3 Publications at ACM CHI '23 | Hamburg, Germany
(1) Probing a Community-Based Conversational Storytelling Agent, (2) Envisioning Narrative Intelligence, and (3) Exploring Design Cards
Last week, I traveled to Hamburg, Germany, where I shared three of my latest peer-reviewed archival publications at the CHI ‘23 Conference on Human Factors in Computing Systems. Below are links to the papers in the ACM Digital Library.
Probing a Community-Based Conversational Storytelling Agent to Document Digital Stories of Housing Insecurity (Best Paper Award 🏆)
Brett A. Halperin, Gary Hsieh, Erin McElroy, James Pierce, & Daniela K. Rosner
Despite the central role that stories play in social movement-building, they are difficult to sustainably document for many reasons. To explore this challenge, this paper describes the design of a community-based conversational storytelling agent (CSA) to document digital stories of housing insecurity. Building on insights from an ongoing grassroots project, the Anti-Eviction Mapping Project, we share how a study initially focused on CSA-support opened an investigation of the role that artificial intelligence may play in housing justice movements. Drawing from 17 interviews with narrators of housing insecurity experiences and collectors of such stories, we find that collectors perceive opportunities to expand means of documentation with multimedia and multi-language support. Meanwhile, some narrators perceive potential for a CSA to offer therapeutic storytelling experiences and document otherwise unrecorded stories. Yet, CSA encounters also surface perils of machine bias, as well as reduced possibilities of human connections and relations.
https://dl.acm.org/doi/10.1145/3544548.3581109
Envisioning Narrative Intelligence: A Creative Visual Storytelling Anthology
Brett A. Halperin & Stephanie M. Lukin
In this paper, we collect an anthology of 100 visual stories from authors who participated in our systematic creative process of improvised story-building based on image sequences. Following close reading and thematic analysis of our anthology, we present five themes that characterize the variations found in this creative visual storytelling process: (1) Narrating What is in Vision vs. Envisioning; (2) Dynamically Characterizing Entities/Objects; (3) Sensing Experiential Information About the Scenery; (4) Modulating the Mood; (5) Encoding Narrative Biases. In understanding the varied ways that people derive stories from images, we offer considerations for collecting story-driven training data to inform automatic story generation. In correspondence with each theme, we envision narrative intelligence criteria for computational visual storytelling as: creative, reliable, expressive, grounded, and responsible. From these criteria, we discuss how to foreground creative expression, account for biases, and operate in the bounds of visual storyworlds.
https://dl.acm.org/doi/10.1145/3544548.3580744
What is in the Cards: Exploring Uses, Patterns, and Trends in Design Cards
Gary Hsieh, Brett A. Halperin, Evan Schmitz, Yen Nee Chew, & Yuan-Chi Tsen
Card-based design tools—design cards—increasingly present opportunities to support practitioners. However, the breadth and depth of the design card landscape remain underexplored. In this work, we surveyed 103 design practitioners to assess current usages and associated barriers. Additionally, we analyzed and classified 161 decks of design cards from 1952-2020. We held a workshop with four experienced practitioners to generate initial categories, and then coded the remaining decks. We found that the cards contain seven different types of design knowledge: Creative Inspiration; Human Insights; Material & Domain; Methods & Tooling; Problem Definition; Team Building; and Values in Practice. The content of these cards can support designers across design stages; however, most are intended to support the early stages of design (e.g., research and ideation) rather than later design stages (e.g., prototyping and implementation). We share additional patterns uncovered and provide recommendations to support the future development and adoption of these tools.