Examinando por Autor "Riquelme, Fabian"

Mostrando 1 - 2 de 2
  • Miniatura
    Ítem
    Can Analytics of Speaking Time Serve as Indicators of Effective Team Communication and Collaboration?
    (ACM, 2021) Salinas, Omar; Riquelme, Fabian; Muñoz, Roberto; Cechinel, Cristian; Martinez, Roberto; Monsalves, Diego
    People with effective teamwork skills, such as collaboration or leadership, are highly demanded in the workplace. In turn, educational providers have adopted active learning methodologies, such as collaborative problem-solving. However, the objective evaluation of collaboration at scale still is a challenge. This paper explores the relationship between quantitative measures obtained from automated transcriptions of speech and qualitative indicators of effective collaboration. An omnidirectional microphone and an artificial intelligence algorithm were used to collect speaking data from 20 triads of students discussing and building a concept map. The study focused on validating the potential value of speech recording devices to quantify the dynamics of communication networks by comparing quantitative metrics obtained from them with an established rating scheme for measuring the extent of collaboration. Results showed a relationship between the standard deviations of the speaking times of the participants in each group and the evaluation obtained from the qualitative rubrics of communication and interpersonal relationships. Thus, the extent to which all group members contribute to the discourse can potentially serve as an indicator of effective group work.
  • Miniatura
    Ítem
    Social influence under improved multi-objective metaheuristics
    (ACS, 2021) Riquelme, Fabian; Muñoz, Francisco; Olivares, Rodrigo
    The influence maximization problem (IMP) and the least cost influence problem (LCI) are two relevant and widely studied problems in social network analysis. The first one consists of maximizing the influence spread in a social network, starting with a given seed size of actors; the second one consists of minimizing the seed set to reach a given number of influenced nodes. Recently, both problems have been studied together with a multi-objective metaheuristic approach. In this work, diffusion filter restrictions based on the network topology are proposed to reduce the search space and thus improving the convergence speed of the solutions. This proposal allows increasing the quality of the results. As the influence spread model, the Linear Threshold model will be used. The solution is tested in three social networks of different sizes, finding promising improvements in harder instances.