article presents the design of an ambient persuasive system that acts as an automatic facilitator by supporting a balanced flow of communication in group conversational activity. The system includes two main components: (a) a context-awareness system that monitors group member non-verbal behavior, and (b) a visualization component that promotes balanced participation, providing targeted directives to participants through peripheral displays. In two empirical studies, a strategy for influencing participant social dynamics based on subtle directives in the form of aesthetically pleasant visual animations was assessed. The findings provide insight on the effect, the acceptability, and the perceived influence of subtle peripheral persuasive messages for ambient displays. The studies indicate that when the participants understand the message intention, the subtle directives have a positive influence on group behavior, and are considered more appealing and less intrusive than overt, language-based messages. Furthermore, it was found that personality traits influenced attitudes towards the system.

In this paper, we propose a mixed-initiative approach to integrate a Q&A site based on a crowd of volunteers with a standard operator-based help desk, ensuring quality of customer service. Q&A sites have emerged as an efficient way to address questions in various domains by leveraging crowd knowledge. However, they lack sufficient reliability to be the sole basis of customer service applications. We built a proof-of-concept mixed-initiative tool that helps a crowd-manager to decide if a question will get a satisfactory and timely answer by the crowd or if it should be redirected to a dedicated operator. A user experiment found that our tool reduced the participants' cognitive load and improved their performance, in terms of their precision and recall. In particular, those with higher performance benefited more than those with lower performance.

In this paper, we present a system that acts as an automatic facilitator by supporting the flow of communication in a group conversation activity. The system monitors the group members' non-verbal behavior and promotes balanced participation, giving targeted directives to the participants through peripheral displays. We describe an initial study to compare two ways of influencing participantsfi social dynamics: overt directives, explicit recommendations of social actions displayed in the form of text; or subtle directives, where the same recommendations are provided in an implicit manner. Our study indicates that, when the participants understand how the implicit messages work, the subtle facilitation is regarded as more useful than the overt one and it is considered to more positively influence the group behavior.

This paper describes a multimodal approach to detect viewers' engagement through psycho-physiological affective signals. We investigate the individual contributions of the different modalities, and report experimental results obtained using several fusion strategies, in both per-clip and per-subject cross-validation settings. A sequence of clips from a short movie was showed to 15 participants, from whom we collected per-clip engagement self-assessments. Cues of the users' affective states were collected by means of (i) galvanic skin response (GSR), (ii) automatic facial tracking, and (iii) electroencephalogram(EEG) signals. The main findings of this study can be summarized as follows: (i) each individual modality significantly encodes the level of engagement of the viewers in response to movie clips, (ii) the GSR and EEG signals provide comparable contributions, and (iii) the best performance is obtained when the three modalities are used together.

A multi-user tabletop interface was designed to support reconciliation of a conflict aimed at shifting hostile attitudes and achieving a greater understanding of another viewpoint. The interface provided a setting for face-to-face shared narration and support for the management of disagreements. The interface allows for escalation and de-escalation of the conflict emerging in the shared narration and requires that participants perform joint actions when a contribution to the story is to be removed from the overall narration. A between-subjects experiment compared the tabletop interface and a desktop multimedia interface with mixed pairs (male Israeli-Jewish and Palestinian-Arab youth). The results demonstrated that the experience with the tabletop interface appears to be motivating and, most importantly, produces at least a short-term shift of attitude toward the other.

The COSPATIAL (Communication and social participation: collaborative technologies for interaction and learning) project explores how we can develop effective and useful educational technologies in the form of shared active surfaces (SASs) and collaborative virtual environments (CVEs) to support the enhancement of social competence skills for children with autism spectrum conditions (ASC). This paper presents a description of the COSPATIAL suite of applications, comprising of two CVE programs and two SAS programs.

In this paper we describe a co-located suite of games on a tabletop device to support social competence training for children with Autism Spectrum Disorder. This suite has been designed to use patterns of collaboration to support therapists in their use of Cognitive-Behavioral Therapy (CBT). In this paper, we discuss the observations collected during a field study where two therapists used the system for social competence training sessions with 8 children. We conclude with lessons learned from meshing software enhanced collaboration within the CBT model.

Museums are both appealing and challenging as an environment for indoor positioning research. By nature, they are dense and rich in objects and information, and as a result they contain more information than a visitor can absorb in a time-limited visit. Many research projects have explored the potential of novel technologies to support information delivery to museum visitors. Having an accurate visitor position is a key factor in the success of such projects. In spite of numerous technologies experimented with, there is no prevailing indoor positioning technology. Each technology has its benefits as well as its limitations. In addition, museums have their own constrains when it comes to installation of sensors in their space. In the framework of the PIL project, a flexible "light weight" proximity based positioning system was developed and deployed at the Hecht museum and a general framework for indoor positioning is proposed. The inherent limitations of the basic technology are addressed by an abstract reasoning layer and by a dialog with the user.

In this paper we propose a new type of system explicitly aimed at influencing immediate behavior in an informal, non goal-oriented co-located small group. The state of the group dynamics is automatically assessed in order for the system to continuously plan and deploy minimalist strategies using evocative means to influence behavior, rather than explicit recommendations. A key aspect of our approach is that the main interaction channel is left for direct human-to-human interaction, while no large conscious elaboration effort nor actions are meant by the user toward the interface. We present here the concept and a working implementation of a prototype system targeted to a museum scenario. The system has the form of a table in the museum cafe, and is aimed at inducing a group of friends to talk about the content of their visit to the museum.

Cultural heritage is an area that has recently drawn research attention, especially for exploring ways to harness novel mobile technologies for supporting visitors. The main benefit of these novel technologies is their ability to provide personalized, context-aware information services to their users. However, the use of context-awareness is connected to a fundamental issue of proactiveness – should the system keep the user in control all the time and only respond to user requests, or should the system take initiative and propose its services when needed? Proactiveness of mobile visitors' guides brings with it a possibility for better service to the user at the cost of taking control out of the user's hand. The amount of choice given to visitors is another key issue. With the vast amount of information available for each exhibit, adaptation of the amount of information by limiting the number of content items, could be warranted to filter the information according to the visitors needs. However, it is not clear how reducing choice in terms of the number of content items that are presented to the visitor affects visitor behavior and satisfaction. We examined these issues in a controlled user study conducted with actual museum visitors; comparing usage, behavior patterns, and attitudes of visitors using three versions of a location-aware mobile museum guide.

COSPATIAL is a multi-disciplinary project that is using collaborative virtual reality and tabletop devices for training social competence within the theoretical framework of Cognitive-Behavioral Therapy. Our ultimate objective is to create a set of patterns for designing applications in collaborative technologies that are suitable for children with autism as well as typically developing children. We describe the rationale for CBT-informed design of collaborative technologies and background related work. Initial steps towards development of a design framework are presented, with illustrated examples from one concept design application for each of the two technologies under consideration. The project is ongoing and an iterative design process will be used to develop and evaluate the applications and further refine the design framework.

The domestic environment is more than a place where to live. It is a territory of meaning, a place where pleasure, affect and aesthetics are deeply interwoven with the functional and utilitarian dimensions. With the aging process, the home is progressively invested with new meanings and functions, and becomes the emotional center of older people's life.

Acceptance of adaptive museum guides raises important issues stemming from both the nature of the scenario (museum visit) and the very kind of technological approach adopted (adaptivity). As to the former, museum guides play a utilitarian role in a hedonic scenario; at present, however, it is not clear how this reflects on the balance between intrinsic and extrinsic motivations for guide acceptance. The adaptive nature of the guide, in turn, raises questions about the impact of the opaqueness of the system behavior, of the alleged loss of perceived control over the interaction, and the role of presentation personalization. All these issues are explored in this paper by means of a model derived from TAM and comprising both extrinsic and intrinsic motivational constructs. The results of a analysis of data from 115 subjects show that the motivational structure of the guide usage is mainly utilitarian, with intrinsic motivations playing a role insofar as they acquire an instrumental value. The impact of the control issues on acceptability is low and indirect, while the importance of the feedback provided by the system is confirmed. Finally, personalization positively impacts on user engagement, this way strengthening the empirical and theoretical groundings for work in adaptive systems.

According to recent studies, a museum visit by a small group (e. g. a family or a few friends) can be considered successful if conversation about the experience develops among its members. Often people stop at the museum café to have a break during the visit or before leaving. The museum café is the location that we foresee as ideal to introduce a tabletop interface meant to foster the conversation of the visitors.

So called intractable conflicts may benefit from more modest and socially oriented approaches than those based on classical conflict resolution techniques. This paper is inspired by theories on small group intervention in a conflict. The general claim is that participants may achieve a greater understanding of and appreciation for the other's viewpoint under conditions that support partaking in a tangible joint task and creating a shared narration. Our goal was to design a methodology wherein the extent to which technology contributes to conflict negotiation and resolution could be assessed. Specifically, a co-located interface for producing a joint narration as a tool for favouring reconciliation is presented and discussed. The results of an initial set of studies where the interface was used by Arab and Jewish youth in Israel provided insight into the usability of the various components of the technology and of the paradigm.

This paper targets the automatic detection of personality traits in a meeting environment by means of audio and visual features; information about the relational context is captured by means of acoustic features designed to that purpose. Two personality traits are considered: Extraversion (from the Big Five) and the Locus of Control. The classification task is applied to thin slices of behaviour, in the form of 1-minute sequences. SVM were used to test the performances of several training and testing instance setups, including a restricted set of audio features obtained through feature selection. The outcomes improve considerably over existing results, provide evidence about the feasibility of the multimodal analysis of personality, the role of social context, and pave the way to further studies addressing different features setups and/or targeting different personality traits.

In this paper, an influence model is used to recognize functional roles played during meetings. Previous works on the same corpus demonstrated a high recognition accuracy using SVMs with RBF kernels. In this paper, we discuss the problems of that approach, mainly over-fitting, the curse of dimensionality and the inability to generalize to different group configurations. We present results obtained with an influence modeling method that avoid these problems and ensures both greater robustness and generalization capability.

Visitors often tend to visit museums in groups, mainly with family or friends, yet most of the today mobile museum guides focus on supporting the individual visitor. The technology described in this paper allows supporting groups of visitors in addition to individuals by providing context-aware services aimed at supporting the whole group. These include context-aware communication and alerting services that are provided by the museum visitor's guide system developed in the framework of the PIL (PEACH-Israel) project, as an example case of a larger variety of possible context-aware services.

Xface is a set of open source tools for creation of embodied conversational agents (ECAs) using MPEG4 and keyframe based rendering driven by SMIL-Agent scripting language. Xface Toolkit, coupled with SMIL-Agent scripting serves as a full 3D facial animation authoring package. Xface project is initiated by Cognitive and Communication Technologies (TCC) division of FBK-irst (formerly ITC-irst). The toolkit is written in ANSI C++, and is open source and platform independent.

In this paper we describe a pilot study for an intervention aimed at enhancing social skills in high functioning children with autism. We found initial evidences that the use of a, social interaction and may lessen the repetitive behaviors typical of autism. These positive effects also appear to be transferred to other tasks following the intervention. We hypothesize that the effect is due to some unique characteristics of the interfaces used, in particular enforcing some tasks to be done together through the use of multiple-user GUI actions.

In this paper, we present a study concerning psychological ownership for digital entities in the context of collaborative working environments. In the first part of the paper we present a conceptual framework of ownership: various issues such as definition, effects, target factors and behavioral manifestation are explicated. We then focus on ownership marking, a behavioral manifestation that is closely tied to psychological ownership. We designed an experiment using DiamondTouch Table to investigate the effect of two of the most widely used ownership markers on users' attitudes and performance. Both performance and attitudinal differences were found, suggesting the significant role of ownership and ownership markers in the groupware and interactive workspaces design.

In this paper, we discuss a machine learning approach to automatically detect functional roles played by participants in a face to face interaction. We shortly introduce the coding scheme we used to classify the roles of the group members and the corpus we collected to assess the coding scheme reliability as well as to train statistical systems for automatic recognition of roles. We then discuss a machine learning approach based on multi-class SVM to automatically detect such roles by employing simple features of the visual and acoustical scene. The effectiveness of the classification is better than the chosen baselines and although the results are not yet good enough for a real application, they demonstrate the feasibility of the task of detecting group functional roles in face to face interactions.

Synthetic characters are an effective modality to convey messages to the user, provide visual feedback about the system internal understanding of the communication, and engage the user in the dialogue through emotional involvement. In this paper we argue for a fine-grain distinction of the expressive capabilities of synthetic agents: avatars should not be considered as an indivisible modality but as the synergic contribution of different communication channels that, properly synchronized, generate an overall communication performance. In this view, we propose SMIL-AGENT as a representation and scripting language for synthetic characters, which abstracts away from the specific implementation and context of use of the character. SMIL-AGENT has been defined starting from SMIL 0.1 standard specification and aims at providing a high-level standardized language for presentations by different synthetic agents within diverse communication and application contexts.

The paper presents a first prototype of a handheld museum guide delivering contextualized information based on the recognition of drawing details selected by the user through the guide camera. The resulting interaction modality has been analyzed and compared to previous approaches. Finally, alternative, more scalable, solutions are presented that preserve the most interesting features of the system described.

Museum visitors can continue interacting with museum exhibits even after they have left the museum. We can help them do this by creating a report that includes a basic, personalized narration of their visit, the items and relationships they found most interesting, pointers to additional related online information, and suggestions for future visits to the current and other museums. In this work we describe the automatic generation of personalized natural language reports to help create one episode in an ongoing coherent sequence of cultural activities.

In this work, we present a study about adaptation on a mobile museum guide aiming at investigating the relationships between personality traits and the attitudes toward some basic dimensions of adaptivity. Each participant was exposed to two simulated systems that realized an adaptive and a non-adaptive version, respectively, on each of the dimensions investigated. The study showed interesting effects of Big Five personality traits on acceptance of the adaptivity dimensions; in particular conscientiousness, creativity and stability. Locus of control seemed to have a limited yet quite selective effect on delegating to the system the choice of follow-ups.

In this paper, we describe the first prototype of a system called StoryTable, aimed at supporting a group of children in the activity of storytelling. The system is based on a special multi-user touchable device (the MERL DiamondTouch) and it was designed with the purpose of enforcing collaboration between children. The paper discusses how the main design choices were influenced by the paradigm of cooperative learning and presents two observational studies to assess the effects of the different design choices on the storytelling activity.

The issue of the seamless interleaving of interaction with a mobile device and stationary devices is addressed, in a typical situation of educational entertainment: the visit to a museum. Some of the salient elements of the described work are the emphasis on multimodality in the dynamic presentation and coherence throughout the visit.The adopted metaphor is of a kind of contextualized TV-like presentation, useful for engaging (young) visitors. On the mobile device, personal video clips are dynamically generated from personalized verbal presentations; on larger stationary screens distributed throughout the museum, further background material and additional information is provided. A virtual presenter follows the visitors in their experience and gives advice on both types of devices and on the museum itself.

In this paper, we introduce a framework to automatically build associations between pieces of information in different media. The key idea is to use a semantic model to co-index the entire information space and exploit the reasoning capabilities of the knowledge base in defining strategies of navigation. The main advantage over traditional hypermedia lies primarily in the ease with which the system can be updated since the new data is automatically connected to the rest of the information.Examples are given from a prototype hypermedia to navigate documentation about a fresco in the Buonconsiglio Castle in Trento, Italy.

Multimodality is a powerful concept for dealing with dialogue cohesion in a human–computer natural language (NL)‐centered system. This work is a modest step toward more effective exploitation of the potentially large bandwidth of communication provided by this situation. The relations between exploration, navigation, and NL‐based communication are discussed in general and with reference to two prototypes. Light cognitive load feedback and direct manipulation are proposed so that user and system can cooperate in mutually establishing the structure of the ongoing dialogue. The main points are: (i) use of an appropriate dialogue structure to constrain inference in the anaphora resolution process; (ii) use of a graphical representation of the structure, to limit the problem of opacity; (iii) allowance for the possibility of direct manipulation on this representation, to avoid the necessity of operating linguistically at the metalevel. The context of the work is within NL‐centered multimodal information access systems, in which basic entities are pairs (most commonly question and answer). A dialogue model is provided by a modified version of the centering model; it is both sufficiently simple to be displayed in an intuitive fashion on the screen, and sufficiently powerful to give accurate results. An extension of the discourse model, oriented to the treatment of deixis, is also proposed. Finally, steps toward an overall approach to the integration of navigational and mediated aspects of interaction are discussed.