El impacto de las aplicaciones estadísticas en el periodismo deportivo: estudio comparativo entre valoraciones algorítmicas y humanas en el fútbol de élite
Loading...
Identifiers
Publication date
Advisors
Tutors
Editors
Journal Title
Journal ISSN
Volume Title
Publisher
Ediciones Complutense
Abstract
Este estudio compara valoraciones periodísticas y algorítmicas del rendimiento de futbolistas de élite en un contexto de creciente influencia de plataformas como Sofascore y Flashscore. Mediante un diseño observacional transversal, se analizó una muestra intencional de 60 jugadores en 10 partidos de relevancia (temporada 2024-2025). Para cada jugador se recopilaron puntuaciones de ambos algoritmos y de dos medios europeos, seleccionados de un total de 13 (7 tradicionales, 6 nativos digitales). Se aplicaron análisis descriptivos e inferenciales para examinar tendencias centrales y dispersión, convergencia entre sistemas, impacto del resultado del partido, variación por posición y rol del jugador, divergencias por tipología y país del medio, patrones por medio específico, además de casos cualitativos paradigmáticos. Los resultados revelan que los medios asignan puntuaciones significativamente más bajas (media 6,76; p < 0,001) y con mayor variabilidad (CV = 26,4 %) que los algoritmos (Sofascore: 7,53, CV = 11,8 %; Flashscore: 7,33, CV = 12,4 %). La correlación entre algoritmos es muy alta (r = 0,858) y mayor que entre medios y algoritmos (r ≈ 0,72). Todos los sistemas muestran sensibilidad significativa al resultado (p ≤ 0,01), pero la magnitud del sesgo es mucho mayor en los medios (-2,01 puntos entre victoria y derrota) que en los algoritmos (-0,75/-0,96). La convergencia es mayor para jugadores destacados (d > 0,90). No se hallaron diferencias significativas por posición ni tipología mediática. Los análisis exploratorios sugieren que la cultura editorial de cada medio es más determinante que su país o tipología. Se concluye que ambos sistemas son epistemológicamente complementarios, y su integración –no sustitución– enriquece la evaluación deportiva.
This study compares journalistic and algorithmic evaluations of elite football players’ performance in a context of growing influence of platforms such as Sofascore and Flashscore. Using a cross-sectional observational design, a purposive sample of 60 players across 10 high-profile matches (2024–2025 season) was analyzed. For each player, ratings were collected from both algorithms and two European media outlets, selected from a total of 13 (7 traditional and 6 digital native). Descriptive and inferential analyses were applied to examine central tendencies and dispersion, convergence between systems, the impact of match outcome, variation by player position and role, divergences by media type and country, patterns by specific outlet, and paradigmatic qualitative cases. Results show that media assign significantly lower ratings (mean 6.76; p < 0.001) and with greater variability (CV = 26.4 %) compared to algorithms (Sofascore: 7.53, CV = 11.8 %; Flashscore: 7.33, CV = 12.4 %). The correlation between algorithms is very high (r = 0.858) and higher than between media and algorithms (r ≈ 0.72). All systems display statistically significant sensitivity to match outcome (p ≤ 0.01), but the magnitude of bias is markedly greater in media (-2.01 points between win and loss) than in algorithms (-0.75/-0.96). Convergence is significantly stronger for standout players (d > 0.90). No significant differences were found by position or media type. Exploratory analyses suggest that each outlet’s editorial culture is more decisive than its country or media type. It is concluded that both systems are epistemologically complementary, and their integration—not substitution—enriches sports performance evaluation.
This study compares journalistic and algorithmic evaluations of elite football players’ performance in a context of growing influence of platforms such as Sofascore and Flashscore. Using a cross-sectional observational design, a purposive sample of 60 players across 10 high-profile matches (2024–2025 season) was analyzed. For each player, ratings were collected from both algorithms and two European media outlets, selected from a total of 13 (7 traditional and 6 digital native). Descriptive and inferential analyses were applied to examine central tendencies and dispersion, convergence between systems, the impact of match outcome, variation by player position and role, divergences by media type and country, patterns by specific outlet, and paradigmatic qualitative cases. Results show that media assign significantly lower ratings (mean 6.76; p < 0.001) and with greater variability (CV = 26.4 %) compared to algorithms (Sofascore: 7.53, CV = 11.8 %; Flashscore: 7.33, CV = 12.4 %). The correlation between algorithms is very high (r = 0.858) and higher than between media and algorithms (r ≈ 0.72). All systems display statistically significant sensitivity to match outcome (p ≤ 0.01), but the magnitude of bias is markedly greater in media (-2.01 points between win and loss) than in algorithms (-0.75/-0.96). Convergence is significantly stronger for standout players (d > 0.90). No significant differences were found by position or media type. Exploratory analyses suggest that each outlet’s editorial culture is more decisive than its country or media type. It is concluded that both systems are epistemologically complementary, and their integration—not substitution—enriches sports performance evaluation.
Description
Bibliographic citation
García-Fernández R. J. . y Quian A. (2026). El impacto de las aplicaciones estadísticas en el periodismo deportivo: estudio comparativo entre valoraciones algorítmicas y humanas en el fútbol de élite . Estudios sobre el Mensaje Periodístico, 32(2), 453-475. https://doi.org/10.5209/esmp.103702
Relation
Has part
Has version
Is based on
Is part of
Is referenced by
Is version of
Requires
Publisher version
https://doi.org/10.5209/esmp.103702Sponsors
Ministerio de Ciencia, Innovación y Universidades del Gobierno de España: proyecto de I D i «Inteligencia artificial en medios digitales en España: efectos y roles» (PID2024-156034OB-C22), financiado por MICIU/AEI/10.13039/501100011033 y «FEDER/UE».
Rights
Attribution 4.0 International








