Analyzing sports commentary in order to automatically recognize events and extract insights

Yanis Miraoui
7/18/2023
cs.CLcs.LGstat.ML

Official code: yanismiraoui/Analyzing-sports-commentary-in-order-to-automatically-recognize-events-and-extract-insights (7 stars, last commit 2023-07-21).

Abstract

In this paper, we carefully investigate how we can use multiple different Natural Language Processing techniques and methods in order to automatically recognize the main actions in sports events. We aim to extract insights by analyzing live sport commentaries from different sources and by classifying these major actions into different categories. We also study if sentiment analysis could help detect these main actions.

View on arXivView PDF

Code Implementations(1)

yanismiraoui/Analyzing-sports-commentary-in-order-to-automatically-recognize-events-and-extract-insightsOfficial70%

Investigate how we can use multiple different Natural Language Processing techniques and methods in order to automatically recognize the main actions in sports events

73Jupyter NotebookJan 13, 20223 years ago
commentarymachine-learningnatural-language-processingsentiment-analysissports+1 more

Similar Papers

Sports Intelligence: Assessing the Sports Understanding Capabilities of Language Models through Question Answering from Text to Video

79% match2024

Do We Need Large VLMs for Spotting Soccer Actions?

79% match2025

Deep Learning for Sports Video Event Detection: Tasks, Datasets, Methods, and Challenges

78% match2025

OSL-ActionSpotting: A Unified Library for Action Spotting in Sports Videos

77% match2024

CS-lol: a Dataset of Viewer Comment with Scene in E-sports Live-streaming

77% match2023

MatchTime: Towards Automatic Soccer Game Commentary Generation

77% match1 repo1042024

Cite this paper

@article{miraoui2023analyzing,
  title  = {Analyzing sports commentary in order to automatically recognize events and extract insights},
  author = {Yanis Miraoui},
  year   = {2023},
  eprint = {2307.10303},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2307.10303v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2307.10303.svg)](https://codeofpaper.com/paper/2307.10303)

Discussion