Logo des Repositoriums

Auflistung nach Autor:in "Consul, Saksham"

1 - 2 von 2
  • Konferenzbeitrag
    A Cautionary Tale About AI-Generated Goal Suggestions
    (Mensch und Computer 2022 - Tagungsband, 2022) Lieder, Falk; Chen, Pin-Zhen; Consul, Saksham; Stojcheski, Jugoslav; Pammer-Schindler, Viktoria
    Setting the right goals and prioritizing them might be the most crucial and the most challenging type of decisions people make for themselves, their teams, and their organizations. In this article, we explore whether it might be possible to leverage artificial intelligence (AI) to help people set better goals and which potential problems might arise from such applications. We devised the first prototype of an AI-powered digital goal-setting assistant and a rigorous empirical paradigm for assessing the quality of AI-generated goal suggestions. Our empirical paradigm compares the AI-generated goal suggestions against randomly-generated goal suggestions and unassisted goal-setting on a battery of self-report measures of important goal characteristics, motivation, and usability in a large-scale repeated-measures online experiment. The results of an online experiment with 259 participants revealed that our intuitively compelling goal suggestion algorithm was actively harmful to the quality of the people’s goals and their motivation to pursue them. These surprising findings highlight three crucial problems to be tackled by future work on leveraging AI to help people set better goals: i) aligning the objective function of the AI algorithms with the design goals, ii) helping people quantify how valuable different goals are to them, and iii) preserving the user’s sense of autonomy.
  • Workshopbeitrag
    Leveraging AI for Effective To-Do List Gamification
    (Mensch und Computer 2022 - Workshopband, 2022) Consul, Saksham; Stojcheski, Jugoslav; Lieder, Falk
    Many people procrastinate and struggle to prioritize their most important work. To help their users overcome such problems, gamified productivity tools like Habitica use heuristic point systems that can be counterproductive. We recently proposed a more principled way to compute point values that avoids such problems. Although it was promising in theory, it required large amounts of computation even for very short to-do lists. Here, we present a scalable approximate method that makes our principled approach to to-do list gamification useable in the real world. Our method leverages artificial intelligence to generate a gamified to-do lists, where each task is incentivized by a number of points that communicates how valuable it is in the long-run. What makes our new method more scalable is that it decomposes the problem of computing long-term plans for how the user can best achieve their goals into a hierarchy of smaller planning problems. We assessed the scalability of our method by applying it to to-do lists with increasingly larger numbers of goals, sub-goals, and tasks, and we also increased the number of nested levels of the goal hierarchy. We found that the method can enable web and mobile applications to compute excellent point systems for fairly large to-do lists, with up to 576 tasks spread out over up to 9 different top-level goals. Our method freely available through an API1. This makes it easy to use our method in gamified web applications and mobile apps.