International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395-0056
Volume: 13 Issue: 02 | Feb 2026
p-ISSN: 2395-0072
www.irjet.net
CONTEXT-AWARE RESUME SCREENING WITH LAYOUT, TIMELINE AND MULTI-LABEL INTELLIGENCE Mrs. P. Swathi1,G. Riya Reddy2, J .Vaishnavi 3, G.Rajalaxmi4, A. Varshith5 1Assistant Professor, Department of IT, TKR College of Engineering and Technology, Telangana, India 2,3,4,5B.Tech Students, Department of IT, TKR College of Engineering and Technology, Telangana, India
---------------------------------------------------------------------***---------------------------------------------------------------------
Abstract - Recruitment has become a highly data-intensive
aligning candidate profiles with job requirements in a more intelligent and fair manner.
process, with organizations often receiving thousands of resumes for a single job opening. Manual resume screening is time consuming, inconsistent, and susceptible to human bias, highlighting the need for intelligent and automated hiring solutions. This project presents an advanced AI-powered resume screening and candidate evaluation system aimed at improving the efficiency, accuracy, and fairness of modern recruitment workflows. The proposed system automates the ingestion and parsing of resumes across multiple formats, extracting structured information such as personal details, educational background, professional experience, skills, and achievements. To move beyond traditional keyword based filtering, the platform employs a multi-factor evaluation framework that integrates semantic similarity analysis, TFIDF weighting, contextual embeddings, and experience based scoring to assess candidate suitability holistically. State-of-theart language models, including BERT and FLAN-T5, are finetuned for tasks such as resume classification, content summarization, and multi-label skill extraction, enabling deeper contextual understanding of candidate profiles.
1.1 Challenges Context-Aware Resume Understanding Using Layout Intelligence Layout intelligence plays a crucial role in understanding resumes beyond plain text by analyzing how information is visually organized within the document. Resumes contain structured sections such as education, experience, skills, certifications, and projects, which are often represented using headings, columns, font styles, and spacing. A contextaware system leverages layout analysis techniques to correctly identify and separate these sections, ensuring that information is interpreted in the correct semantic context. For example, the same skill mentioned under a “Projects” section may carry different importance compared to one listed under “Work Experience.” By preserving spatial and structural relationships, layout-aware models reduce misclassification errors and improve information extraction accuracy. This intelligence also helps handle diverse resume formats, templates, and design styles used by candidates. Ultimately, layout-based context understanding enables automated screening systems to read resumes in a way that closely resembles human interpretation, leading to more reliable and meaningful candidate evaluation.
Keywords : AI-powered Recruitment, Resume Screening, Candidate Evaluation, Natural Language Processing (NLP), Resume Parsing, Semantic Similarity, TF-IDF, Contextual Embeddings, BERT, FLAN-T5, Skill Extraction.
1. INTRODUCTION
1.2 Timeline Analysis and Multi-Label Intelligence for Intelligent Screening
The rapid growth of digital recruitment platforms has resulted in organizations receiving thousands of resumes for a single job opening, making manual resume screening timeconsuming, inconsistent, and prone to human bias. Traditional automated resume screening systems mainly rely on keyword matching, which often fails to capture the true context, structure, and career progression of a candidate. These systems ignore important aspects such as resume layout, employment timelines, and the possibility that a candidate may be suitable for multiple roles simultaneously. As a result, many qualified candidates are overlooked, while irrelevant resumes may pass initial screening. To overcome these limitations, context-aware resume screening has emerged as a promising solution. By integrating layout understanding, timeline analysis, and multi-label intelligence, modern systems can evaluate resumes more holistically and accurately. This approach enables recruiters to make better hiring decisions by
© 2026, IRJET
|
Impact Factor value: 8.315
Timeline analysis focuses on understanding the chronological progression of a candidate’s career by examining employment durations, gaps, role transitions, and overlapping experiences. This temporal understanding allows the system to assess career stability, growth patterns, and relevance of experience to a specific job role. Instead of treating all experiences equally, the system prioritizes recent and long-term roles that align with the job requirements. In addition, multi-label intelligence enables the model to assign multiple suitable job categories or skill labels to a single resume. This is particularly useful in modern job markets where candidates often possess interdisciplinary skills and are eligible for more than one role. By combining timeline insights with multi-label classification, the system provides a richer and more flexible assessment of candidate suitability. This approach improves shortlisting accuracy, reduces
|
ISO 9001:2008 Certified Journal
|
Page 234