En este artículo presentamos los potencia­les de las redes basadas en la API Google Vision para el estudio de las imágenes en lí­nea, abordando tres modalidades importan­tes como parte de una metodología visual crítica: el contenido de la propia imagen, su forma específica de “audienciación” a través de referencias web (o metadatos de la ima­gen) y los sitios de circulación de la imagen. En primer lugar, definimos conceptual y técnicamente diferentes redes construidas a partir de ciertas características de visión artificial: imagen-etiqueta, imagen-entidades web e imagen-dominio. En segundo lugar, presentamos un diagrama de protocolo de investigación que ilustra cómo construir redes de imágenes con sus respectivas des­cripciones o sitios de circulación. En tercer lugar, discutimos las potencialidades de las redes de visión artificial como dispositivos de investigación, enfatizando sus (trans) formaciones relacionales de datos y sus especificidades interpretativas. Se presen­tarán tres diferentes estudios de caso como ejemplo. En conclusión, sostenemos que una metodología visual de este tipo requiere prácticas técnicas críticas que tengan en cuenta las múltiples capas de mediación técnica que están involucradas.

In this paper we present the design of research protocol diagrams as a didactic tool in communication design education. The goal is to teach critical aspects of dataset design processes to design students. The context is a five-month course of Data Visualization addressed to master students in Communication Design. For the last five years, the course has been structured in three phases that gradually introduce students to the demanding issues deriving from communication with data in complex situations. In the second phase, students learn how to map and present -through an interactive report -, a controversial issue based on data coming from online sources. The process is question-driven: each group starts with a set of research questions, defines a protocol for data collection and analysis, and produces research findings using data visualizations. In this phase, students are asked to critically reflect on data collection as a design activity and to visually communicate the dataset design process creating protocol diagrams.Dataset design is a critical aspect of the entire research process, raising technical and ethical considerations. From our point of view, designing a dataset means dealing with data as an artifact, as the result of a series of steps leading to the construction of the dataset that will be encoded through data visualization. Even if the protocol diagram represents all the steps of the research, from the question to the final visualization, the most important part is the visual representation of the dataset design process.Visual representation of processes by diagrams is an established practice dating back more than one hundred years. While research protocol diagrams have been widely used in other scientific disciplines to represent processes, they can be repurposed for the field of Communication Design for educational purposes.In this context, protocol diagrams have two functions at different times: before the final delivery, when the diagram is continually updated as the research goes on, is a negotiation tool which helps students in previewing the possible path they should follow to complete the analysis, in disentangling and correlating individual actions, in examining, doubting and legitimizing the arbitrary choices they are led to make in the process of dataset design and finally is a tool for discussing within the group work and with teachers during the weekly reviews.Once students complete their research, they submit a final report that includes the protocols, visualizations, and main findings. Hence, the protocol diagram becomes a dissemination tool addressed both to researchers or future students that want to replicate the same process. Students are free to choose the shape of the diagram they prefer, and they are not provided with international standards to follow. Usually, results are hybrids forms of process charts and activity diagrams attributable to the visual archetype of the flow-chart. The protocol diagram teaches students about the non-objective, situated and interpretative natu...

Where are the frontiers of Human-Computer Interaction? What theories, methodologies, tools, and sensitivities do researchers, designers and practitioners need to explore uncharted territories? These are the questions that inspired CHItaly 2021, the 14th edition of the biannual conference of the Italian SIGCHI Chapter. Some initial answers are documented in the proceedings and summarised in this foreword alongside a reflection on future frontiers of hybrid scientific conferences.The original focus of inquiry was on transcending disciplinary, communication and national boundaries, reaching out to new scholars, engaging the public, and supporting internationalisation. The COVID-19 pandemics abruptly challenged us to explore unexpected frontiers of space and time in evolving virtualities fraught with uncertainties. Unlike most human-computer interaction conferences, CHItaly 2021 was planned as a hybrid meeting with the aim of reconfiguring physical and digital spaces to mutual benefit. The Free University of Bozen-Bolzano infrastructured the physical space for scholars and citizens within changing local, national and international safety legislation. The technical chair (Fabio Butussi) and the digital frontiers chairs (Fabio Morreale and Ilaria Torre) infrastructured the connection between Bozen-Bolzano and the rest of the world.The conference started on July the 11th with the first edition of the Interactive Experiences track at CHItaly. Marìa Menéndez-Blanco, Ceçil Uğur Yavuz and Jennifer Schubert curated this hybrid exhibition to connect artists, the conference attendees, the local population and the virtual public. It included eleven artefacts authored by international artists, researchers and designers to spark foundational critical discourses, such as reflections on AI and user profiling, human-technology symbiosis, and digital obsolescence. In parallel, six workshops (selected by Barbara Rita Barricelli and Catia Prandi) provided the venues for speculating about equality, diversity and inclusion in machine learning and virtual reality, imagining trans-urban futures, reflecting on socio-political consequences of digitalisation in rural regions, and exploring the space of outdoors-related HCI, virtual games and extended realities. Finally, the doctoral colloquium, chaired by Fabio Paternò and Daniela Fogli, provided a venue for young researchers to share and refine their work.v

In this paper we present Top Tom, a digital platform whose goal is to provide analytical and visual solutions for the exploration of a dynamic corpus of user‐generated messages and media articles, with the aim of i) distilling the information from thousands of documents in a low‐dimensional space of explainable topics, ii) cluster them in a hierarchical fashion while allowing to drill down to details and stories as constituents of the topics, iii) spotting trends and anomalies. Top Tom implements a batch processing pipeline able to run both in near‐real time with time stamped data from streaming sources and on historical data with a temporal dimension in a cold start mode. The resulting output unfolds along three main axes: time, volume and semantic similarity (i.e. topic hierarchical aggregation). To allow the browsing of data in a multiscale fashion and the identification of anomalous behaviors, three visual metaphors were adopted from biological and medical fields to design visualizations, i.e. the flowing of particles in a coherent stream, tomographic cross sectioning and contrast‐like analysis of biological tissues. The platform interface is composed by three main visualizations with coherent and smooth navigation interactions: calendar view, flow view, and temporal cut view. The integration of these three visual models with the multiscale analytic pipeline proposes a novel system for the identification and exploration of topics from unstructured texts. We evaluated the system using a collection of documents about the emerging opioid epidemics in the United States.

The XAI Primer showcases a collection of items clustered according their mutual similarity By zooming in, clusters reveal single projects, represented by glyphs. network LAYERBy zooming in, clusters reveal single projects, represented by glyphs.The last layer of explorations, shows the relations among projects, artificial intelligence strategies and media.