We are pleased to announce our very first joint publication! It is an academic paper where we introduce the SYMBIOTIK framework together with an extensive discussion of the current challenges and opportunities for adaptive user interfaces. Here is the abstract:
User interface adaptations for Information Visualisation (InfoVis) have yet to unlock their potential in critical decision-making scenarios, like emergency rooms or self-driving cars. We argue that future solutions should consider a user-centric approach guided by context awareness and emotion sensing capabilities. In this regard, we propose an innovative adaptive framework inspired by symbiosis principles where humans and machines cooperate and co-evolve to support decision making processes. We also discuss the most pressing challenges in adaptive user interfaces to achieve this vision and propose a series of integrative solutions to advance the field.
In this paper, we argue that InfoVis technologies provide a way to expand and enhance our innate cognitive abilities, and enable us to accomplish a range of tasks, from simple (e.g., company revenue assessment) to intractable (e.g., air-traffic control). However, depending on the timing and context, we may have a greater or lesser ability to make rapid and effective decisions. Yet our ability to do so based on fast-flowing streams of data may be decisive. In this regard, we propose that Artificial Intelligence (AI) enhanced with context-aware attributes will play a key role in leading the necessary advancements for next-generation adaptive InfoVis systems.
To fulfill this goal, we need to define what is “awareness” and how to implement it computationally. We further need to incorporate basic elements of social functioning by means of an altruistic, multi-agent environment, as well as emotion recognition capabilities (via cross-modal communication) for establishing the sensing and the affective, which play a fundamental role in our social interactions.
The SYMBIOTIK framework facilitates a more natural dialogue between humans and adaptive systems to support critical decision-making processes. Importantly, this requires that machines are equipped with emotion sensing and expressing capabilities. With these abilities, machines can start to reason, which increases their potential as intelligent partners. To this end, we have chosen to deviate from classic exploration mechanisms for decision making and propose the investigation of exploration-conscious criteria that will allow for adaptation and learning to be manifested in a more autonomous manner.
The paper (available online very soon) will be presented at the Workshop on Future of Computational Approaches for Understanding and Adapting User Interfaces as part of the very prestigious ACM SIGCHI Conference on Human Factors in Computing Systems, known as CHI. Here is the official reference:
- Luis A. Leiva, Ioannis Arapakis, Michalis Vakalellis, Jean Vanderdonckt. Context-aware Adaptive Visualizations for Critical Decision Making. CHI Workshop on Future of Computational Approaches for Understanding and Adapting User Interfaces, 2023.