This paper describes a Recommender System that implements a Multiagent System for making personalised context and intention-aware recommendations of Points of Interest (POIs). A twoparted agent architecture was used, with an agent responsible for gathering POIs from a location-based service, and a set of Personal Assistant Agents (PAAs) collecting information about the context and intentions of its respective user. In each PAA were embedded four Machine Learning algorithms, with the purpose of ascertaining how wellsuited these classifiers are for filtering irrelevant POIs, in a completely automatic fashion. Supervised, incremental learning occurs when the feedback on the true relevance of each recommendation is given by the user to his PAA. To evaluate the recommendations' accuracy, we performed an experiment considering three types of users, using different contexts and intentions. As a result, all the PAA had high accuracy, revealing in specific situations F1 scores higher than 87%.
In this paper we report on a game design exercise that focus on the sensoriality and sensemaking participant dimensions for conceiving and evaluating gameplay experience, by framing design intentions, artifact characteristics and user participation. Through this exercise we were able to build understandings of user participation in the soundscape constituting the gameplay scenario. By employing a goal-question-metric approach we demonstrated the viability of using the participation-centric gameplay model dimensions as a basis for the synthesis of gameplay participation indicators and metrics, and their analysis in the context of interactions with a game as soundscape.
A game soundscape often includes sounds that are triggered by the game logic according to the player's actions and to other real time occurrences. The dynamic nature of such triggering events leads to a composition that is not necessarily interesting, at a given moment. We propose a system aiming at the enhancement of the soundscape generated during gameplay. The main component of the system is a module that implements heuristics, which we set to follow principles from Acoustic Ecology and, specifically, the notion of healthy soundscape. In order to inform the heuristics, designers can characterize the sounds being handled by the sound engine, using an API that aims to be accessible and informative about the designer's intentions.We also present reflections on an essay where a game was remade using the proposed system, which helped us to support the feasibility of the proposed system.
A game soundscape often includes sounds that are triggered by the game logic according to the player's actions and to other real time occurrences. The dynamic nature of such triggering events can lead to a composition that is not necessarily interesting, at a given moment. Following principles from Acoustic Ecology, and specifically the notion of healthy soundscape, we propose a system aiming at the moderation of sounds generated during gameplay in a way that the composition retains its communicational meaningfulness. For instance, the system aims to ensure that the soundscape does not get overcrowded by the superimposition of whatever sounds might be triggered, and that the player can actually ear the relevant stimuli. The main component of the system is a module that implements heuristics that free designers from restating accepted sound design principles, and programmers from embedding such intelligence in the game logic. Thus, designers can focus on expressing their design intents, by using an API to create and characterize the sound sources to be handled by the sound engine. The use of this API also conveys a more readable expression of the game's sound design, easing communication and reuse. Hence, this proposal can be particularly relevant during fast prototyping phases, when it can constitute an expedite way to test and refine creative ideas, while avoiding extensive coding and the typical complexity and cost of existing middleware, which is particular relevant for small budget and sound novice practitioners. We finish by presenting results from a proof of concept implementation, and a game remake for evaluating the proposed system.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.