The field of natural language processing is moving towards the development of more accurate and efficient models for detecting abusive language, analyzing sentiment, and understanding nuances of human communication. Recent studies have focused on creating models that can identify and classify negative sentiments, detect hate speech, and analyze the tone and intent behind language. In the area of sports analytics, researchers are working on developing more sophisticated models for evaluating player and team performance, predicting game outcomes, and analyzing fan sentiment. The use of machine learning and deep learning techniques is becoming increasingly prevalent in this field, with applications in player tracking, game state reconstruction, and action valuation. One notable trend is the increasing use of large language models and transfer learning techniques to improve the accuracy and efficiency of natural language processing tasks. Another trend is the growing importance of sports analytics in informing coaching decisions, player evaluations, and fan engagement strategies. Notable papers include:

• A study on detecting abusive language targeting women on social media, which achieved a macro F1 score of 0.729 using a BERT-based model.
• A survey on action valuation in sports, which introduced a taxonomy with nine dimensions related to the task and identified essential characteristics of effective valuation methods.
• A paper on game state reconstruction, which presented a robust end-to-end pipeline for tracking players and achieved state-of-the-art results in the SoccerNet Game State Reconstruction Challenge 2024.