Optimizing Cricket Team Selection Using Fuzzy Assignment Problem with Sentiment Analysis

Abstract

This study introduces an innovative approach to cricket team selection by adapting the fuzzy assignment problem framework to allocate players to specific roles (Batsman, Bowler, Wicket Keeper, All-Rounder) based on linguistic performance ratings. Building on the methodology proposed by [1], we employ Triangular Fuzzy Numbers (TFNs) and the Robust Ranking Technique to convert linguistic data (e.g., "Very High" batting ability) into numerical costs. The Modified Revised Ones Assignment Method (ROA), developed by [2, 3], is utilized to achieve an optimal assignment that minimizes costs, thereby enhancing team performance. A novel aspect of this study is the integration of sentiment analysis from social media platforms (e.g., X posts) to incorporate fan perceptions, thereby improving the fairness and public acceptance of selections. The approach is implemented in Python and validated through a case study involving four
players. Results demonstrate an optimal assignment with a total cost of 1.5, verified by the Hungarian algorithm. This method provides a robust, data-driven framework for sports team optimization, with potential applications in other domains requiring linguistic data
processing.