Predicting In-Game Actions from Interviews of NBA Players
Sports competitions are widely researched in computer and social science, with the goal of understanding how players act under uncertainty. Although there is an abundance of computational work on player metrics prediction based on past performance, very few attempts to incorporate out-of-game signal...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
The MIT Press
2020-07-01
|
| Series: | Computational Linguistics |
| Online Access: | http://dx.doi.org/10.1162/coli_a_00383 |
| _version_ | 1797795376793649152 |
|---|---|
| author | Nadav Oved Amir Feder Roi Reichart |
| author_facet | Nadav Oved Amir Feder Roi Reichart |
| author_sort | Nadav Oved |
| collection | DOAJ |
| description | Sports competitions are widely researched in computer and social science, with the goal of understanding how players act under uncertainty. Although there is an abundance of computational work on player metrics prediction based on past performance, very few attempts to incorporate out-of-game signals have been made. Specifically, it was previously unclear whether linguistic signals gathered from players’ interviews can add information that 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 data set of transcripts from key NBA players’ pre-game interviews and their in-game performance metrics, totalling 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 utilize both textual input and past-performance 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 a latent Dirichlet allocation–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. |
| first_indexed | 2024-03-13T03:18:10Z |
| format | Article |
| id | doaj.art-66b43b8683cc48249e038c9c29c54721 |
| institution | Directory Open Access Journal |
| issn | 1530-9312 |
| language | English |
| last_indexed | 2024-03-13T03:18:10Z |
| publishDate | 2020-07-01 |
| publisher | The MIT Press |
| record_format | Article |
| series | Computational Linguistics |
| spelling | doaj.art-66b43b8683cc48249e038c9c29c547212023-06-25T14:50:05ZengThe MIT PressComputational Linguistics1530-93122020-07-0146310.1162/coli_a_00383Predicting In-Game Actions from Interviews of NBA PlayersNadav OvedAmir FederRoi ReichartSports competitions are widely researched in computer and social science, with the goal of understanding how players act under uncertainty. Although there is an abundance of computational work on player metrics prediction based on past performance, very few attempts to incorporate out-of-game signals have been made. Specifically, it was previously unclear whether linguistic signals gathered from players’ interviews can add information that 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 data set of transcripts from key NBA players’ pre-game interviews and their in-game performance metrics, totalling 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 utilize both textual input and past-performance 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 a latent Dirichlet allocation–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.http://dx.doi.org/10.1162/coli_a_00383 |
| spellingShingle | Nadav Oved Amir Feder Roi Reichart Predicting In-Game Actions from Interviews of NBA Players Computational Linguistics |
| title | Predicting In-Game Actions from Interviews of NBA Players |
| title_full | Predicting In-Game Actions from Interviews of NBA Players |
| title_fullStr | Predicting In-Game Actions from Interviews of NBA Players |
| title_full_unstemmed | Predicting In-Game Actions from Interviews of NBA Players |
| title_short | Predicting In-Game Actions from Interviews of NBA Players |
| title_sort | predicting in game actions from interviews of nba players |
| url | http://dx.doi.org/10.1162/coli_a_00383 |
| work_keys_str_mv | AT nadavoved predictingingameactionsfrominterviewsofnbaplayers AT amirfeder predictingingameactionsfrominterviewsofnbaplayers AT roireichart predictingingameactionsfrominterviewsofnbaplayers |