PhD student — feature selection approach based on metaheuristic algorithms for text mining
Text
ClassificationAs a PhD researcher specializing in text mining and meta-heuristic optimization, I focus on the intersection of data extraction and algorithmic efficiency to support model learning. My research involves designing advanced feature selection approaches to identify and structure high-value textual representations, which are essential for the training and evaluation of supervised learning systems. This work directly supports data labeling excellence by automating the transformation of unstructured raw text into precise, high-quality learning targets through optimized selection processes. • Text Mining research aligned with supervised NLP modeling: Developing methodologies to refine raw data into high-signal inputs for model training. • Optimization-driven improvement of workflows: Utilizing meta-heuristic algorithms to streamline feature selection, reducing noise and increasing the reliability of training datasets. • Evaluation of labeled text outputs: Assessing the accuracy and logical consistency of model outputs against optimized benchmarks to ensure high-performance model alignment.