GraphRank Pro+: Advancing Talent Analytics Through Knowledge Graphs and Sentiment-Enhanced Skill Profiling
Sirisha Velampalli, Chandrashekar Muniyappa
TL;DR
GraphRank Pro+ tackles the challenge of extracting structured talent signals from semi-structured resumes at scale by converting resumes into a weighted Knowledge Graph using a skill-sentiment gazetteer and edge-weight propagation. The pipeline processes resumes via NLP techniques, constructs skill-project edge weights, and learns JobSeeker-Skill strengths from project-level signals, implemented in Neo4j. Key results show Skill Extraction precision $=92\%$, recall $=88\%$, F1 $=90\%$; Sentiment accuracy $=85\%$; Top-10 resume ranking accuracy $=90\%$, demonstrating superior performance over traditional baselines. The approach enables targeted filtering, ranking, and advanced talent analytics, with future work including Graph Neural Networks for similarity search and DeepWalk-based analysis of job shifts to inform workforce planning.
Abstract
The extraction of information from semi-structured text, such as resumes, has long been a challenge due to the diverse formatting styles and subjective content organization. Conventional solutions rely on specialized logic tailored for specific use cases. However, we propose a revolutionary approach leveraging structured Graphs, Natural Language Processing (NLP), and Deep Learning. By abstracting intricate logic into Graph structures, we transform raw data into a comprehensive Knowledge Graph. This innovative framework enables precise information extraction and sophisticated querying. We systematically construct dictionaries assigning skill weights, paving the way for nuanced talent analysis. Our system not only benefits job recruiters and curriculum designers but also empowers job seekers with targeted query-based filtering and ranking capabilities.