Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Aspect-based Sentiment Evaluation of Chess Moves (ASSESS): an NLP-based Method for Evaluating Chess Strategies from Textbooks

Haifa Alrdahi, Riza Batista-Navarro

TL;DR

The paper addresses evaluating chess moves described in textbooks by applying Aspect-Based Sentiment Analysis (ABSA) to move-action phrases that jointly encode the player and action. It proposes a domain-specific ABSA framework, constructs a fine-grained LEAP-derived dataset with move-action annotations, and fine-tunes RoBERTa-based models to predict sentiment toward moves. Empirical results show that domain-tuned models improve minority-class detection when data are oversampled, and that sentiment labels correlate with engine-derived outcomes from Stockfish, suggesting ABSA can serve as a text-driven evaluation function. The work demonstrates the potential of NLP to complement traditional search-based chess analysis and highlights avenues for future integration with board state grounding and reinforcement learning for deeper strategic understanding.

Abstract

The chess domain is well-suited for creating an artificial intelligence (AI) system that mimics real-world challenges, including decision-making. Throughout the years, minimal attention has been paid to investigating insights derived from unstructured chess data sources. In this study, we examine the complicated relationships between multiple referenced moves in a chess-teaching textbook, and propose a novel method designed to encapsulate chess knowledge derived from move-action phrases. This study investigates the feasibility of using a modified sentiment analysis method as a means for evaluating chess moves based on text. Our proposed Aspect-Based Sentiment Analysis (ABSA) method represents an advancement in evaluating the sentiment associated with referenced chess moves. By extracting insights from move-action phrases, our approach aims to provide a more fine-grained and contextually aware `chess move'-based sentiment classification. Through empirical experiments and analysis, we evaluate the performance of our fine-tuned ABSA model, presenting results that confirm the efficiency of our approach in advancing aspect-based sentiment classification within the chess domain. This research contributes to the area of game-playing by machines and shows the practical applicability of leveraging NLP techniques to understand the context of strategic games.

Aspect-based Sentiment Evaluation of Chess Moves (ASSESS): an NLP-based Method for Evaluating Chess Strategies from Textbooks

TL;DR

The paper addresses evaluating chess moves described in textbooks by applying Aspect-Based Sentiment Analysis (ABSA) to move-action phrases that jointly encode the player and action. It proposes a domain-specific ABSA framework, constructs a fine-grained LEAP-derived dataset with move-action annotations, and fine-tunes RoBERTa-based models to predict sentiment toward moves. Empirical results show that domain-tuned models improve minority-class detection when data are oversampled, and that sentiment labels correlate with engine-derived outcomes from Stockfish, suggesting ABSA can serve as a text-driven evaluation function. The work demonstrates the potential of NLP to complement traditional search-based chess analysis and highlights avenues for future integration with board state grounding and reinforcement learning for deeper strategic understanding.

Abstract

The chess domain is well-suited for creating an artificial intelligence (AI) system that mimics real-world challenges, including decision-making. Throughout the years, minimal attention has been paid to investigating insights derived from unstructured chess data sources. In this study, we examine the complicated relationships between multiple referenced moves in a chess-teaching textbook, and propose a novel method designed to encapsulate chess knowledge derived from move-action phrases. This study investigates the feasibility of using a modified sentiment analysis method as a means for evaluating chess moves based on text. Our proposed Aspect-Based Sentiment Analysis (ABSA) method represents an advancement in evaluating the sentiment associated with referenced chess moves. By extracting insights from move-action phrases, our approach aims to provide a more fine-grained and contextually aware `chess move'-based sentiment classification. Through empirical experiments and analysis, we evaluate the performance of our fine-tuned ABSA model, presenting results that confirm the efficiency of our approach in advancing aspect-based sentiment classification within the chess domain. This research contributes to the area of game-playing by machines and shows the practical applicability of leveraging NLP techniques to understand the context of strategic games.
Paper Structure (15 sections, 3 figures, 4 tables)

This paper contains 15 sections, 3 figures, 4 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. ABSA for Chess Move Evaluation
  4. Dataset Description
  5. Annotation Process
  6. Data Augmentation
  7. Transformer Models for ABSA
  8. Generic ABSA Models
  9. Fine-tuned ABSA Models
  10. Evaluation
  11. ABSA Results
  12. ABSA vs. Stockfish Analysis
  13. Error Analysis
  14. Conclusion
  15. Bibliographical References

Figures (3)

  • Figure 1: The annotation interface as shown in Prodigy.
  • Figure 2: Different types of knowledge infusion for aspect-based sentiment classification models.
  • Figure 3: Heatmap based on a sample (10%) to visualise the correlation between the sentiment labels predicted by our baseline ABSA model for a move ('Positive', 'Neutral', 'Negative'), and the probable outcome ('Win', 'Draw', 'Lose') of the move provided by the Stockfish engine.