Predicting In-game Actions from Interviews of NBA Players

Abstract

Sports competitions are widely researched in computer and social science, with the goal of understanding how players act under uncertainty. While there is an abundance of computational work on player metrics prediction based on past performance, very few attempts to incorporate out-ofgame signals have been made. Specifically, it was previously unclear whether linguistic signals gathered from players' interviews can add information which does not appear in performance metrics. To bridge that gap, we define text classification tasks of predicting deviations from mean in NBA players' in-game actions, which are associated with strategic choices, player behavior and risk, using their choice of language prior to the game. We collected a dataset of transcripts from key NBA players' pre-game interviews and their in-game performance metrics, totalling in 5,226 interview-metric pairs. We design neural models for players' action prediction based on increasingly more complex aspects of the language signals in their open-ended interviews. Our models can make their predictions based on the textual signal alone, or on a combination of that signal with signals from past-performance metrics. Our text-based models outperform strong baselines trained on performance metrics only, demonstrating the importance of language usage for action prediction. Moreover, the models that employ both textual input and pastperformance metrics produced the best results. Finally, as neural networks are notoriously difficult to interpret, we propose a method for gaining further insight into what our models have learned. Particularly, we present an LDA-based analysis, where we interpret model predictions in terms of correlated topics. We find that our best performing textual model is most associated with topics that are intuitively related to each prediction task and that better models yield higher correlation with more informative topics. 1

SOCCER: An Information-Sparse Discourse State Tracking Collection in the Sports Commentary Domain

“…Another similar dataset, BALLGAME (Keshet et al, 2011) is comprised of baseball commentary with annotated events and timestamps, but it contains less than 20 games and the annotation is unavailable online. Some work focuses on sports-related inference of player performance metrics (Oved et al, 2019) or game outcomes (Velichkov et al, 2019) that predict full-time results based on signals from pre-game player interviews. However, no in-game sequential contexts are provided in these datasets.…”

CausaLM: Causal Model Explanation Through Counterfactual Language Models

“…Another interesting concept that we can explore using the reviews dataset is Topics, as captured by the Latent Dirichlet Allocation (LDA) model (Blei, Ng, and Jordan 2003). Topics capture high-level semantics of documents, and are widely used in NLP for many language understanding purposes (Boyd-Graber et al 2017;Oved, Feder, and Reichart 2019). Topics are qualitatively different from Adjectives, as Adjectives are concrete and local while Topics are abstract and global.…”